CN118968097A - Image detection method, device, computer equipment, readable storage medium and program product - Google Patents
Image detection method, device, computer equipment, readable storage medium and program product Download PDFInfo
- Publication number
- CN118968097A CN118968097A CN202411283422.4A CN202411283422A CN118968097A CN 118968097 A CN118968097 A CN 118968097A CN 202411283422 A CN202411283422 A CN 202411283422A CN 118968097 A CN118968097 A CN 118968097A
- Authority
- CN
- China
- Prior art keywords
- image
- detected
- icon
- design
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/04817—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance using icons
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the field of data processing, and particularly discloses an image detection method, an image detection device, computer equipment, a readable storage medium and a program product. The method comprises the following steps: acquiring a design image to be detected corresponding to a target object; icon extraction is carried out on a plurality of image layers of the design image to be detected respectively, so that layer icons in at least one image layer are obtained; if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image characteristic information of the design image to be detected, and inquiring the similar abnormal image corresponding to the design image to be detected according to the image characteristic information and the target layer icon; and under the condition that similar abnormal images corresponding to the design images to be detected are inquired, determining that the target object does not possess copyrights of the design images to be detected. By adopting the method, the image detection can be accurately carried out.
Description
Technical Field
The present application relates to the field of data processing technology, and in particular, to an image detection method, an image detection apparatus, a computer device, a computer readable storage medium, and a computer program product.
Background
With the development of science and technology, image detection is a hot topic of great concern. The enterprise judges whether the image is an infringing image or not by detecting the image, and then deletes the image possibly causing infringement so as to reduce the loss of the enterprise caused by using the infringement image.
Currently, the method for image detection includes: obtaining an image to be detected, directly inquiring a similar image with the similarity exceeding a preset threshold value from an image blacklist database, and judging the image to be an infringement image if the similar image with the similarity exceeding the preset threshold value is inquired, wherein the image to be detected is quite similar to the similar image. However, the conventional image detection method has a problem of insufficient accuracy.
Disclosure of Invention
Based on this, it is necessary to provide an accurate image detection method, apparatus, computer device, computer readable storage medium and computer program product in view of the above technical problems.
In a first aspect, the present application provides an image detection method, including:
acquiring a design image to be detected corresponding to a target object;
icon extraction is carried out on a plurality of image layers of the design image to be detected respectively, so that layer icons in at least one image layer are obtained;
if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image characteristic information of the design image to be detected, and inquiring the similar abnormal image corresponding to the design image to be detected according to the image characteristic information and the target layer icon;
And under the condition that similar abnormal images corresponding to the design images to be detected are inquired, determining that the target object does not possess copyrights of the design images to be detected.
In one embodiment, extracting image feature information of the design image to be detected, and querying a similar abnormal image corresponding to the design image to be detected according to the image feature information and the target layer icon, further includes:
Inquiring similar normal images corresponding to the design images to be detected from a preset normal image library;
Under the condition that similar normal images are not inquired, extracting to-be-detected image characteristic information of the to-be-detected design image from a preset abnormal image library, and inquiring similar abnormal images corresponding to the to-be-detected design image according to the to-be-detected image characteristic information and the target layer icon.
In one embodiment, the image feature information to be detected includes image feature vector information to be detected and a graying image to be detected;
According to the feature information of the image to be detected and the icon of the target image layer, inquiring the similar abnormal image corresponding to the design image to be detected, including:
Acquiring a layer icon to be matched of an image to be matched, feature vector information of the image to be matched and a gray-scale image to be matched from images to be matched of a preset abnormal image library;
Inquiring a target parameter matched with at least one of the target layer icon, the image feature vector information to be detected and the gray image to be detected from the image layer icon to be matched, the image feature vector information to be matched and the gray image to be matched;
And determining the image to be matched corresponding to the inquired target parameter as a similar abnormal image.
In one embodiment, if the copyright identification result of any target layer icon in each layer icon indicates that whether the target object has the copyright of the design image to be detected cannot be identified, before extracting the image feature information of the design image to be detected, the method further includes:
aiming at any target layer icon in each layer icon, acquiring a signature object identifier and an icon name identifier of the target layer icon;
Determining a rights object of the target layer icon based on the signature object identification and the icon name identification;
and determining whether the target object owns the copyright of the copyright object, and obtaining the copyright identification result of the target layer icon.
In one embodiment, the method further comprises:
If the copyright identification result of any target layer icon exists in each layer icon, whether the target object has the copyright of the design image to be detected or not cannot be identified is characterized, and the object layer icon belonging to the same copyright object as the target layer icon is obtained;
Replacing the target layer icon in the design image to be detected with the target layer icon to obtain a first combined design image;
And extracting first combined image characteristic information of the first combined design image, and inquiring similar abnormal images corresponding to the design image to be detected according to the image characteristic information, the first combined image characteristic information and the target layer icon.
In one embodiment, obtaining an object layer icon that belongs to the same rights object as the target layer icon includes:
Acquiring a rights object of a layer icon;
Determining a rights object vector of the rights object;
Querying a target object vector matched with the rights object vector in the object vectors of the pre-stored design icons;
and determining the design icon corresponding to the target object vector as an object layer icon belonging to the same rights object as the layer icon.
In one embodiment, the method further comprises:
If the copyright identification result of any target layer icon exists in the layer icons, whether the target object has the copyright of the design image to be detected or not cannot be identified is characterized, and the target layer icon is moved from the target layer to other layers except the target layer, so that a second combined design image is obtained;
and extracting second combined image characteristic information of the second combined design image, and inquiring similar abnormal images corresponding to the design image to be detected according to the image characteristic information, the second combined image characteristic information and the target layer icon.
In a second aspect, the present application also provides an image detection apparatus, including:
The image acquisition module is used for acquiring a design image to be detected corresponding to the target object;
the icon extraction module is used for extracting icons from a plurality of image layers of the design image to be detected respectively to obtain layer icons in at least one image layer;
The query module is used for extracting the image characteristic information of the design image to be detected if the copyright identification result of any target layer icon exists in each layer icon to indicate whether the target object has the copyright of the design image to be detected or not, and querying similar abnormal images corresponding to the design image to be detected according to the image characteristic information and the target layer icon;
The detection module is used for determining that the target object does not possess the copyright of the design image to be detected under the condition that the similar abnormal image corresponding to the design image to be detected is inquired.
In one embodiment, the query module is further configured to query a similar normal image corresponding to the design image to be detected from a preset normal image library, extract feature information of the image to be detected of the design image to be detected from a preset abnormal image library under the condition that the similar normal image is not queried, and query a similar abnormal image corresponding to the design image to be detected according to the feature information of the image to be detected and the target layer icon.
In one embodiment, the image feature information to be detected includes image feature vector information to be detected and a gray level image to be detected, the query module is further configured to obtain a layer icon to be matched, image feature vector information to be matched and a gray level image to be matched from the images to be matched in the preset abnormal image library, and query a target parameter matched with at least one of the target layer icon, the image feature vector information to be detected and the gray level image to be matched from the layer icon to be matched, the image feature vector information to be matched and the gray level image to be matched, and determine the image to be matched corresponding to the queried target parameter as the similar abnormal image.
In one embodiment, the query module is further configured to obtain, for any target layer icon in the layer icons, a signature object identifier and an icon name identifier of the target layer icon, determine a rights object of the target layer icon based on the signature object identifier and the icon name identifier, determine whether the target object has rights of the rights object, and obtain a rights identification result of the target layer icon.
In one embodiment, the image detection device further includes a first combination module, where the first combination module is configured to, if the copyright identification result of any one of the target layer icons exists in each layer icon, characterize whether the target object has the copyright of the design image to be detected, obtain the object layer icon that belongs to the same copyright object as the target layer icon, replace the target layer icon in the design image to be detected with the target layer icon, obtain a first combined design image, extract first combined image feature information of the first combined design image, and query a similar abnormal image corresponding to the design image to be detected according to the image feature information, the first combined image feature information, and the target layer icon.
In one embodiment, the first combination module is further configured to obtain a rights object of the layer icon, determine a rights object vector of the rights object, query a target object vector matched with the rights object vector in the object vectors of the pre-stored design icons, and determine the design icon corresponding to the target object vector as an object layer icon belonging to the same rights object as the layer icon.
In one embodiment, the image detection device further includes a second combination module, where the second combination module is configured to, if the copyright identification result of any one of the target layer icons exists in each layer icon, characterize whether the target object has the copyright of the design image to be detected, move the target layer icon from the target layer to other layers except the target layer to obtain a second combined design image, extract second combined image feature information of the second combined design image, and query a similar abnormal image corresponding to the design image to be detected according to the image feature information, the second combined image feature information and the target layer icon.
In a third aspect, the present application also provides a computer device comprising a memory and a processor, the memory storing a computer program, the processor implementing the following steps when executing the computer program:
acquiring a design image to be detected corresponding to a target object;
icon extraction is carried out on a plurality of image layers of the design image to be detected respectively, so that layer icons in at least one image layer are obtained;
if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image characteristic information of the design image to be detected, and inquiring the similar abnormal image corresponding to the design image to be detected according to the image characteristic information and the target layer icon;
And under the condition that similar abnormal images corresponding to the design images to be detected are inquired, determining that the target object does not possess copyrights of the design images to be detected.
In a fourth aspect, the present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
acquiring a design image to be detected corresponding to a target object;
icon extraction is carried out on a plurality of image layers of the design image to be detected respectively, so that layer icons in at least one image layer are obtained;
if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image characteristic information of the design image to be detected, and inquiring the similar abnormal image corresponding to the design image to be detected according to the image characteristic information and the target layer icon;
And under the condition that similar abnormal images corresponding to the design images to be detected are inquired, determining that the target object does not possess copyrights of the design images to be detected.
In a fifth aspect, the application also provides a computer program product comprising a computer program which, when executed by a processor, performs the steps of:
acquiring a design image to be detected corresponding to a target object;
icon extraction is carried out on a plurality of image layers of the design image to be detected respectively, so that layer icons in at least one image layer are obtained;
if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image characteristic information of the design image to be detected, and inquiring the similar abnormal image corresponding to the design image to be detected according to the image characteristic information and the target layer icon;
And under the condition that similar abnormal images corresponding to the design images to be detected are inquired, determining that the target object does not possess copyrights of the design images to be detected.
The image detection method, the device, the computer equipment, the computer readable storage medium and the computer program product are different from directly judging the similarity of the images to be detected. In the whole process, a plurality of icons of a plurality of layers in the image to be detected can be automatically extracted layer by directly uploading the image to be detected, missing detection objects are reduced, the icons of the image are comprehensively detected one by one, and under the condition that the copyright identification result of any target layer icon exists in each layer icon to represent whether the target object cannot identify whether the copyright of the design image to be detected is possessed or not, the image detection accuracy is improved by comprehensively inquiring similar abnormal images corresponding to the design image to be detected from the aspects of image characteristic information of the design image to be detected and the target layer icon to consider, so that the target object is determined not to possess the copyright of the design image to be detected under the condition that the similar abnormal images corresponding to the design image to be detected are inquired.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the related art, the drawings that are required to be used in the description of the embodiments of the present application or the related technologies will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present application, and other related drawings may be obtained according to the drawings without any inventive effort for those skilled in the art.
FIG. 1 is a diagram of an application environment for an image detection method in one embodiment;
FIG. 2 is a flow chart of an image detection method according to an embodiment;
FIG. 3 is a flowchart of an image detection method according to another embodiment;
FIG. 4 is a flow chart of an image detection method according to another embodiment;
FIG. 5 is a flowchart of an image detection method in a specific embodiment;
FIG. 6 is a block diagram of an image detection apparatus in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the detailed description and specific examples, while indicating the application, are not intended to limit the application. It should be noted that, in the embodiments of the present application, some existing solutions in the industry such as software, group, model, etc. may be mentioned, and they should be regarded as exemplary, for the purpose of illustrating the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or must not use the solution.
It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present application are both information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to meet the related regulations. The technical scheme of the application obtains, stores, uses, processes and the like the data, which all meet the relevant regulations of national laws and regulations.
The image detection method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server.
The user uploads the design image to be detected corresponding to the target object to an image detection platform in the interface of the terminal 102, or selects the design image to be detected corresponding to the target object from a local database of the terminal 102, and clicks a detection control in the image detection platform. It should be explained that the design image to be detected corresponding to the target object does not mean that the design image to be detected is designed by the template object, and the target object herein refers to the object to which the design image to be detected is to be used. That is, the image detection of the present application essentially determines whether the target object owns the usage right of the design image to be detected.
The terminal 102 obtains the design image to be detected corresponding to the target object, and generates an image detection request based on the design image to be detected corresponding to the target object, wherein the image detection request carries the design image to be detected corresponding to the target object. The terminal 102 uploads the image detection request to the server 104.
The server 104 extracts the design image to be detected corresponding to the target object in the image detection request, and respectively extracts icons from a plurality of image layers of the design image to be detected to obtain layer icons in at least one image layer; if the copyright identification result of any target layer icon in each layer icon represents that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image characteristic information of the design image to be detected, and inquiring a similar abnormal image corresponding to the design image to be detected according to the image characteristic information and the target layer icon; and under the condition that similar abnormal images corresponding to the design images to be detected are inquired, determining that the target object does not possess copyrights of the design images to be detected. Further, in the case that it is determined that the target object does not possess the copyright of the design image to be detected, the server 104 pushes an image detection message to the terminal 102, and the terminal 102 presents the image detection message to the user.
The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, where the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart vehicle devices, projection devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The head-mounted device may be a Virtual Reality (VR) device, an augmented Reality (Augmented Reality, AR) device, smart glasses, or the like. The server 104 may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud computing services.
In an exemplary embodiment, as shown in fig. 2, an image detection method is provided, and an example of application of the method to the server 104 in fig. 1 is described. Wherein:
s200, obtaining a design image to be detected corresponding to the target object.
The design image to be detected corresponding to the target object does not mean that the design image to be detected is designed by a template object, and the target object refers to an object to which the design image to be detected is to be used.
Specifically, the terminal acquires a design image to be detected corresponding to the target object, and generates an image detection request based on the design image to be detected corresponding to the target object, wherein the image detection request carries the design image to be detected corresponding to the target object. And the terminal uploads the image detection request to the server. And the server extracts the design image to be detected corresponding to the target object in the image detection request.
S400, respectively extracting icons from a plurality of image layers of the design image to be detected, and obtaining the image layer icons in at least one image layer.
Specifically, unlike splitting the picture in the design image to be detected directly by naked eyes, the server extracts the icon of each image layer from the plurality of image layers of the design image to be detected, and because some image layers may not have icons but have texts, the icon of the image layer in at least one image layer can be obtained.
In one embodiment, icon extraction is performed from a plurality of image layers of a design image to be detected, respectively, to obtain a layer icon in at least one image layer, including: and extracting icons from a plurality of image layers of the design image to be detected according to the icon format of the design image to be detected, and obtaining the layer icons in at least one image layer. For example, the icon format of the design image to be detected is typically a picture format, such as JPG (Joint Photographic Experts Group, joint picture experts group) format or PNG (Portable Network Graphics ) format, etc., when an icon in the picture format is detected from a plurality of image layers of the design image to be detected, the icon can be extracted, and when text in the text format is detected from a plurality of image layers of the design image to be detected, the text need not be extracted.
In one embodiment, icon extraction is performed from a plurality of image layers of a design image to be detected, so as to obtain a layer icon in at least one image layer, and the method further includes: and respectively extracting icons from the plurality of image layers of the design image to be detected according to the priority order of the plurality of image layers of the design image to be detected, so as to obtain the layer icon in at least one image layer. The priority order may be preset, for example, may be set to be the highest priority of the top image layer, the second highest priority of the second image layer, …, and so on, where the lowest image layer has the highest priority, and at this time, icon extraction may be sequentially performed from the top image layer to the bottom image layer, to obtain the image layer icon in at least one image layer. And the order of priority is not limited to the above example, and may be set according to the requirement of image detection.
In one embodiment, icon extraction is performed from a plurality of image layers of a design image to be detected, so as to obtain a layer icon in at least one image layer, and the method further includes: and (3) extracting icons from a plurality of image layers of the design image to be detected through a depth priority strategy from the top image layer, traversing the icons in all the image layers, and obtaining the image layer icons in at least one image layer. The depth-first strategy refers to that, starting from a certain vertex v in the layer:
(1) Accessing a vertex v;
(2) Sequentially starting from adjacent points which are not accessed by v in other layers, and performing depth-first traversal on the layers until vertexes which are in path communication with v in the layers are accessed;
(3) If no vertex is accessed in the graph at this time, starting from an unaccessed vertex, performing depth-first traversal again until all vertices in the graph are accessed.
That is, the main idea of the depth-first strategy is to start from an unviewed vertex V in the graph, go all the way to the bottom along a path, then go back from the node at the end of the path to the last node, then start from another path to the bottom …, and repeat the process repeatedly and continuously until all the vertices are traversed, which is characterized in that the process is not repeated until the south wall is not hit, the path is firstly completed, and then the path is changed to continue the travel.
And S600, if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image characteristic information of the design image to be detected, and inquiring the similar abnormal image corresponding to the design image to be detected according to the image characteristic information and the target layer icon.
The target layer icon refers to any one layer icon in the layer icons, namely, the target icon of the target layer. There are three cases of copyright recognition results, including: the first kind, the target object has the copyright of the design image to be detected; the second type, the target object does not possess the copyright of the design image to be detected; thirdly, whether the target object has copyrights of the design image to be detected cannot be identified. The similar abnormal image refers to an abnormal image similar to the design image to be detected.
Specifically, if the copyright identification result of any target layer icon indicates that whether the target object has the copyright of the design image to be detected cannot be identified, image processing is performed on the design image to be detected, and image characteristic information of the design image to be detected is obtained. The method can query similar abnormal images corresponding to the design image to be detected based on the target layer icon, and can query similar abnormal images corresponding to the design image to be detected based on the feature information of the image to be detected. And the accuracy of image detection is improved from the two aspects of the target layer icon and the image characteristic information to be detected.
In one embodiment, in order to improve the efficiency of image detection, if the copyright identification result of any target layer icon in each layer icon indicates that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image feature information of the design image to be detected includes: and if the copyright identification result of any target layer icon exists in the layer icons to indicate whether the target object has the copyright of the design image to be detected or not, and the copyright identification result of the layer icons except the target layer icon does not indicate that the target object does not have the copyright of the design image to be detected, extracting the image characteristic information of the design image to be detected. That is, when the copyright identification result of the layer icon indicates that the target object does not possess the copyright of the design image to be detected, the target object can be directly determined that the target object does not possess the copyright of the design image to be detected, and at this time, the design image to be detected is considered to have an infringement risk.
In one embodiment, if the copyright identification results of all the layer icons represent that the target object has the copyright of the design image to be detected, determining that the target object has the copyright of the design image to be detected, and at this time, considering that the design image to be detected has no infringement risk.
S800, under the condition that similar abnormal images corresponding to the design image to be detected are inquired, determining that the target object does not possess copyrights of the design image to be detected.
Specifically, under the condition that similar abnormal images corresponding to the design image to be detected are queried, determining that the target object does not have copyrights of the design image to be detected. And under the condition that similar abnormal images corresponding to the design images to be detected are not inquired, determining that the target object has copyrights of the design images to be detected. Further, the server 104 pushes an image detection message to the terminal 102, and the terminal 102 displays the image detection message to the user, where the image detection message includes the copyright of the design image to be detected owned by the target object or the copyright of the design image to be detected not owned by the target object.
In the image detection method, the application provides a more accurate image detection method, which is different from directly judging the similarity of the images to be detected. In the whole process, a plurality of icons of a plurality of layers in the image to be detected can be automatically extracted layer by directly uploading the image to be detected, missing detection objects are reduced, the icons of the image are comprehensively detected one by one, and under the condition that the copyright identification result of any target layer icon exists in each layer icon to represent whether the target object cannot identify whether the copyright of the design image to be detected is possessed or not, the image detection accuracy is improved by comprehensively inquiring similar abnormal images corresponding to the design image to be detected from the aspects of image characteristic information of the design image to be detected and the target layer icon to consider, so that the target object is determined not to possess the copyright of the design image to be detected under the condition that the similar abnormal images corresponding to the design image to be detected are inquired.
In an exemplary embodiment, as shown in fig. 3, S600 further includes:
S610, if the copyright identification result of any target layer icon exists in each layer icon to indicate whether the target object has the copyright of the design image to be detected or not, inquiring a similar normal image corresponding to the design image to be detected from a preset normal image library.
S620, extracting feature information of the image to be detected of the design image to be detected from a preset abnormal image library under the condition that the similar normal image is not queried, and querying the similar abnormal image corresponding to the design image to be detected according to the feature information of the image to be detected and the target layer icon.
The preset normal image library is also called a white list image library, and refers to images which are all copyrighted and have no infringement risk and contained in the image library, and once the images are matched with the images in the preset normal image library, the images are copyrighted and have no infringement risk. The preset abnormal image library is also called a blacklist image library, and refers to images which are contained in the image library and have no copyright and are in infringement risk, and once the images are matched with the images in the preset normal image library, the images are indicated to be the images which have no copyright and are in infringement risk.
Specifically, when the copyright identification result of any target layer icon exists in each layer icon to indicate whether the target object has the copyright of the design image to be detected or not, firstly, inquiring a similar normal image corresponding to the design image to be detected from a preset normal image library based on the target layer icon. In one embodiment, querying a similar normal image corresponding to a design image to be detected based on a target layer icon includes: and acquiring a plurality of layer icons of the normal image from a preset normal image library, inquiring the layer icon matched with the target layer icon in the plurality of layer icons, and determining the normal image corresponding to the layer icon as a similar normal image corresponding to the designed image to be detected.
Under the condition that similar normal images corresponding to the design image to be detected can be queried based on each target layer icon, the design image to be detected is confirmed to be an image with use copyright of the target object, and infringement risk is avoided.
Under the condition that similar normal images corresponding to the design image to be detected are not queried based on each target layer icon, whether the design image to be detected is an image with the use copyright of a target object cannot be confirmed at the moment. And extracting the feature information of the image to be detected of the design image to be detected from a preset abnormal image library, and respectively inquiring whether the feature information of the image to be detected is matched with the feature information of the image to be detected or inquiring whether the layer icon of the image to be detected is matched with the layer icon of the object according to the feature information of the image to be detected and the layer icon of the object, if so, determining the matched feature information of the image or the abnormal image corresponding to the layer icon as a similar abnormal image corresponding to the design image to be detected.
In the above embodiment, by presetting the normal image library and the preset abnormal image library, whether the similar normal image or the similar abnormal image corresponding to the design image to be detected exists or not is rapidly checked, so that the efficiency of image detection is improved. Furthermore, under the condition that similar normal images are not queried, the feature information of the images to be detected of the designed images to be detected is extracted from the preset abnormal image library, so that unnecessary query operation is reduced, and the image detection efficiency is further improved.
In an exemplary embodiment, as shown in fig. 4, the image feature information to be detected includes image feature vector information to be detected and a graying image to be detected; s600 includes:
S630, if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, extracting the image characteristic information of the design image to be detected.
S640, obtaining a layer icon to be matched of the image to be matched, feature vector information of the image to be matched and a gray-scale image to be matched from the image to be matched of the preset abnormal image library.
S650, inquiring a target parameter matched with at least one of the target layer icon, the image feature vector information to be detected and the gray image to be detected from the image layer icon to be matched, the image feature vector information to be matched and the gray image to be matched.
S660, determining the image to be matched corresponding to the inquired target parameter as a similar abnormal image.
Specifically, the query of the similar abnormal image corresponding to the design image to be detected is actually whether the parameters of the query abnormal image are matched with the feature information of the image to be detected and the icon of the target image layer. Further, the image feature information to be detected comprises image feature vector information to be detected and a graying image to be detected, and the image feature information, the graying image and the target layer icon are triggered to comprehensively inquire similar abnormal images.
Under the condition that the image feature information to be detected comprises image feature vector information to be detected and grayscale images to be detected, firstly, parameters such as an image layer icon to be matched, image feature vector information to be matched and grayscale images to be matched of the images to be matched are required to be obtained from images to be matched of a preset abnormal image library, and at least one matched target parameter in the parameters of the images to be matched, the target image layer icon, the image feature vector information to be detected and the grayscale images to be detected is respectively inquired. In one embodiment, the feature vector information of the image to be detected may be stretched and combined with the original feature vector of the image to be detected to update the feature vector information of the image to be detected.
And finally, under the condition that the target parameters are inquired, determining the images to be matched corresponding to the inquired target parameters as similar abnormal images.
In the above embodiment, from three aspects of feature vector information, a grayscale image and a target layer icon, parameters of an abnormal image are comprehensively retrieved to determine a target parameter matched with at least one of the target layer icon, feature vector information of an image to be detected and the grayscale image to be detected, so as to accurately query a similar abnormal image corresponding to the design image to be detected.
In an exemplary embodiment, if the copyright identification result of any target layer icon in the layer icons indicates that whether the target object has the copyright of the design image to be detected cannot be identified, before extracting the image feature information of the design image to be detected, the method further includes:
And aiming at any target layer icon in the layer icons, acquiring signature object identifications and icon name identifications of the target layer icons, determining the copyright objects of the target layer icons based on the signature object identifications and the icon name identifications, and determining whether the target objects have copyrights of the copyright objects to obtain a copyright identification result of the target layer icons.
The signature object identifier refers to an author identifier of the layer icon, such as a first, a second and the like. The icon name identifier refers to an identifier of the name of the layer icon, such as picture1, picture2, and the like.
Specifically, when designing the design image to be detected, because each layer icon in the design image to be detected may be designed by itself or may be designed by dragging icons of other designers in a combined manner, each layer icon in the design image to be detected automatically carries information such as signature object identification, icon name identification, creation time, modification time and the like. The rights object is distinguished from the signature object, which may be a signature object individual designing the target layer icon or may be an enterprise owning the rights of the target layer icon.
Any target layer icon in the layer icons is analyzed, and copyright information of the target layer icons is acquired, wherein the copyright information comprises, but is not limited to, signature object identification, icon name identification, creation time, modification time and the like. Based on the signature object identification and the icon name identification, the icon which is matched with the signature object identification and the icon name identification together is queried from a picture library, namely, the picture of the picture name under the signature object name can be queried from the picture. When an icon which is matched with the signature object identification and the icon name identification together is queried, the rights object of the icon is determined, for example, the rights object of the icon may be the signature object of the design icon or the rights object of the icon of the target layer, for example, an enterprise A, a webpage B and the like. And determining the rights object of the icon as the rights object of the target layer icon.
Further, whether the target object owns the copyright of the copyright object is determined, and a copyright identification result of the target layer icon is obtained. For example, let the rights object be enterprise a, the target object be enterprise C, the rights identification result of each layer icon represents that whether the target object has the rights of the design image to be detected or not can not be identified, the target layer icon of the rights of the target layer icon of enterprise a is icon a, whether enterprise C has the rights of the target layer icon of enterprise a or not is determined, and if enterprise C has the rights of icon a of enterprise a, the rights identification result represents that the target object has the rights of the design image to be detected.
In one embodiment, when querying the icon matching the signature object identifier and the icon name identifier together from the picture library, the icon name identifier may be queried with ambiguity, and the signature object identifier may be queried with accuracy, that is, the icon matching the signature object identifier and the icon name identifier is queried from the picture library.
In the above embodiment, by aiming at any target layer icon in the layer icons, from the angles of signature object identification and icon name identification, whether the target object has the copyright of the copyright object of the target layer icon is judged, and the copyright identification result of the target layer icon is determined, so that whether the target object has the copyright of the design image to be detected is accurately identified, and the accuracy of image detection is improved.
In an exemplary embodiment, the method further comprises:
If the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, acquiring the object layer icon belonging to the same copyright object as the target layer icon, replacing the target layer icon in the design image to be detected with the target layer icon to obtain a first combined design image, extracting first combined image characteristic information of the first combined design image, and inquiring similar abnormal images corresponding to the design image to be detected according to the image characteristic information, the first combined image characteristic information and the target layer icon.
Specifically, if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, in order to more comprehensively identify whether the target object has the copyright of the design image to be detected, the object layer icon belonging to the same copyright object as the target layer icon can be obtained, that is, by determining the copyright object of the target layer icon, other layer icons under the name of the copyright object are determined, and the other layer icons under the name of the copyright object are determined to be the object layer icons.
And replacing the target layer icon in the design image to be detected with the target layer icon to obtain a first combined design image, inquiring whether parameters of images in a preset abnormal image library can be matched or not according to the first combined image characteristic information of the first combined design image, the image characteristic information of the design image to be detected and the target layer icon, and determining the images with the matched parameters as similar abnormal images.
For example, the icon of the target layer in the design image to be detected is the icon a of the layer 1, the author of the icon a is the first, and other icons b and c under the first name are obtained. And placing the icon b at the position of the icon a instead of the icon a to obtain a first combined design image, or placing the icon c at the position of the icon a instead of the icon a to obtain a first combined design image. And inquiring whether parameters of images in a preset abnormal image library can be matched or not according to the first combined image characteristic information of the first combined design image, the image characteristic information of the design image to be detected and the target layer icon, and determining the images with the matched parameters as similar abnormal images.
In the above embodiment, the object layer icon belonging to the same rights object as the target layer icon replaces the target layer icon, so that a new first combined design image can be formed, and means for detecting whether the new first combined design image has a corresponding similar abnormal image is newly added on the basis of detecting whether the original image feature information and the target layer icon have a corresponding similar abnormal image, so that the rights detection is more comprehensively performed on the image.
In an exemplary embodiment, acquiring an object layer icon belonging to the same rights object as the target layer icon includes:
The method comprises the steps of obtaining a copyright object of a layer icon, determining a copyright object vector of the copyright object, inquiring a target object vector matched with the copyright object vector in object vectors of pre-stored design icons, and determining the design icon corresponding to the target object vector as an object layer icon belonging to the same copyright object as the layer icon.
Specifically, in the application, the object layer icon belonging to the same rights object as the target layer icon is obtained through the vector mapping relation. More specifically, first, the rights object of the layer icon is acquired, and a rights object vector corresponding to the rights object is obtained. And mapping the rights object vector corresponding to the rights object to other design icons to obtain other design icons of the same rights object vector, and determining the other design icons of the same rights object vector as an object layer icon belonging to the same rights object as the layer icon.
Further, the mapping of the rights object vector corresponding to the rights object to other icons is achieved by querying a target object vector matched with the rights object vector in the object vectors of the pre-stored design icons, and querying the design icon corresponding to the target object vector.
In the above embodiment, the accuracy of determining the object layer icon belonging to the same rights object as the target layer icon is improved by accurately querying the target object vector matched with the rights object vector in the object vector of the pre-stored design icon through the rights object vector of the rights object.
In an exemplary embodiment, the method further comprises:
If the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, moving the target layer icon from the target layer to other layers except the target layer to obtain a second combined design image, extracting second combined image characteristic information of the second combined design image, and inquiring similar abnormal images corresponding to the design image to be detected according to the image characteristic information, the second combined image characteristic information and the target layer icon.
Specifically, if the copyright identification result of any target layer icon exists in each layer icon to indicate that whether the target object has the copyright of the design image to be detected cannot be identified, in order to more comprehensively identify whether the target object has the copyright of the design image to be detected, the target layer icon can be moved from the target layer to other layers except the target layer to obtain a second combined design image, the second combined image characteristic information of the second combined design image is extracted, and whether parameters of images in a preset abnormal image library can be matched or not is inquired according to the second combined image characteristic information of the second combined design image, the image characteristic information of the design image to be detected and the target layer icon, and the image with the matched parameters is determined to be a similar abnormal image.
Further, moving the target layer icon from the target layer to other layers than the target layer includes the following:
First, the target layer icon is moved from the target layer to other layers except the target layer, one of the icons in the other layers is replaced, and the original target layer icon of the target layer is deleted.
And the second type is to move the target layer icon from the target layer to other layers except the target layer to replace one of the icons in the other layers, but not delete the original target layer icon of the target layer.
Third, the target layer icon is moved from the target layer to other layers except the target layer, and combined with the original icons in the other layers, but the original icons in the other layers and the target layer are not deleted.
Fourth, the icon of the target layer is moved from the target layer to other layers except the target layer, and combined with the original icon in the other layers, the original icon in the other layers is not deleted, but the original icon in the target layer is deleted.
In the above embodiment, the new second combined design image is formed by moving the target layer icon from the target layer icon to other layers except the target layer icon, and the means for detecting whether the new second combined design image has the corresponding similar abnormal image is newly added on the basis of detecting whether the original image feature information and the target layer icon have the corresponding similar abnormal image, so that the copyright of the image is more comprehensively detected.
In a specific embodiment, as shown in fig. 5, a user uploads a design manuscript to be detected corresponding to a target object to an image detection platform of a terminal, and the image detection platform sends the design manuscript to be detected to a server. The image detection process of the server comprises the participation of a design draft analyzer, a picture analyzer, a copyright analyzer, a white list picture library and a black list picture library, and specifically comprises the following steps:
1. The design draft analyzer acquires a design draft to be detected corresponding to the target object, analyzes the design draft to be detected corresponding to the target object according to a design draft format, and extracts icons from a plurality of image layers of the design draft to be detected respectively through a depth-first strategy to obtain layer icons in at least one image layer.
2. And the picture analyzer analyzes at least one target layer icon transmitted by the design draft analyzer to obtain the picture name of the target layer icon, the copyright information such as an author and the like.
3. And the copyright analyzer searches the picture name of the target layer icon and copyright information such as an author and the like sent by the picture analyzer, and determines the copyright object of the target layer icon. And further determining whether the target object has the copyright of the copyright object, and obtaining the copyright identification result of the target layer icon. If the copyright identification result of the target layer icon represents the copyright of the copyright object owned by the target object, the copyright analyzer feeds back a message that the target layer icon of the picture analyzer does not have infringement risk. If the copyright identification result of the target layer icon represents that the target object does not possess the copyright of the copyright object, the copyright analyzer feeds back a message that the target layer icon of the picture analyzer has infringement risk. If the copyright identification result of the target layer icon indicates that whether the target object has the copyright of the copyright object can not be identified, the following step 4 is performed.
4. And the picture analyzer sends the target layer icon which cannot be identified by the copyright analyzer to the white list picture library for searching, and if the parameters similar to the target layer icon are searched in the parameters of the images in the white list picture library, the parameters are fed back to the message that the target layer icon of the picture analyzer does not have infringement risk. And if the parameters similar to the icons of the target layers are not searched in the parameters of the images in the white list picture library, performing the subsequent step 5.
5. And the picture analyzer performs graying and feature extraction on the design manuscript to be detected to obtain feature vector information of the image to be detected and a graying image to be detected of the design manuscript to be detected. The picture analyzer sends the feature vector information of the image to be detected, the gray-scale image to be detected and the target layer icon into the blacklist picture library for searching, and if at least one matched target parameter exists among the parameters of the image in the blacklist picture library, the image corresponding to the target parameter is determined to be a similar abnormal image. And determining that the design manuscript to be detected does not possess the copyright of the design manuscript to be detected.
In addition, an object layer icon belonging to the same author as the target layer icon can be obtained through a vector mapping method, the target layer icon is replaced by the object layer icon in the design manuscript to be detected, a first combined design image is obtained, first combined image feature information of the first combined design manuscript is extracted, and similar abnormal images corresponding to the design manuscript to be detected are inquired according to the image feature information, the first combined image feature information and the target layer icon.
Further, the target layer icon can be moved from the target layer to other layers except the target layer to obtain a second combined design image, second combined image feature information of the second combined design draft is extracted, and similar abnormal images corresponding to the design draft to be detected are inquired according to the image feature information, the second combined image feature information and the target layer icon.
6. The picture analyzer feeds back all the icon layers, the positions of the icon layers and the image detection results to the design manuscript analyzer, and the design manuscript analyzer feeds back all the icon layers, the positions of the icon layers and the image detection results to the user.
It should be understood that, although the steps in the flowcharts related to the above embodiments are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides an image detection device for realizing the image detection method. The implementation of the solution provided by the device is similar to the implementation described in the above method, so the specific limitation in the embodiments of the image detection device or devices provided below may be referred to the limitation of the image detection method hereinabove, and will not be repeated here.
In an exemplary embodiment, as shown in fig. 6, there is provided an image detection apparatus 900 including: an image acquisition module 200, an icon extraction module 400, a query module 600, and a detection module 800, wherein:
The image acquisition module 200 is used for acquiring a design image to be detected corresponding to the target object;
the icon extraction module 400 is configured to extract icons from a plurality of image layers of the design image to be detected, respectively, to obtain a layer icon in at least one image layer;
the query module 600 is configured to extract image feature information of the design image to be detected if the copyright identification result of any target layer icon in each layer icon indicates that whether the target object has the copyright of the design image to be detected cannot be identified, and query similar abnormal images corresponding to the design image to be detected according to the image feature information and the target layer icon;
The detection module 800 is configured to determine that the target object does not possess the copyright of the design image to be detected, under the condition that the similar abnormal image corresponding to the design image to be detected is queried.
In one embodiment, the query module 600 is further configured to query a similar normal image corresponding to the design image to be detected from a preset normal image library, extract feature information of the image to be detected of the design image to be detected from a preset abnormal image library under the condition that the similar normal image is not queried, and query the similar abnormal image corresponding to the design image to be detected according to the feature information of the image to be detected and the target layer icon.
In one embodiment, the to-be-detected image feature information includes to-be-detected image feature vector information and to-be-detected grayscale image, the query module 600 is further configured to obtain to-be-matched image layer icons of the to-be-matched image, to-be-matched image feature vector information and to-be-matched grayscale images from to-be-matched images of a preset abnormal image library, and query a target parameter matched with at least one of the target image layer icons, the illustrated to-be-detected image feature vector information and the to-be-detected grayscale images from to-be-matched image layer icons, to-be-matched image feature vector information and to-be-matched grayscale images, and determine the to-be-matched image corresponding to the queried target parameter as the similar abnormal image.
In one embodiment, the query module 600 is further configured to obtain, for any target layer icon of the layer icons, a signature object identifier and an icon name identifier of the target layer icon, determine a rights object of the target layer icon based on the signature object identifier and the icon name identifier, determine whether the target object has rights of the rights object, and obtain a rights identification result of the target layer icon.
In one embodiment, the image detection apparatus 900 further includes a first combination module, where the first combination module is configured to, if the copyright identification result of any target layer icon exists in each layer icon, characterize whether the target object has the copyright of the design image to be detected, acquire the object layer icon that belongs to the same copyright object as the target layer icon, replace the target layer icon in the design image to be detected with the object layer icon, obtain a first combined design image, extract first combined image feature information of the first combined design image, and query a similar abnormal image corresponding to the design image to be detected according to the image feature information, the first combined image feature information, and the target layer icon.
In one embodiment, the first combination module is further configured to obtain a rights object of the layer icon, determine a rights object vector of the rights object, query a target object vector matched with the rights object vector in the object vectors of the pre-stored design icons, and determine the design icon corresponding to the target object vector as an object layer icon belonging to the same rights object as the layer icon.
In one embodiment, the image detection apparatus 900 further includes a second combination module, where the second combination module is configured to, if the copyright identification result of any one of the target layer icons exists in each layer icon, characterize whether the target object has the copyright of the design image to be detected, move the target layer icon from the target layer to other layers except the target layer to obtain a second combined design image, extract second combined image feature information of the second combined design image, and query similar abnormal images corresponding to the design image to be detected according to the image feature information, the second combined image feature information and the target layer icon.
The respective modules in the above-described image detection apparatus may be implemented in whole or in part by software, hardware, and combinations thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one exemplary embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for storing design image login data to be detected corresponding to the target object. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement an image detection method.
It will be appreciated by persons skilled in the art that the architecture shown in fig. 7 is a block diagram of some of the architecture relevant to the present inventive arrangements and is not limiting as to the computer device to which the present inventive arrangements are applicable, and that a particular computer device may include more or less components than those shown, or may combine some of the components, or have a different arrangement of components.
In an embodiment, there is also provided a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, carries out the steps of the method embodiments described above.
In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile memory and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (RESISTIVE RANDOM ACCESS MEMORY, reRAM), magneto-resistive Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in various forms such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), etc. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computation, an artificial intelligence (ARTIFICIAL INTELLIGENCE, AI) processor, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the present application.
The foregoing examples illustrate only a few embodiments of the application and are described in detail herein without thereby limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.
Claims (17)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411283422.4A CN118968097A (en) | 2024-09-13 | 2024-09-13 | Image detection method, device, computer equipment, readable storage medium and program product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411283422.4A CN118968097A (en) | 2024-09-13 | 2024-09-13 | Image detection method, device, computer equipment, readable storage medium and program product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118968097A true CN118968097A (en) | 2024-11-15 |
Family
ID=93407465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411283422.4A Pending CN118968097A (en) | 2024-09-13 | 2024-09-13 | Image detection method, device, computer equipment, readable storage medium and program product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118968097A (en) |
-
2024
- 2024-09-13 CN CN202411283422.4A patent/CN118968097A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR100353798B1 (en) | Method for extracting shape descriptor of image object and content-based image retrieval system and method using it | |
| US12183056B2 (en) | Adversarially robust visual fingerprinting and image provenance models | |
| US20170337449A1 (en) | Program, system, and method for determining similarity of objects | |
| US12192207B2 (en) | Media data based user profiles | |
| CN101669117A (en) | Use matching images with shape descriptors | |
| US12074907B2 (en) | Systems and methods of detecting anomalous websites | |
| US11816189B1 (en) | Data model to organize, generate, and share data about an object with multiple media formats via various presentation systems | |
| JP2019028700A (en) | Verification device, method, and program | |
| CN114359352B (en) | Image processing method, apparatus, device, storage medium, and computer program product | |
| CN115952313A (en) | Commodity feature processing method, electronic device and computer storage medium | |
| JP6173754B2 (en) | Image search system, image search apparatus, and image search method | |
| CN110633733A (en) | Intelligent image matching method and device and computer readable storage medium | |
| CN110737794A (en) | Image query method, system, server and storage medium | |
| CN118968097A (en) | Image detection method, device, computer equipment, readable storage medium and program product | |
| CN115905608B (en) | Image feature acquisition method, device, computer equipment, and storage medium | |
| CN103942239A (en) | Information processing apparatus and information processing method | |
| JP6997656B2 (en) | Search device, search method and search program | |
| CN115687673B (en) | Picture archiving method and device, electronic equipment and readable storage medium | |
| CN119131348A (en) | Model training method and fire detection method | |
| CN111461136B (en) | Data processing method, device, system, computer-readable storage medium | |
| CN112017092B (en) | Generation of watermark detection model and watermark detection method, device and equipment | |
| JP7091055B2 (en) | Search device, search method and search program | |
| JP7088665B2 (en) | Search device, search method and search program | |
| US12326900B1 (en) | Content similarity detection (CSD) computing platform and service | |
| CN111429294B (en) | Account identification method and device, electronic equipment and storable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |