CN111815500A - Image processing method, device, equipment and storage medium - Google Patents

Abstract

The present application discloses an image processing method, apparatus, device and storage medium, and relates to the technical field of image processing. The specific implementation scheme is: obtaining the published information in the published platform; wherein, the published information includes text content and a watermarked picture; obtaining the original picture associated with the watermarked picture; combining the original picture with the watermarked picture The text content is uploaded to the platform to be released for information release. The embodiment of the present application realizes the automatic migration of the published information from the published platform to the platform to be published, without the need for the collection of text materials, the removal of watermarking of watermarked pictures, and the need for manual editing of the published information, thereby improving information publishing. efficiency.

Description

An image processing method, device, equipment and storage medium

technical field

The present application relates to the field of artificial intelligence technology, in particular to image processing technology. Specifically, the present application provides an image processing method, apparatus, device, and storage medium that utilize image processing technology to publish information.

Background technique

With the development of Internet technology, various information sharing platforms have emerged. In order to increase the exposure of information, information publishers usually choose to publish the same information on different platforms, thereby increasing the dissemination of information.

When the published information on one platform is re-published on another platform, the watermarked images in the published information need to be de-watermarked, and the processed images and their associated content are published on the platform to be published. Due to the cumbersome process of de-watermarking, the efficiency of information release is low.

SUMMARY OF THE INVENTION

The present application provides an image processing method, apparatus, device and storage medium with higher information release efficiency.

According to an aspect of the present application, an image processing method is provided, comprising:

Obtain the published information in the published platform; wherein, the published information includes text content and watermark images;

obtaining the original picture associated with the watermark picture;

The original picture and the text content are uploaded to the platform to be released, and information is released.

According to another aspect of the present application, an image processing apparatus is provided, comprising:

A published information acquisition module, used to acquire the published information in the published platform; wherein, the published information includes text content and watermark pictures;

an original image acquisition module, used to acquire the original image associated with the watermark image;

The information release module is used for uploading the original picture and the text content to the platform to be released for information release.

According to yet another aspect of the present application, an electronic device is provided, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein,

The memory stores instructions executable by the at least one processor, where the instructions are executed by the at least one processor, so that the at least one processor can perform any image processing provided by the embodiments of the present application method.

According to another aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to execute any image processing method provided by the embodiments of the present application .

The technical solution according to the present application improves the information release efficiency in the information sharing platform.

It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.

Description of drawings

The accompanying drawings are used for better understanding of the present solution, and do not constitute a limitation to the present application. in:

1 is a flowchart of an image processing method provided by an embodiment of the present application;

2 is a flowchart of another image processing method provided by an embodiment of the present application;

3 is a flowchart of another image processing method provided by an embodiment of the present application;

4 is a flowchart of another image processing method provided by an embodiment of the present application;

5 is a structural diagram of an image processing apparatus provided by an embodiment of the present application;

FIG. 6 is a block diagram of an electronic device for implementing an image processing method according to an embodiment of the present application.

Detailed ways

Exemplary embodiments of the present application are described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to facilitate understanding, and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present application. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.

The image processing methods and image processing apparatuses provided in the embodiments of the present application are suitable for the situation that the information published in one information sharing platform is released in another information sharing platform by using image processing technology, the method Executed by an image processing apparatus, the apparatus is implemented by software and/or hardware, and is specifically configured in an electronic device.

FIG. 1 is a flowchart of an image processing method provided by an embodiment of the present application, and the method includes:

S101. Acquire published information on a published platform; wherein, the published information includes text content and watermarked pictures.

The watermark picture can be understood as a picture added with a watermark associated with the published platform.

In an optional implementation of this embodiment of the present application, the published information may be pre-stored in the electronic device or a storage device associated with the electronic device. In the storage device, the published information is obtained.

In order to reduce the cost of data storage or the maintenance of the stored data, in another optional implementation of the embodiment of the present application, it is also possible to log in to the published platform, and to crawl the published information on the published website of the published platform. Pick.

In order to realize the automatic crawling of the published information on the published platform and improve the efficiency of data acquisition, it is also possible to monitor the set information publishers in real time or regularly on the published platform, and monitor the information publishers on the published platform after monitoring. When publishing information, crawl the published information from the published platform according to the URL of the published information.

It should be noted that, in order to avoid disputes caused by copyright issues, the crawling and subsequent processing of published information is usually performed only after the permission or authorization of the information publisher.

S102. Obtain the original picture associated with the watermarked picture.

Among them, the original picture can be understood as the picture without the platform-related watermark added when the information is published on the published platform. It should be noted that the original picture can be the original picture used by the information publisher when the information is published on the published platform, or the original image used by the information publisher when the information is published on other published platforms. Original Image.

It should be noted that, in order to avoid the loss of sharpness or distortion of the original image after multiple editing, the unwatermarked image may also be used when publishing the information associated with the published information for the first time. Picture, as the original picture associated with the watermark picture.

Optionally, in the local electronic device or other storage devices associated with the electronic device, the original picture associated with the watermarked picture is pre-stored. Correspondingly, the original picture can be searched through the watermarked picture, so that the original picture can be searched through the original picture. Instead of de-watermarking the watermarked pictures, it provides information material for subsequent information release, reduces the data processing cost, and improves the picture processing efficiency.

Exemplarily, to obtain the original picture associated with the watermarked picture, the original picture associated with the watermarked picture can be searched and obtained from the local electronic device or other storage devices associated with the electronic device through the description of the watermarked picture.

Since the descriptions of the drawings corresponding to different pictures may be the same, the search results of the original pictures associated with the watermarked pictures may be inaccurate in the search for the original pictures associated with the watermarked pictures through the descriptions of the drawings. In an optional implementation manner of the example, an original picture with high correlation with the watermarked picture may also be searched in the original picture library, and the found original picture is used as the original picture associated with the watermarked picture.

Exemplarily, the similarity between the original picture and the watermarked picture itself is determined, and according to the similarity determination result, the original picture associated with the watermarked picture is selected from each original picture. Specifically, one of the original pictures whose similarity is greater than the set similarity threshold may be selected as the original picture associated with the watermarked picture. Wherein, the setting of the similarity threshold can be determined by technical personnel according to needs or empirical values.

Exemplarily, in the original picture library, searching for the original picture with high correlation with the watermark picture may be: extracting the feature data of the watermark picture to obtain the watermark picture feature; The image features are compared; the original image associated with the watermarked image is determined according to the comparison result. It can be understood that the feature data extraction of the watermark image by image processing technology provides data support for the search and determination of the original image, and also avoids the increase in the amount of data caused by the comparison between the original image and the watermark image itself.

Specifically, determining the original image associated with the watermarked image according to the comparison result may be: determining the original image whose similarity with the watermarked image feature is greater than the set similarity threshold, and using the determined original image as the watermarked image The associated original image. And/or determine a set number of original pictures with the highest similarity with the watermarked picture feature comparison as candidate original pictures; select one of the candidate original pictures as the original picture associated with the watermarked picture. Among them, the set similarity threshold is determined by the technical personnel according to the needs or experience, and the set similarity threshold can be fine-tuned within a certain error range according to the actual comparison results; wherein, the set number is determined by the technical personnel according to the needs. It is determined by an empirical value, for example, a fixed value, or a fixed percentage, which is set as a variable value according to the product of the number of original pictures contained in the original picture library and the fixed percentage.

S103, upload the original image and text content to the platform to be released, and release the information.

The original image and text content are uploaded to the platform to be released, so that on the information release page of the platform to be released, new release information is generated according to the original image and text content.

It should be noted that, generally, in order to avoid copyright disputes, during the publishing process, a watermark associated with the platform to be published is added to the published original image.

The embodiment of the present application obtains the published information in the published platform; wherein, the published information includes the text content and the watermarked picture; obtains the original picture associated with the watermarked picture; uploads the original picture and the textual content to the platform to be published, Release information. The embodiment of the present application realizes the multiplexing of the text content in the published information by acquiring the published information, provides information materials for the subsequent information release on the platform to be released, and reduces the acquisition time of the text materials; The search of the original image replaces the watermarking process of the watermarked image, providing information material for the subsequent information release on the platform to be released, reducing the acquisition time of the image material; by using the original image associated with the text content and the watermarked image on the platform to be released. Publishing, thereby realizing the automatic migration of the published information from the published platform to the platform to be published, without manual editing of the published information, thereby improving the information publishing efficiency.

FIG. 2 is a flowchart of another image processing method provided by an embodiment of the present application, which is optimized and improved on the basis of the technical solutions of the foregoing embodiments.

Further, the operation "obtain the original picture associated with the watermarked picture" is refined into "perform feature extraction on the watermarked picture to obtain the watermarked picture feature; according to the watermarked picture feature, search for the original picture feature library associated with the watermarked picture. "Original Picture" to improve the acquisition mechanism of the original picture.

An image processing method as shown in Figure 2, comprising:

S201. Acquire published information on a published platform; wherein, the published information includes text content and watermarked pictures.

S202. Perform feature extraction on the watermarked picture to obtain features of the watermarked picture.

S203. According to the watermarked picture feature, determine the original picture feature associated with the watermarked picture in the original picture feature library.

S204: Obtain the original picture associated with the determined original picture feature as the original picture associated with the watermarked picture.

Exemplarily, the original image feature library is traversed in turn to determine the similarity between each original image feature in the original image feature library and the watermarked image feature; the original image feature associated with the watermarked image is determined from the original image feature library according to the similarity. ; According to the determined original picture feature, obtain the corresponding original picture as the original picture associated with the watermarked picture.

It can be understood that, by pre-extracting the feature data of each original image, the original image features are obtained, and added to the pre-built original image feature library. Therefore, in the process of determining the original image associated with the watermarked image, the feature of the watermarked image is directly searched and compared in the original image feature library, and there is no need to perform feature extraction for each original image, thereby improving the determination efficiency of the original image.

It should be noted that, with the increase in the number of information publishers in the same department and the increase in the working years of the information publishers, there may be a situation where the number of original pictures is too large. Correspondingly, the number of original image features in the original image feature library will also be larger, so that the method of searching for the original image features associated with the watermarked image in turn will take up a lot of data computing resources, and will also consume a relatively large amount of data. high time cost.

In order to avoid traversal interruption during the traversal process of the original image feature library, it is necessary to re-traverse the original image feature library, resulting in repeated data processing. During the original image feature library traversal process, real-time or timing can also be performed. The progress is saved, so that when the traversal is interrupted, the traversal of the original image feature library can be continued based on the latest stored progress position, thereby reducing unnecessary repeated operations.

In order to reduce the occupancy of data computing resources and improve the efficiency of data query, in an optional implementation of the embodiment of the present application, each original image feature in the original image feature library may be The publisher identifier of the information publisher is stored in batches, and multiple feature search libraries are obtained; correspondingly, according to the watermark picture feature, the original picture feature associated with the watermark picture is determined in the original picture feature library, which can be The feature library to be searched is determined from the original picture feature library according to the serialization attribute of the published information and/or the information publisher; the original picture feature associated with the watermark picture is searched in the feature library to be searched according to the watermark picture feature.

Among them, the serialization attribute can be understood as an attribute of other published information that is associated with time sequence and content before and after the published information. For example, serialized novels published on the platform are published information with serialization properties.

Wherein, the publisher identifier may be a unique publisher name or serial number or the like.

For example, when the information published on the published platform is a serialized novel, an original image feature library is created separately for the serialized novel to store the original image features of the original images in the published information in the serialized novel, so as to After the serialized novel is crawled on the published website of the published platform, the original image feature associated with the watermarked image in the crawled serialized novel is determined by searching and matching the original image feature library of the serialized novel, and then the original image The original picture associated with the feature is the original picture associated with the watermark picture. Since there is no need to search all original image feature databases, data query time and resource occupancy during data search are reduced.

For another example, a department has multiple information publishers, and different information publishers are responsible for publishing different types of content. In this case, the original image feature library can be created separately for different information publishers to store the original image features of the original images in the information published by the information publishers, so that the matching method can be searched through the watermark image features. The original image feature associated with the watermarked image is determined in the original image feature library, and then the original image associated with the original image feature is used as the original image associated with the watermarked image in the crawled data. Since there is no need to search all original image feature databases, data query time and resource occupancy during data search are reduced.

For another example, when a serialized novel is published alternately by multiple information publishers, it is also possible to construct an original image feature library of the original images of the serialized novel when the serialized novel is published for the parts of the serialized novel published by the information publishers, and then publish the original images in the published novels. After the serialized novel is crawled on the webpage, the original image feature library is searched according to the information publisher and the serialized novel to determine the original image feature associated with the watermarked image, and then the original image associated with the original image feature is used as the crawling data. The original image associated with the watermarked image in . Since there is no need to search all original image feature databases, data query time and resource occupancy during data search are reduced.

On the basis of the technical solutions of the above embodiments, in order to reduce the resource occupancy when determining the original image and improve the efficiency of determining the original image, in another optional implementation of the embodiments of the present application, the original image feature library is Each of the original picture features of the . Exemplarily, if the original image feature contains a re-release logo on a certain platform, it means that the release information corresponding to the original image associated with the original image feature has been released on the platform; The re-publishing logo indicates that the publishing information corresponding to the original image associated with the original image feature has not been published on this platform.

Correspondingly, unrepublished original image features are selected from the original image feature library according to the republished identifier; original image features associated with the watermarked image are determined according to the watermarked image features and the unrepublished original image features.

Specifically, the similarity between the watermarked picture feature and each unpublished original picture feature is determined; at least one original picture feature whose similarity is greater than the set similarity threshold is determined as the original picture feature associated with the watermarked picture. Wherein, the set similarity threshold is determined by personnel according to needs or experience.

S205, upload the original image and text content to the platform to be released, and release the information.

In the embodiment of the present application, the feature of the watermarked picture is obtained by extracting the features of the watermarked picture; according to the feature of the watermarked picture, the original picture feature associated with the watermarked picture is determined in the original picture feature library; the original picture feature associated with the determined original picture feature is obtained. The picture is used as the original picture associated with the watermarked picture, which avoids determining the original picture features for each original picture in the process of determining the original picture, which improves the efficiency of determining the original picture, thereby improving the release of information release on the platform to be released. Efficiency laid the foundation.

FIG. 3 is a flowchart of another image processing method provided by an embodiment of the present application, which is optimized and improved on the basis of the technical solutions of the foregoing embodiments.

Further, the operation "obtain the published information in the published platform" is refined into "according to the web page structure of the published platform, crawl the published information from the published web pages of the published platform"; correspondingly, The operation "Upload the original image and text content to the platform to be released for information release" is refined into "Upload the original image and text content to the platform to be released to release information according to the web page structure of the platform to be released", To improve the access mechanism of published information.

An image processing method as shown in Figure 3, comprising:

S301. According to the web page structure of the published platform, crawl published information from the published web pages of the published platform; wherein, the published information includes text content and watermark images.

Exemplarily, at least one content tag may be determined according to the web page structure of the published platform; according to each content tag, the published information including text content and watermark images is sequentially crawled from the published web pages of the published platform.

The web page structure of each platform may be pre-stored locally on the electronic device or in a storage device associated with the electronic device. Correspondingly, when the published platform performs information crawling, the web page results of the published platform are searched and obtained.

It is understandable that, in order to avoid network congestion or be identified as malicious operations by the platform for crawling and blocking, when a published platform crawls published information, the crawling frequency will be set for the published platform in advance, and then the crawling frequency will be set according to the crawling frequency. Frequency of crawling of published information in published pages of published platforms. The crawling frequency may be determined according to the blocked crawling frequency of the published platform.

S302. Obtain the original picture associated with the watermarked picture.

S303 , uploading the original image and text content to the platform to be released, so as to release information according to the web page structure of the platform to be released.

Exemplarily, the original picture and text content are uploaded to the platform to be released, so that a watermark associated with the platform to be released is added to the original picture to obtain a new watermarked picture; according to the webpage structure of the platform to be released, the text content and the new watermark are Images are typeset and published.

Exemplarily, if the web page structure of the published platform contains redundant web page tags that are not included in the web page structure of the platform to be published, the redundant content corresponding to the redundant web page tags in the crawled text content needs to be eliminated. , so that information is released on the platform to be released based on the deleted text content and the new watermark image.

Optionally, the original picture and text content can be uploaded to the platform to be released; a watermark associated with the platform to be released is added to the original picture to obtain a new watermarked picture; the webpage structure of the published platform and the webpage structure of the platform to be released are compared. Comparison; according to the comparison result, determine the redundant webpage tags in the webpage structure; remove the redundant content corresponding to the redundant webpage tags in the crawled text content; according to the webpage tags in the webpage structure of the platform to be published Attribute information of the proposed text content and new watermark images are typeset and published.

In order to reduce the amount of data uploaded, optionally, redundant webpage tags can be determined in advance according to the webpage structure of the published platform and the webpage structure of the platform to be released; Remove the remaining content; add a watermark associated with the platform to be published to the original image to obtain a new watermarked image; upload the new watermarked image and the removed text content to the platform to be published; The attribute information of the tag, typeset the uploaded information, and publish it.

It should be noted that the present application does not make any limitation on the sequence of the generation operation of the new watermark image and the processing operation of the text content.

Exemplarily, if the web page structure of the platform to be published includes additional web page tags that do not exist in the web page structure of the published platform, then according to the web page structure of the platform to be published, information is published, which may be: generating according to the text content. The description content corresponding to the extra webpage label; according to the webpage structure of the platform to be released, the original image, text content and description content are released on the platform to be released.

Exemplarily, the extra webpage tag can be at least one of information such as abstract, keyword, and subtitle; correspondingly, the text content can be semantically analyzed through the natural semantic processing technology in the artificial intelligence technology, and the corresponding extra webpage tag can be generated. description content.

It can be understood that, by generating the description content of the additional webpage label based on the text content, the content included in the information published on the platform to be published is improved, and data support is provided for information publishing on the platform to be published.

In the embodiment of the present application, when the published platform crawls the published information, the published information is crawled from the published web pages of the published platform according to the web page structure of the published platform; correspondingly, the information is published on the platform to be published. When the original image and text content are uploaded to the platform to be released, information has been released according to the web page structure of the platform to be released. By adopting the above technical solution, when the platform publishes information, the published information can be adapted to the typesetting requirements of the platform, thereby realizing the migration of published information between platforms with different typesetting requirements.

On the basis of the above technical solutions, when crawling the published information from the published web pages of the published platform according to the web page structure of the published platform, it is also possible to determine the published web page according to the published web pages of the published platform Whether there is a parallel web page associated with it; if the published web page is associated with a parallel web page, the published information will be crawled from the published web page according to the web page structure of the published platform, and the associated published information will be crawled from the parallel web page of the published web page. It is used to publish related publishing information on other platforms to be published.

It can be understood that by crawling the published information from a published web page of the published platform, the associated published information is crawled from the parallel web page associated with the published web page, so that the association in the parallel web page is crawled. When publishing information on other platforms to be published, it is no longer necessary to collect and crawl the related publishing information on the webpage, and just use the related publishing information directly, which improves the subsequent related publishing information. The publishing efficiency of the platform when publishing information.

Exemplarily, in order to avoid missing processing of the crawled published information, a message queue may also be set up to store the synchronously crawled associated published information; correspondingly, the subsequent associations are sequentially performed from the message queue Consumption processing of published information.

FIG. 4 is a flowchart of an image processing method provided by an embodiment of the present application, and the method provides a preferred implementation based on the technical solutions of the foregoing embodiments.

As shown in FIG. 4 , an image processing method includes: an information crawling stage 410 , an information matching stage 420 and an information publishing stage 430 .

Exemplarily, the information crawling stage 410 includes crawler crawling 411 , data cleaning 412 and watermark image extraction 413 . in,

The crawler 411 is used for crawling the published information from the published web pages of the published platform according to the set frequency according to the structure of the web page; the published information includes text content and watermark images.

Specifically, according to the webpage label when the published information is extracted, the text content and the watermark image in the published information are distinguished.

The watermark picture is a picture formed by adding a watermark associated with the published platform to the original picture published by the published platform.

The data cleaning 412 is used to organize the extracted text content and watermark pictures according to the web page structure of the published web page to form an initial document and store it in the content library.

The watermark picture extraction 413 is used for extracting the features of the watermark picture to obtain the features of the watermark picture.

Exemplarily, the information matching stage 420 includes: information filtering 421 and original picture determination 422 . in,

Information filtering 421 is used to filter the non-picture content associated with the original picture, add each filtered original picture to the local feature library, and store the original picture features of each original picture in association.

Specifically, if the original picture is stored in the Word document, the text content in the document can be filtered.

The original picture determination 422 is used to query the original picture feature associated with the watermarked picture in the image search feature library according to the feature similarity based on the feature similarity; and in the local feature library, find the original picture corresponding to the original picture feature as the The original image associated with the watermark image.

Among them, the image search feature library stores original image feature sub-bases constructed in batches according to serialization attributes and information publishers; according to the information publishers in the crawled published information and the serialization attributes of the crawled published information, Determine the original image feature sub-base in the image search feature library as the feature library to be queried; determine the feature similarity of each original image feature and the watermark image feature in the feature library to be queried; select one of the feature similarity greater than the set similarity threshold The original picture feature is used as the original picture feature associated with the watermarked picture.

Exemplarily, the information release stage 430 includes: threshold adjustment 431 and information release 432 .

in,

Threshold adjustment 431 is used to obtain the initial document from the content library; replace the watermark picture in the initial document with the original picture associated with the watermark picture to obtain the target document; compare the target document and the initial document; If the original image is different from the watermarked image in the initial document before the watermark is added, the similarity threshold will be set larger; if there is no original image corresponding to the watermarked image in the initial document in the target document, the similarity threshold will be set. Decrease the degree threshold.

Information release 432 is used for uploading the verified original picture associated with the watermark picture and the crawled text content to the platform to be released; information is released.

The platform to be published adds a watermark associated with the platform to be published to the original image to generate a new watermarked image; the new watermarked image and text content are typeset and published according to the web page structure of the platform to be published.

It should be noted that, in order to facilitate the subsequent search and comparison of the original image and the watermarked image, after determining the corresponding relationship between the original image and the watermarked image, the original image with the corresponding relationship and the watermarked image can be associated and uploaded to the cloud storage. server; when the original image associated with the watermark image needs to be obtained later, the original image is searched from the cloud storage server. In order to reduce the amount of data when uploading, you can also compress the image, and upload the compressed image to the cloud storage server. Correspondingly, when acquiring an image, the acquired image is decompressed and used.

5 is a structural diagram of an image processing apparatus provided by an embodiment of the present application. The image processing apparatus 500 includes: a published information acquisition module 501 , an original image acquisition module 502 , and an information release module 503 . in,

The published information acquisition module 501 is used to acquire the published information in the published platform; wherein, the published information includes text content and watermark pictures;

The original picture obtaining module 502 is used for obtaining the original picture associated with the watermark picture;

The information release module 503 is used for uploading the original picture and text content to the platform to be released for information release.

In the embodiment of the present application, the published information in the published platform is obtained through the published information acquisition module; wherein, the published information includes text content and watermark pictures; the original picture acquisition module obtains the original pictures associated with the watermark pictures; through the information The publishing module uploads the original image and text content to the platform to be published for information publishing. The embodiment of the present application realizes the multiplexing of the text content in the published information by acquiring the published information, provides information materials for the subsequent information release on the platform to be released, and reduces the acquisition time of the text materials; The search of the original image replaces the watermarking process of the watermarked image, providing information material for the subsequent information release on the platform to be released, reducing the acquisition time of the image material; by using the original image associated with the text content and the watermarked image on the platform to be released. Publishing, thereby realizing the automatic migration of the published information from the published platform to the platform to be published, without manual editing of the published information, thereby improving the information publishing efficiency.

Further, the original picture acquisition module 502 includes:

The feature extraction unit is used to perform feature extraction on the watermark image to obtain the feature of the watermark image;

an original picture feature determining unit, configured to determine the original picture feature associated with the watermark picture in the original picture feature library according to the watermark picture feature;

An original picture obtaining unit, configured to obtain the original picture associated with the determined original picture feature as the original picture associated with the watermark picture.

Further, the original picture feature determination unit includes:

a feature library to be searched determining subunit, configured to determine the feature library to be searched from the original image feature library according to the serialization attribute of the published information and/or the information publisher;

The original picture feature determination subunit is configured to search for the original picture feature associated with the watermark picture in the feature library to be searched according to the watermark picture feature.

Further, each original picture feature in the original picture feature library is stored with a re-release identifier, which is used to distinguish the re-release situation of the original picture associated with each original picture feature;

Correspondingly, the original image feature determination unit includes:

The original image feature screening subunit is used to filter the unrepublished original image features from the original image feature library according to the reissue identifier;

The original picture feature determination subunit is used to determine the original picture feature associated with the watermarked picture according to the watermarked picture feature and each unpublished original picture feature.

Further, the published information acquisition module 501 includes:

The published information crawling unit is used to crawl the published information from the published web pages of the published platform according to the web page structure of the published platform;

Correspondingly, the information release module 503 includes:

The information release unit is used to upload the original pictures and text content to the platform to be released, so as to release information according to the web page structure of the platform to be released.

Further, the published information crawling unit includes:

The parallel webpage determination subunit is used to determine whether the published webpage is associated with a parallel webpage according to the published webpage of the published platform;

The associated published information crawling sub-unit is used to crawl published information from the published web page according to the web page structure of the published platform if the published web page contains associated parallel web pages, and from the parallel web pages of the published web page, Crawl the associated release information to publish the associated release information on other platforms to be released.

Further, if the web page structure of the platform to be published includes additional web page tags that do not exist in the web page structure of the published platform, the information publishing unit includes:

The description content generation subunit is used to generate description content corresponding to the extra webpage label according to the text content;

The information release subunit is used to release the original image, text content and description content on the platform to be released according to the web page structure of the platform to be released.

The above-mentioned image processing apparatus can execute the image processing method provided by any embodiment of the present application, and has corresponding functional modules and beneficial effects for executing the image processing method.

According to the embodiments of the present application, the present application further provides an electronic device and a readable storage medium.

As shown in FIG. 6 , it is a block diagram of an electronic device implementing the image processing method of the embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are by way of example only, and are not intended to limit implementations of the application described and/or claimed herein.

As shown in FIG. 6, the electronic device includes: one or more processors 601, a memory 602, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or otherwise as desired. The processor may process instructions executed within the electronic device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In other embodiments, multiple processors and/or multiple buses may be used with multiple memories and multiple memories, if desired. Likewise, multiple electronic devices may be connected, each providing some of the necessary operations (eg, as a server array, a group of blade servers, or a multiprocessor system). A processor 601 is taken as an example in FIG. 6 .

The memory 602 is the non-transitory computer-readable storage medium provided by the present application. The memory stores instructions executable by at least one processor, so that the at least one processor executes the image processing method provided by the present application. The non-transitory computer-readable storage medium of the present application stores computer instructions, and the computer instructions are used to cause the computer to execute the image processing method provided by the present application.

As a non-transitory computer-readable storage medium, the memory 602 can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the image processing method in the embodiments of the present application (for example, appendix). The published information acquisition module 501, the original picture acquisition module 502, and the information release module 503 shown in FIG. 5). The processor 601 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions and modules stored in the memory 602, ie, implements the image processing method in the above method embodiments.

The memory 602 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function; the storage data area may store data created by the use of an electronic device implementing the image processing method, etc. . Additionally, memory 602 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 602 may optionally include memory disposed remotely relative to the processor 601, and these remote memories may be connected to the electronic device implementing the image processing method through a network. Examples of such networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

The electronic device implementing the image processing method may further include: an input device 603 and an output device 604 . The processor 601 , the memory 602 , the input device 603 and the output device 604 may be connected by a bus or in other ways, and the connection by a bus is taken as an example in FIG. 6 .

The input device 603 can receive input numerical or character information, and generate key signal input related to user settings and function control of the electronic device implementing the image processing method, such as a touch screen, a keypad, a mouse, a trackpad, a touchpad, a pointing stick , one or more mouse buttons, trackballs, joysticks and other input devices. Output devices 604 may include display devices, auxiliary lighting devices (eg, LEDs), haptic feedback devices (eg, vibration motors), and the like. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some implementations, the display device may be a touch screen.

Various implementations of the systems and techniques described herein can be implemented in digital electronic circuitry, integrated circuit systems, application specific ASICs (application specific integrated circuits), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.

These computational programs (also referred to as programs, software, software applications, or codes) include machine instructions for programmable processors, and may be implemented using high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages calculation program. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or apparatus for providing machine instructions and/or data to a programmable processor ( For example, magnetic disks, optical disks, memories, programmable logic devices (PLDs), including machine-readable media that receive machine instructions as machine-readable signals. The term "machine-readable signal" refers to any signal used to provide machine instructions and/or data to a programmable processor.

To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.

The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.

According to the technical solutions of the embodiments of the present application, by acquiring the published information, multiplexing of the text content in the published information is realized, information materials are provided for subsequent information release on the platform to be released, and the acquisition time of the text materials is reduced; By searching for the original image of the watermarked image instead of removing the watermarking process of the watermarked image, information materials are provided for subsequent information release on the platform to be released, and the acquisition time of image materials is reduced; by using the text content and the original image associated with the watermarked image in Information is released on the platform to be released, thereby realizing automatic migration of released information from the platform to be released to the platform to be released, without manual editing of the released information, thereby improving the efficiency of information release.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present application can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in the present application can be achieved, no limitation is imposed herein.

The above-mentioned specific embodiments do not constitute a limitation on the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of this application shall be included within the protection scope of this application.

Claims (16)

1. An image processing method, comprising: Obtain the published information in the published platform; wherein, the published information includes text content and watermark images; obtaining the original picture associated with the watermark picture; The original picture and the text content are uploaded to the platform to be released, and information is released. 2. The method according to claim 1, wherein obtaining the original picture associated with the watermark picture comprises: Perform feature extraction on the watermarked image to obtain watermarked image features; According to the watermark picture feature, determine the original picture feature associated with the watermark picture in the original picture feature library; The original picture associated with the determined original picture feature is acquired as the original picture associated with the watermarked picture. 3. The method according to claim 2, wherein, according to the watermark picture feature, determining the original picture feature associated with the watermark picture in the original picture feature library, comprising: According to the serialization attribute of the published information and/or the information publisher, determine the feature library to be searched from the original picture feature library; According to the feature of the watermarked picture, in the feature library to be searched, the original picture feature associated with the watermarked picture is searched. 4. The method according to claim 2, wherein each original picture feature in the original picture feature library is stored with a re-release identification for distinguishing the re-release situation of the original picture associated with each original picture feature; Correspondingly, according to the watermark picture feature, determine the original picture feature associated with the watermark picture in the original picture feature library, including: According to the re-release identifier, filter the original image features that have not been re-released from the original image feature library; According to the feature of the watermarked picture and the features of each of the original unpublished pictures, the feature of the original picture associated with the watermarked picture is determined. 5. The method according to any one of claims 1-4, wherein obtaining the published information in the published platform comprises: According to the web page structure of the published platform, crawling the published information from the published web pages of the published platform; Correspondingly, uploading the original picture and the text content to the platform to be released for information release, including: Uploading the original picture and the text content to the platform to be published, so as to publish information according to the web page structure of the platform to be published. 6. The method according to claim 5, wherein, according to the web page structure of the published platform, crawling the published information from the published web pages of the published platform, comprising: According to the published web pages of the published platform, determine whether the published web pages are associated with parallel web pages; If the published web page is associated with a parallel web page, crawl the published information from the published web page according to the web page structure of the published platform, and crawl the published web page from the parallel web pages of the published web page. Get the associated release information, which is used to release the associated release information on other platforms to be released. 7. The method according to claim 5, wherein, if the web page structure of the platform to be published includes additional web page tags that do not exist in the web page structure of the published platform, the web page structure of the platform to be published is based on the , to release information, including: generating description content corresponding to the additional webpage tag according to the text content; According to the webpage structure of the platform to be published, the original picture, the text content and the description content are published on the platform to be published. 8. An image processing device, comprising: A published information acquisition module, used to acquire the published information in the published platform; wherein, the published information includes text content and watermark pictures; an original image acquisition module, used to acquire the original image associated with the watermark image; The information release module is used for uploading the original picture and the text content to the platform to be released for information release. 9. The apparatus according to claim 8, wherein the original picture acquisition module comprises: a feature extraction unit, configured to perform feature extraction on the watermarked picture to obtain watermarked picture features; an original picture feature determining unit, configured to determine the original picture feature associated with the watermark picture in the original picture feature library according to the watermark picture feature; An original picture obtaining unit, configured to obtain the original picture associated with the determined original picture feature as the original picture associated with the watermark picture. 10. The apparatus according to claim 9, wherein the original picture feature determination unit comprises: a feature library to be searched determining subunit, configured to determine the feature library to be searched from the original image feature library according to the serialization attribute of the published information and/or the information publisher; The original picture feature determination subunit is configured to search for the original picture feature associated with the watermark picture in the feature library to be searched according to the watermark picture feature. 11. The device according to claim 9, wherein each original picture feature in the original picture feature library is stored with a redistribution mark for distinguishing the redistribution situation of the original picture associated with each original picture feature; Correspondingly, the original picture feature determination unit includes: an original picture feature screening subunit, used for screening unrepublished original picture features from the original picture feature library according to the re-release identifier; The original picture feature determination subunit is configured to determine the original picture feature associated with the watermarked picture according to the watermarked picture feature and each of the unpublished original picture features. 12. The apparatus according to any one of claims 8-11, wherein the published information acquisition module comprises: A published information crawling unit, configured to crawl the published information from the published web pages of the published platform according to the web page structure of the published platform; Correspondingly, the information release module includes: An information release unit, configured to upload the original picture and the text content to the platform to be released, so as to release information according to the web page structure of the platform to be released. 13. The apparatus of claim 12, wherein the published information crawling unit comprises: a parallel web page determination subunit, configured to determine whether the published web page is associated with a parallel web page according to the published web page of the published platform; The associated published information crawling subunit is configured to crawl the published information from the published web page according to the web page structure of the published platform if the published web page contains associated parallel web pages, and retrieve the published information from the published web page. In the parallel web pages of the published web pages, the associated publication information is crawled for publishing the associated publication information on other platforms to be published. 14. The apparatus according to claim 12, wherein, if the web page structure of the platform to be published includes additional web page tags that do not exist in the web page structure of the published platform, the information publishing unit comprises: a description content generating subunit, configured to generate description content corresponding to the additional webpage tag according to the text content; The information publishing subunit is configured to publish the original picture, the text content and the description content on the platform to be published according to the web page structure of the platform to be published. 15. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the execution of any of claims 1-7 an image processing method. 16. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform an image processing method according to any one of claims 1-7.

Images