WO2019174606A1 - Image processing method and terminal - Google Patents

Abstract

Provided are an image processing method, a terminal, and a computer storage medium. The method comprises: starting a session interface in an application that supports communication on a terminal, and obtaining image data comprising the session interface; identifying, in the image data, a target region where sensitive information in the session interface is located; and performing, in the image data, privacy protection processing on the target region, and obtaining privacy image data, wherein the session interface comprises a session between users.

Description

Image processing method and terminal

This application is required to be submitted to the Chinese Patent Office on March 15, 2018, application number 201810215678.X, the name is "an image processing method and device", and submitted to the Chinese Patent Office on March 15, 2018, the application number is 201810215115.0. The priority of the Chinese Patent Application, which is incorporated herein by reference in its entirety in its entirety in its entirety in the the the the the the the the the

Technical field

The present disclosure relates to the technical field of computer processing, and in particular to an image processing method and terminal.

Background technique

With the development of technology, mobile terminals such as mobile phones and tablet computers are increasingly used in people's work, study, and daily communication.

In order to communicate using a mobile terminal, users often install communication tools in these mobile terminals to open a conversation window with other users in the installed communication tool and communicate with other users in the conversation window. In some scenarios, users will share session records in the session window when communicating with other users to facilitate other users to understand the content of the session or to obtain relevant information.

When sharing, users usually share the content of the session window. However, in order to protect privacy, users generally choose to protect some private information.

To this end, the user usually first intercepts the screen of the session window to save the image data, and then enables a special image editing tool to smear the private information recorded in the image data, and then share the processed image data.

Summary of the invention

According to an aspect of the present disclosure, an image processing method is provided, including:

Obtain image data containing a session interface;

Identifying, in the image data, a target area in which the sensitive information in the session interface is located;

Performing a privacy protection process on the target area in the image data to obtain privacy image data;

The session interface includes a session between users.

In accordance with another aspect of the present disclosure, a terminal is provided comprising a memory and a processor, the memory storing a computer program executable on the processor, the processor configured to run the computer program to Said terminal implementation:

Obtain image data containing a session interface;

Identifying a target area in which the sensitive information in the session interface is located in the image data;

Performing a privacy protection process on the target area in the image data to obtain privacy image data;

The session interface includes a session between users, and the sensitive information includes user information.

According to still another aspect of the present disclosure, a computer readable nonvolatile storage medium storing a computer program, wherein the computer program is executed by a processor, implements the image processing method described above.

DRAWINGS

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the present disclosure, Those skilled in the art can also obtain other drawings based on these drawings without paying any creative work.

1 is a schematic structural diagram of hardware of a mobile phone according to some embodiments of the present disclosure;

2 is a flow chart of steps of an image processing method according to some embodiments of the present disclosure;

3A to 3H are diagrams showing an example of performing an image processing method provided by some embodiments of the present disclosure on a mobile terminal;

FIG. 4 is a structural block diagram of an image processing apparatus according to some embodiments of the present disclosure.

detailed description

The above-described objects, features and advantages of the present disclosure will become more apparent from the aspects of the appended claims.

The image processing method provided by some embodiments of the present disclosure may be applied to a mobile terminal, such as a mobile phone, a tablet computer, a smart wearable device (such as a smart watch, smart glasses), and the like; or may be applied to a non-mobile terminal, such as a personal computer. The smart television, and the like, the embodiment of the present disclosure does not limit this.

The operating systems of these mobile terminals and non-mobile terminals include Android (Android), IOS, and Windows Phone. On these operating systems, applications that support communication are usually run, for example, instant messaging tools, email clients, microblog applications, forums. Application, etc. In some embodiments, the user initiates a session interface in an instant messaging tool, a mailbox client, a microblog, a forum, etc., to engage with friends, non-friends, strangers, group users, etc., and form a session record.

The session interface is typically in the form of a session window. The session window usually includes private information such as a group avatar, a group name, a user name, and a user avatar. In the terminal, the image including the session window can be protected by privacy, for example, smearing, covering, obscuring, and hollowing out. The privacy information is processed in a manner to protect the user's private information.

The following is a mobile phone as an example to illustrate how the terminal implements the technical solution of the image processing method. It should be understood that the handset 100 shown in FIG. 1 is merely an example, and a handset in an actual application may have more or fewer components than the handset of FIG.

As shown in FIG. 1, the mobile phone 100 includes a processor 01, a signal transmitting and receiving circuit 02, a display screen 03, a touch screen 04, a power source 05, a memory 06, an audio circuit 07, a camera 08, and a sensor 09.

The signal transceiving circuit 02 is configured to receive and transmit signals. When the mobile phone opens a conversation window to perform a chat session, the signal transceiving circuit 02 sends the information to the chat object or sends the information sent by the chat object to the processor for processing. In some embodiments, the signal transceiving circuit 02 includes a radio frequency circuit, WIFI, and Bluetooth. The radio frequency circuit includes, for example, an antenna, an amplifier, a duplexer, and the like. Wireless Fidelity (WIFI) and Bluetooth communicate wirelessly with other terminals using appropriate communication protocols.

The display screen 03 is configured to display images, data, and a user interface, which may be a liquid crystal display, an organic electroluminescent display, or the like.

The touch screen 04 is configured to input a user instruction, the user performs a touch press operation on the touch screen 04, and the touch screen 04 converts the sensed operation into a user instruction, and transmits the user instruction to the processor 01 for processing. The device 01 performs the corresponding function after receiving the user instruction.

The memory 06 is capable of storing a computer software program, and the processor 01 performs various operations by running the computer software program. The memory 06 may be a high speed random access memory, a nonvolatile memory, or a volatile fixed memory or the like.

The audio circuit 07 is configured to accept audio and output audio. The audio circuit 07 includes a microphone and a speaker capable of converting a sound signal into an electrical signal, and the speaker is capable of converting the received electrical signal into a sound signal.

The camera 08 is configured to take still pictures or short films and is a very important additional component of the mobile phone.

The sensor 09 is configured to sense changes in the handset and the external environment. For example, the sound sensor can sense the size of the external sound and send the sensing result to the processor 01, and the processor 01 adjusts the sound volume emitted by the speaker; the ambient light sensor can sense the brightness of the ambient light and send the sensing result to the The processor 01 adjusts the brightness of the display screen 03 by the processor 01; the acceleration sensor can sense the magnitude and direction of the gravity to identify the usage state of the mobile phone, such as a horizontal screen display and a vertical screen display.

The power source 05 is configured to supply power to the processor 01, the signal transceiving circuit 02, the display screen 03, the touch screen 04, the memory 06, the audio circuit 07, the camera 08, and the sensor 09.

The image processing method to be described below can be implemented on the mobile phone 600 having the above-described hardware configuration.

FIG. 2 is a flow chart of steps of an image processing method according to some embodiments of the present disclosure. The image processing method may include S100-S106:

S100, monitor the screenshot operation.

The screenshot operation can be implemented as a screen capture, a screenshot, a photograph, and the like. In some embodiments, the screenshot operation can be monitored in at least one of the following ways:

1, listening to the broadcast

In the operating system, the listener is registered for the screenshot operation, and the broadcast sent when the screenshot operation is monitored.

2, monitor the physical button

In the mobile terminal, most of the physical button combinations are supported to perform the screenshot operation quickly. For example, pressing the power button and the volume down button simultaneously performs a screenshot operation, and the combination of the physical buttons can be monitored by the screenshot operation.

3, monitor image data changes

There is a media database in the Android system. Each time you take a photo, or use the system screen capture to capture an image, it will add its details to the media database and issue a content change notification. Therefore, you can use the content observer (Content Observer). Listening to changes in the media database, when the database changes, the last inserted image data is obtained, and if the image data meets a specific rule, the screenshot operation is considered to be performed.

Taking a screen capture operation as an example, the specific rule includes one or more of the following:

3.1, time rules

The generation time of the image data is after the start of the monitoring and is separated from the current time by a threshold (for example, 10 seconds).

3.2, size rules

The size of the image data does not exceed the size of the screen, and if it is a sliding screen, the width or length of the image data does not exceed the width or length of the screen.

3.3, path judgment

The path of the image data contains specific keywords such as "screenshot".

Of course, the manner of monitoring the screenshot operation is only an example. In the implementation of the embodiment of the present disclosure, other manners of monitoring the screenshot operation may be set according to actual conditions, which is not limited by the embodiment of the present disclosure. In addition, in addition to the above manner of monitoring the screenshot operation, those skilled in the art may also adopt other manners for monitoring the screenshot operation according to actual needs, and the embodiment of the present disclosure does not limit this.

If the user is monitored to perform the screenshot operation, the screenshot content corresponding to the screenshot operation may be detected, that is, the interface content at the time of the screenshot.

S100', identifying whether the screenshot content in the image data obtained in the screenshot operation includes a session window.

When the screenshot operation is detected, the screenshot content in the image data obtained in the screenshot operation is identified; if the screenshot content includes a session window, the screenshot content is determined to be image data including a session window. If the screenshot content does not include a session window, the image data obtained by the screenshot operation is displayed.

In some embodiments of the present disclosure, S100' includes:

Matching the image data obtained by the screenshot operation with a preset session image template;

When the image data is successfully matched with the session image template, it is determined that the screenshot content of the screenshot operation includes a session window.

In some embodiments of the present disclosure, the UI (User Interface) designed for the session window is relatively stable over a period of time, and thus may be based on image data having features in the UI of the session window of different applications. Set the session image template to store the set session image template in the database.

If the screenshot operation is detected, the image data obtained by the screenshot operation may be acquired, and the image data may be matched with the session image template of the specific application by means of image similarity or the like, or may be matched with the session image template one by one.

In some embodiments of the present disclosure, the feature information of the image data and the feature information in the session image template may be extracted, and then the extracted feature information is subjected to similarity calculation.

The feature information may include at least one of shape feature information and color feature information; the shape feature information may refer to information that characterizes image shape characteristics, and the color feature information may refer to information that characterizes image color characteristics.

There are two main types of representation methods for shape feature information, one is the region feature, which is mainly for the entire shape region of the image, and the other is the contour feature, which is for the outer boundary of the object.

Typical methods for extracting shape feature information include boundary eigenvalue method (outer boundary of image), geometric parameter method (image geometric parameterization processing), shape invariant moment method (finding image invariant moment feature), and Fourier shape description method (Fourier transform method) and so on.

The color feature information may be described by the color features of the image or image area, which is holistic.

Typical methods of extracting color feature information include color histograms, color sets, color moments, and the like.

Of course, the above-mentioned feature information is only an example. When the embodiment of the present disclosure is implemented, other feature information may be set according to actual conditions, which is not limited by the embodiment of the present disclosure.

If the similarity between the image data and the session image template is higher than a preset threshold, it may be considered that the matching between the two is successful, and the screenshot content of the screenshot operation is determined to include the session window.

In addition to the above manner of matching with the session image template, those skilled in the art may also adopt other methods for detecting the content of the screenshot according to actual needs, for example, detecting an application to which the uppermost window of the operating system belongs, if the application is a loadable session window. The application determines that the screenshot content includes a session window, and embodiments of the present disclosure do not limit this.

S100", determining whether to perform privacy protection processing on the image including the session window.

If the screenshot content includes a session window, then the manner in which the image is processed is determined. If the image is not required to be subjected to the privacy protection process, the image data obtained by the screenshot operation is displayed; if the image needs to be subjected to the privacy protection process, then S101 is performed.

S101. Acquire image data including a session window.

In some embodiments, the user launches a session window in an instant messaging tool, a mailbox client, a microblog, a forum, etc., to engage with friends, strangers, group users, etc., and form a session record.

At this time, the user can form image data for the session window by means of screen capture, screenshot, photographing, etc., wherein the image data is image data of the user interface layer. In some embodiments, the user may perform a screen capture process on the session window, or may call a previously stored session record, or use a session record sent by another device, and use the formed or received image data as image data to be processed. .

S102. Identify, in the image data, a target area where the sensitive information in the session window is located. In some embodiments of the present disclosure, the sensitive information is private information, and before the sharing, the target area in which it is located is identified, and the user information is protected.

The sensitive information includes user information, and the user information includes at least one of the following:

Group avatar, group name, user name, user avatar.

Of course, the foregoing user information is only used as an example. In some embodiments, other user information is set according to actual conditions, and the disclosure does not limit this. In addition, in addition to the foregoing user information, other user information may be used by those skilled in the art according to actual needs, and the disclosure does not limit this.

The user information in the session window has certain characteristics (such as area, location, shape, etc.) with which the user information in the session window is identified from the image data.

In some embodiments, in the session window of the application, the user's own user avatar is located on the right side, and the other user's user avatar is located on the left side; the user's own user name is located on the left side of the user's own avatar, and other users' users are located. The name is located to the right of the other user's user avatar.

In some embodiments, in a session window of an application, when a user conducts a session with another single user, information such as a user avatar, a user name, and the like of the single user is displayed at the top of the session window, and when the user performs a session in the group, The group avatar, group name and other information of the group is displayed at the top of the session window.

In some embodiments, the shape of the user's avatar is square or circular in the session window of the application.

In some embodiments, the S102 further includes S201-S204:

S201. Divide a target image from the image data.

In the session window, the user information that is more concerned with privacy, such as group avatar, group name, user name, user avatar, etc., can be separated, so that the image data can be separated, and the target image containing the user information is from the session window. The scene is taken out so that subsequent processing can focus on the target image where the user information is located.

In some embodiments, S201 includes the following sub-steps S11-S13:

S11, performing grayscale processing on the image data.

For a given image data I(x,y) _color , the red, green and blue three-channel pixels contained are represented as I(x,y) _red , I(x,y) _green , I(x,y) _Yellow .

Where x, y represent the index positions of the abscissa and the ordinate in the image, respectively, and the image data is grayscale processed by the following formula:

I(x,y) _gray =0.299I(x,y) _red +I(x,y) _green +I(x,y) _blue formula 1

Where I(x, y) _gray is image data after gradation processing.

S12, performing binarization processing on the image data after the gradation processing.

First, the image data is subjected to gradation processing to convert the image data from color image data to grayscale image data, and then performing binarization processing to convert the image data from grayscale image data to binary value. (eg 0, 1) image data.

Taking the maximum inter-class variance method as an example, the maximum inter-class variance method is an adaptive threshold determination method. The image data is divided into a background image and a foreground image (ie, a target) according to the gradation characteristics of the image data.

The larger the variance between the background image and the foreground image, the greater the difference between the background image and the foreground image constituting the image data. When the partial foreground image is misclassified into the background image or part of the background image is divided into the foreground image, the background will be caused. The difference between the image and the foreground image becomes smaller. Therefore, the segmentation that maximizes the variance between classes means that the probability of misclassification is minimal.

In some embodiments, for the image data I(x, y) _gray after the gradation processing, the segmentation threshold of the foreground image and the background image is denoted by T, and the number of pixels belonging to the foreground image occupies the entire image data I(x, y The ratio of _gray is ω ₀ , and its average gradation μ ₀ , the number of pixels belonging to the background image is ω ₁ in the ratio of the entire image data I(x, y) _gray , and the average gradation is μ ₁ . The total average gray scale of the image data I(x, y) _gray is denoted by μ, and the variance between classes is denoted by g.

It is assumed that the background of the image data I(x, y) _gray is dark, and the size of the image data I(x, y) _gray is M×N, and the pixel in the image data I(x, y) _gray is smaller than the threshold T. The number is recorded as N ₀ , and the number of pixels whose pixel gradation is greater than the threshold T is denoted as N ₁ , and the following conditions are met:

ω ₀ =N ₀ /M×N Equation 2

ω ₁ =N ₁ /M×N Equation 3

N ₀ +N ₁ =M×N Equation 4

ω ₀ +ω ₁ =1 Equation 5

_{μ = ω 0 * μ 0 +} ω 1 * μ 1 formula ⑥

g=ω ₀ (μ ₀ -μ) ² +ω ₁ (μ ₁ -μ) ² Equation 7

Combining the above conditions, the equivalent formula is obtained: g = ω ₀ ω ₁ (μ _{0 -} μ ₁ ) ² Equation 8

The entire image data is traversed to obtain a threshold T that maximizes the variance between the classes, and the maximum threshold T is used to divide the foreground image and the background image, and the following binary segmentation is followed:

If I(x _i , y _i )>T, then I(x _i , y _i ) _binary =1

If I(x _i , y _i ) < T, then I(x _i , y _i ) _binary =0

Where I(x _i , y _i ) _binary is image data after binarization, and I(x _i , y _i ) is the i-th pixel point.

S13, dividing the foreground image from the image data after the binarization processing, and using the divided foreground image as the target image.

After the binarization processing, the image processing terminal recognizes from the image data which regions are foreground images (such as pixels having a value of 0), that is, target images containing user information.

Of course, the manner of dividing the target image is only an example. In some embodiments, other manners of dividing the target image are set according to actual conditions. For example, after enhancing the contrast of the image data, the foreground image in the image data is extracted by using a Gaussian model as a target. The image is not limited in this disclosure. In addition, in addition to the above-described manner of dividing the target image, those skilled in the art may also adopt other manners of dividing the target image according to actual needs, and the disclosure does not limit this.

S202. Mark a boundary area of the target image.

Determining the boundary region, that is, determining the outer boundary of the target image, the boundary of the hole, and the hierarchical relationship thereof, and the boundary regions and the regions of the image data have a one-to-one correspondence, for example, in the binarized image, the outer boundary corresponds to a pixel value of 1. The connected area, the hole boundary corresponds to a connected area with a pixel value of zero.

Thus, in some embodiments, the boundary regions are used to represent and divide the image, traversing the entire image data, thereby calibrating the boundary regions of the user information in the image data.

In some embodiments, the target image located in a predetermined designated area (such as a range having a certain distance from the left and right edges) is subjected to expansion processing, and the boundary image is marked on the target image after the expansion processing.

In some embodiments, the user information such as the user's avatar is usually located in a preset designated area, and there are many holes in the designated area. Therefore, the target image in the designated area is expanded, so that the target image becomes a whole. Convenient for subsequent processing.

The expansion processing operation needs to set the expansion operator D, and the expansion operator D and the binary image data I(x _i , y _i ) _{binary are} combined to obtain the processed _binary image as II (x _i , y _i ) _binary .

Of course, for user information such as a user name, or user information that is not to be protected by privacy, such as a session frame, a session record, and a time, the boundary area can be directly calibrated.

S203. Generate a candidate area on the basis of the boundary area.

The target area of the target image generation specification for the boundary area is calibrated.

In some embodiments, the largest rectangle formed by the circumscribed boundary region is calculated as the target region. The largest rectangle formed therein refers to the largest area of the rectangle. Of course, in addition to the rectangle, in other embodiments, other graphics are generated, such as elliptical, circular, star, etc., and the disclosure is not limited thereto.

S204. Determine, in the candidate area, a target area where the user information is located in the session window.

The target image identified in the image data may contain other information, such as a session box, session record, time, etc., in addition to the required user information, and thus, in some embodiments, further recognition from the candidate region The target area where the user information for privacy protection is located.

In some embodiments, if the user information to be privacy protected is a user avatar, determining that the candidate area in the preset designated area (such as a range of a certain distance from the left and right edges) is the user avatar in the session window. The target area at the location. In other embodiments, if the user information to be privacy protected is the user name, in some cases, the user name is displayed, and in other cases, the user name is not displayed.

Therefore, when the user name is identified, the candidate area in the session window in the session window is searched for in an area outside the designated area, where the session box is the area carrying the session record.

In some embodiments, the candidate image is outside the designated area as the area in which the user name is located, and in other embodiments, the candidate image outside the designated area is the area in which the session box, session record, time, and the like are located.

The height and area of the image including the user name, session record, time, and the like are the same or similar, and are difficult to distinguish. The parameters such as the height and area of the image containing the session record of the session frame are larger than the user name, session record, time, etc. The image of the information is easier to distinguish, and the relative position between the user name and the session box and the user's avatar is fixed. Therefore, by comparing parameters such as height and area, the session box in the session window is found, thereby identifying the user. name.

In order to represent a certain session record sent by a user, the user's avatar of the user is usually displayed adjacent to the session record of the user along with the session box, so that the target area and the session box where at least part of the user avatar with the same ordinate is located are searched. The candidate region is located, and the target region in which the user avatar is located (which may be based on the top) and the candidate region in which the session frame is located (which may be based on the top) are the ordinate difference values.

When the ordinate difference between the target area where the user avatar is located and the candidate area where the session box is located is greater than a preset threshold, the candidate area located between the user avatar and the session box is where the user name is located in the session window. Target area.

When the ordinate difference between the target area where the user avatar is located and the candidate area where the session box is located is less than or equal to a preset threshold, the user name is not displayed in the session window.

Set the candidate area in the specified area to the target area where the user's avatar is located. The candidate area with the largest parameter such as traversal height and area is the area where the session box is located, and find the user avatar (candidate area) and the session box with at least the same ordinate. (candidate area), if the position difference between the user avatar and the session frame is greater than a preset threshold, the candidate image between the user avatar (candidate area) and the session frame (candidate area) is set as the user name. . Set another specified location at the top of the session window to the target zone where the group name is located.

Of course, the above manner of identifying user information is only an example. When implementing the present disclosure, other ways of identifying user information are set according to actual conditions, for example, identifying a candidate area of another designated area located at the top of the session window as a user name or group. The target area in which the group name is located is not limited in this disclosure. In addition, in addition to the above manner of identifying user information, those skilled in the art may also adopt other ways of identifying user information according to actual needs, and the disclosure does not limit this.

S103: Perform privacy protection processing on the target area in the image data. After identifying the target area where the user information is located, in the image data, performing privacy protection processing on the target area, so that the user information cannot be clearly distinguished in the processed image, thereby protecting user information in the target area. After that, the user can share the image data to other places without revealing the user information.

In some examples of the privacy protection process, the target area in the image data is smeared with a mask image of a specified size (eg, a red image, a mosaic) to obtain the target image data.

In some embodiments, the same type of user information uses the same size of the occlusion image, and different types of user information may use the same or different occlusion image sizes. For example, the masked image that smears the user's avatar is a square, and the masked image that smears the user's name is a rectangle.

If the user information is partially obscured in the session window, the size of the shadow image may be adjusted according to the shaded area such that the shadow image is not applied to the shaded area.

In some embodiments, when the user avatar is removed at the top of the conversation window, the upper portion of the user avatar is obscured while the lower portion is unmasked, at which point the size of the occlusion image is adjusted to smear the exposed lower portion.

In some embodiments, when the user's avatar is moved in at the bottom of the conversation window, the lower portion is shaded and the upper portion is unmasked. At this time, the size of the shadow image is adjusted to smear the exposed upper portion.

In some embodiments, in addition to smearing a masked image of a specified size, other privacy protection processes are employed, such as overlaying other occlusion images (eg, overlaying a cartoon image on a user avatar), hollowing out, etc., without limitation.

S104. Display the privacy image data.

If the user information is hidden in the privacy image data, it can be displayed to the user for other processing.

In order to enable those skilled in the art to better understand the embodiments of the present disclosure, the image processing method in the embodiments of the present disclosure will be described below by way of specific examples.

As shown in FIG. 3A, the example is applied in a mobile terminal to listen to a screenshot operation, assuming that the user performs a session and screenshots in a group of instant messaging tools.

At this time, if the mobile terminal monitors the screenshot operation, the image data obtained by the screenshot is acquired, and whether the session window is included in the image data is detected.

If the image data includes a session window, as shown in FIG. 3B, a prompt message is generated to prompt the user to include privacy information in the screenshot and whether to perform privacy protection processing on the image data.

If the user clicks "No", the image data is not subjected to privacy protection processing, and the image data is directly displayed.

If the user clicks "Yes", the image data is subjected to privacy protection processing.

As shown in FIG. 3C, the image data obtained by the screenshot is color image data (not shown), and the image data is subjected to gradation processing to convert the color image data into grayscale image data.

As shown in FIG. 3D, the image data after the gradation processing is binarized to separate the foreground image (target image) from the background image.

The foreground image (target image) includes user information such as a user box and a user name waiting for privacy protection, and includes user information such as a session box and a session record that are not protected by privacy.

As shown in Fig. 3E, for the foreground image (target image) located in the designated area, such as the user's avatar, the expansion process is performed and the boundary area is calibrated, and for other foreground images (target image), the boundary area is directly calibrated.

As shown in FIG. 3F, the maximum circumscribed rectangle of the boundary region is calculated, and the largest circumscribed rectangle is used as the candidate region.

As shown in FIG. 3G, the target area in which the group name is located is located in the image data (color not shown in the drawing), and the masked image of the specified size is applied to the target area, thereby obtaining the privacy image data.

The top user avatar is ready to move out of the session window, obscuring the upper portion and exposing the lower portion. Therefore, the size of the occlusion image is modified to shield the exposed lower portion without processing the upper portion of the occlusion.

As shown in FIG. 3H, the privacy image data is displayed to the user.

In some embodiments of the present disclosure, when the screenshot operation is detected, the screenshot content corresponding to the screenshot operation is detected, and if the screenshot content includes the session window, determining the processing manner of the image data obtained for the screenshot operation, if the processing method is privacy The protection process performs privacy protection processing on the target area of the user information in the image data, obtains the privacy image data, and displays the privacy image data, automatically protecting the privacy information of the user in the session window, and avoids enabling the special image editing tool to be performed. Manually smearing greatly reduces the efficiency of processing. The processing time is generally less than 200 milliseconds, which greatly reduces the processing time. At the same time, the privacy processing program is strictly executed, avoiding excessive or too little processing, and reducing the chance of error. The quality of the processing is improved, and the image data is directly replaced at the time of screen capture, without affecting the normal browsing of the user.

S105. Generate an operation interface for the privacy image data.

The operation interface for generating the privacy image data includes a sharing operation, a collecting operation, a deleting operation, and an editing operation, and when the user clicks more options, an operation interface for playing a slide show, printing, renaming, rotating, displaying on the map, etc. is displayed. For the user to choose. It should be noted that, for the method embodiment, for the sake of simple description, it is expressed as a series of action combinations, but those skilled in the art should understand that the embodiments of the present disclosure are not limited by the described action sequence, because In certain embodiments of the present disclosure, certain steps may be performed in other sequences or concurrently. In addition, those skilled in the art should also understand that the embodiments described in the specification belong to some exemplary embodiments, and the actions involved are not necessarily required by the embodiments of the present disclosure.

S106. Perform an image operation corresponding to the operation interface on the privacy image data when the operation interface is selected.

In some embodiments of the present disclosure, the user browses the privacy image data, and an operational interface for the privacy image data can be generated below the privacy image data.

The user can click on one of the operation interfaces as needed, and select the operation interface to perform an image operation corresponding to the selected operation interface on the privacy image data.

In a specific operation, the image operation includes at least one of the following:

Share operations, favorite operations, delete operations, edit operations.

The sharing operation may refer to calling an interface of another application to share the privacy image data to the application.

A favorite operation may refer to the collection of the private image data to a specific location of the gallery.

The delete operation may refer to deleting the privacy image data.

The editing operation may refer to additional editing processing such as rotation, trimming, filtering, blurring, and the like of the privacy image data.

Of course, the above image operations are only examples. When implementing the embodiments of the present disclosure, other image operations may be set according to actual conditions, for example, playing a slide show, printing, renaming, rotating, displaying on a map, etc., the implementation of the present disclosure This example does not limit this. In addition, other image operations may be employed by those skilled in the art in addition to the above-described image operations, and the embodiments of the present disclosure do not limit this.

As some variations on the image processing method shown in FIG. 2, the image processing method may not be completely performed in accordance with the steps and/or sequences shown in FIG. 2. In some embodiments of the present disclosure, some of the operational steps may be omitted, or the order of execution of some of the steps may be changed. For example, the image processing method may include only S101 to S103, or the image processing method need not include S105 to S106 or S100 to S100"; and, for example, the execution order of S100" may be located after S101 (instead of before).

FIG. 4 is a structural block diagram showing an image processing provided by some embodiments of the present disclosure. The image processing apparatus 4 includes a memory 41, a processor 42, and a computer program 411 stored in the memory 41 and operable on the processor 42. The processor 42 is configured to:

(1) acquiring image data including a session window;

(2) identifying, in the image data, a target area in which the user information is located in the session window;

(3) Performing a privacy protection process on the target area in the image data.

The user information includes at least one of the following:

Group avatar, group name, user name, user avatar.

In some embodiments, when configured to (2) identify in the image data the target area in which the user information is located in the session window, the processor is further configured to:

(21) dividing a target image from the image data;

(22) calibrating the boundary area to the target image;

(23) generating a candidate region based on the boundary region;

(24) Determining a target area in which the user information is located in the session window in the candidate area.

In some embodiments, when configured to (21) divide a target image from image data, the processor is further configured to:

(211) performing grayscale processing on the image data;

(212) performing binarization processing on the image data after the gradation processing;

(213) The foreground image is divided from the image data after the binarization processing as a target image.

In some embodiments, when the processor is configured to (22) calibrate a boundary region to a target image, the processor is further configured to:

(221) augmenting the target image located in the preset designated area;

(222) The boundary area is marked for the target image after the expansion processing.

In some embodiments, the processor is configured to (23) generate a candidate region based on the boundary region, the processor further configured to:

Calculate the largest rectangle of the circumscribed boundary area, and use the calculated area of the largest rectangle as the target area.

In some embodiments, the processor is configured to (24) determine, in the candidate region, a target region in which the user information is located in the session window, the processor further configured to:

(241) determining that the candidate area located in the preset designated area is the target area where the user avatar is located in the session window;

and / or,

(241') finding a candidate area in which the session frame is located in the session window in an area outside the designated area;

(242') finding a target area in which at least part of the user avatar having the same ordinate is located and a candidate area in which the session box is located;

(243') determining that the candidate area between the user avatar and the session box is in the session window when the ordinate difference between the target area where the user avatar is located and the candidate area where the session box is located is greater than a preset threshold The target area where the user name is located.

In some embodiments, the processor is configured to (3) when performing privacy protection processing on the target area in the image data, the processor is further configured to:

A masked image of a specified size is applied to the target area in the image data.

In some embodiments of the present disclosure, the processor is further configured to:

(4) generating an operation interface for the privacy image data;

(5) performing an image operation corresponding to the operation interface on the privacy image data when the operation interface is selected;

Wherein, the image operation comprises at least one of the following:

Share operations, favorite operations, delete operations, edit operations.

For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

Some embodiments of the present disclosure provide a computer readable storage medium storing a computer program, wherein the image processing method is implemented when the computer program is executed by a processor.

The various embodiments in the present specification are described in a progressive manner, and each embodiment focuses on differences from other embodiments, and the same similar parts between the various embodiments can be referred to each other.

Those skilled in the art will appreciate that embodiments of the present disclosure may be provided as a method, apparatus, or computer program product. Thus, embodiments of the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, embodiments of the present disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.

Embodiments of the present disclosure are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the present disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or FIG. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing terminal device to produce a machine such that instructions are executed by a processor of a computer or other programmable data processing terminal device Means are generated that are configured to implement the functions specified in one or more blocks of the flowchart or in a block or blocks of the flowchart.

The computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device. The instruction device implements the functions specified in one or more blocks of the flowchart or in a flow or block of the flowchart.

These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device such that a series of operational steps are performed on the computer or other programmable terminal device to produce computer-implemented processing, such that the computer or other programmable terminal device The instructions executed above provide steps that are configured to implement the functions specified in one or more of the flow or processes and/or block diagrams of a block or blocks.

Although a few embodiments of the present disclosure have been described, those skilled in the art can make additional changes and modifications to the embodiments once they are aware of the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and the modifications and

In this document, relational terms such as first and second are used merely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual. Relationship or order. Furthermore, the terms "comprises" or "comprising" or "comprising" or any other variations are intended to encompass a non-exclusive inclusion, such that a process, method, article, or terminal device that includes a plurality of elements includes not only those elements but also Other elements that are included, or include elements inherent to such a process, method, article, or terminal device. In the absence of further limitations, the elements defined by the phrase "comprising a ..." do not exclude the presence of additional equivalent elements in the process, method, article, or terminal device that comprises the element. An image processing method and an image processing apparatus provided by the present disclosure have been described in detail above. The principles and implementations of the present disclosure have been described using specific examples. The description of the above embodiments is only configured as To help understand the method of the present disclosure and its core idea; at the same time, for those skilled in the art, according to the idea of the present disclosure, there will be changes in the specific embodiments and application scopes. It should not be construed as limiting the disclosure.

Claims (18)

An image processing method comprising: Obtain image data containing a session interface; Identifying, in the image data, a target area in which the sensitive information in the session interface is located; Performing a privacy protection process on the target area in the image data to obtain privacy image data; The session interface includes a session between users. The method of claim 1 wherein the sensitive information comprises user information. The method of claim 2, the user information comprising at least one of the following: Group avatar, group name, user name, and user avatar. The method according to claim 2 or 3, wherein identifying the target area in which the user information is located in the session interface in the image data comprises: Dividing a target image from the image data; Determining a boundary area for the target image; Generating a candidate region based on the boundary region; A target area in which the user information is located in the session interface is determined in the candidate area. The method of claim 4, wherein dividing the target image from the image data comprises: Performing gradation processing on the image data; Binarizing the image data after the grayscale processing; The foreground image is divided from the image data after the binarization processing as a target image. The method of claim 4 wherein locating the boundary region for the target image comprises: Amplifying the target image located in the preset designated area; The boundary area is calibrated to the target image after the expansion process. The method of claim 4, wherein generating a candidate region based on the boundary region comprises: Calculate the largest rectangle circumscribing the boundary area as the target area. The method according to claim 4, wherein determining, in the candidate area, a target area in which the user information is located in the session interface comprises: Determining that the candidate area located in the preset designated area is the target area in which the user avatar is located in the session interface. The method according to claim 4, wherein determining a target area in which the user information is located in the session interface in the candidate area comprises: Finding a candidate area where the session frame is located in the session interface in an area located outside the designated area; Finding at least a part of the target area where the user avatar with the same ordinate is located and a candidate area where the session box is located; Determining a candidate region between the user avatar and the session box when a difference in ordinate between a target area in which the user avatar is located and a candidate area in which the session box is located is greater than a preset threshold The target area in which the user name is located in the session interface. The method according to claim 1 or 2, wherein the privacy protection process is performed on the target area in the image data, including: The target area in the image data is smeared with a mask image of a specified size. The method according to claim 1 or 2, further comprising: before acquiring the image data including the session interface: Monitor the screenshot operation; Identifying the screenshot content in the image data obtained in the screenshot operation when the screenshot operation is detected; If the screenshot content includes a session interface, the screenshot content is determined to be image data including a session interface. The method of claim 11, wherein the identifying the screenshot content in the image data obtained by the screenshot operation comprises: Matching the image data obtained by the screenshot operation with a preset session image template; In response to the image data being successfully matched with the session image template, determining that the screenshot content of the screenshot operation comprises a session interface. The method of claim 11, wherein after the screenshot content in the image data obtained by the screenshot operation comprises the session interface, the method further comprises: Determining a processing manner for the image data; In response to the processing mode being privacy protection processing, privacy protection processing is performed on the target area in which the user information is located in the image data. The method of claim 1 or 2, further comprising: Generating an operation interface to the privacy image data; Performing an image operation corresponding to the operation interface on the privacy image data when the operation interface is selected; Wherein, the image operation comprises at least one of the following: Share operations, favorite operations, delete operations, and edit operations. A terminal comprising a memory and a processor, the memory storing a computer program executable on the processor, the processor being configured to execute the computer program to cause the terminal to: Obtain image data containing a session interface; Identifying a target area in which the sensitive information in the session interface is located in the image data; Performing a privacy protection process on the target area in the image data to obtain privacy image data; The session interface includes a session between users, and the sensitive information includes user information. The terminal of claim 15, when configured to identify a target area in which user information is located in a session interface in image data, the processor is further configured to: Dividing a target image from the image data; Determining a boundary area for the target image; Generating a candidate region based on the boundary region; A target area in which the user information is located in the session interface is determined in the candidate area. The terminal of claim 15, the processor further configured to: Listening to the screenshot operation to obtain image data; Identifying whether the screenshot content in the image data includes a session interface; Determine whether to protect the image containing the session interface for privacy protection. A computer readable non-volatile storage medium storing a computer program, wherein the computer program is executed by a processor to implement the method of any one of claims 1 to 14.

Images