Digital watermark extraction method and apparatus, and electronic device and storage medium

Abstract

Provided in the embodiments of the present disclosure are a digital watermark extraction method and apparatus, and an electronic device and a storage medium. The method comprises: acquiring a screenshot image with regard to a target display interface, wherein a foreground watermark is embedded in the target display interface; on the basis of watermark parameter information, determining a target color channel where the foreground watermark is located, and on the basis of the target color channel, performing feature enhancement on a watermark feature in the screenshot image, so as to obtain a first enhanced image; and performing extraction with regard to a watermark feature in the first enhanced image, so as to obtain a watermark extraction result, wherein the watermark extraction result is used for representing watermark content of the foreground watermark. In the embodiments of the present disclosure, a target color channel where a foreground watermark is located is determined by means of watermark parameter information, and feature enhancement is then performed on a watermark feature on the basis of the target color channel, thereby achieving the effects of reducing the difficulty of watermark extraction, and improving the accuracy and efficiency of watermark extraction.

Description

Digital watermark extraction method, device, electronic device and storage medium

[0001] This application claims priority to Chinese Patent Application No. 202311288356.5 filed on October 7, 2023, and the contents of the above-mentioned Chinese patent application disclosure are hereby incorporated by reference in their entirety as a part of this application. Technical Field

[0002] The embodiments of the present disclosure relate to a digital watermark extraction method, device, electronic device, and storage medium. Background Art

[0003] The screen capture images obtained by screen photography may have poor clarity due to the influence of factors such as the shooting environment and the screen display effect, which leads to the problem of being unable to accurately obtain the digital watermark in the screen capture image.

[0004] Summary of the Invention

[0005] The embodiments of the present disclosure provide a digital watermark extraction method, device, electronic device, and storage medium.

[0006] In a first aspect, an embodiment of the present disclosure provides a digital watermark extraction method, comprising:

[0007] A screen shot of a target display interface is obtained, wherein the target display interface has a foreground watermark embedded therein; a target color channel in which the foreground watermark is located is determined based on watermark parameter information, and based on the target color channel, feature enhancement is performed on the watermark features in the screen shot to obtain a first enhanced image; the watermark features in the first enhanced image are extracted to obtain a watermark extraction result, wherein the watermark extraction result is used to characterize the watermark content of the foreground watermark.

[0008] In a second aspect, an embodiment of the present disclosure provides a digital watermark extraction device, comprising:

[0009] an acquisition module configured to acquire a screen shot image of a target display interface, wherein the target display interface has a foreground watermark embedded therein;

[0010] an enhancement module configured to determine, based on the watermark parameter information, a target color channel in which the foreground watermark is located, and perform feature enhancement on the watermark feature in the screen capture image based on the target color channel to obtain a first enhanced image, wherein the watermark parameter information is used to indicate the target color channel in which the foreground watermark is located, and the feature enhancement of the watermark feature is performed based on the target color channel of the screen capture image;

[0011] The extraction module is configured to extract watermark features from the first enhanced image to obtain a watermark extraction result, wherein the watermark extraction result is used to characterize the watermark content of the foreground watermark.

[0012] In a third aspect, an embodiment of the present disclosure provides an electronic device, including: a processor and a memory;

[0013] The memory stores computer-executable instructions;

[0014] The processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the digital watermark extraction method as described in the first aspect and various possible designs of the first aspect.

[0015] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the digital watermark extraction method described in the first aspect and various possible designs of the first aspect is implemented.

[0016] In a fifth aspect, an embodiment of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the digital watermark extraction method described in the first aspect and various possible designs of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, a brief introduction will be given below to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] FIG1 is a diagram showing an application scenario of the digital watermark extraction method provided by an embodiment of the present disclosure;

[0019] FIG2 is a flow chart of a digital watermark extraction method according to an embodiment of the present disclosure;

[0020] FIG3 is a schematic diagram of a process for generating a first enhanced image according to an embodiment of the present disclosure;

[0021] FIG4 is a flowchart of a specific implementation of step S103 in the embodiment shown in FIG2 ;

[0022] FIG5 is a schematic diagram of a second enhanced image provided by an embodiment of the present disclosure;

[0023] FIG6 is a second flow chart of the digital watermark extraction method provided by an embodiment of the present disclosure;

[0024] FIG7 is a flowchart of a specific implementation of step S205 in the embodiment shown in FIG6 ;

[0025] FIG8 is a schematic diagram of a process for generating a first enhanced image according to an embodiment of the present disclosure;

[0026] FIG9 is a flowchart of a specific implementation of step S209 in the embodiment shown in FIG6 ;

[0027] FIG10 is a schematic diagram of generating a second enhanced image according to an embodiment of the present disclosure;

[0028] FIG11 is a structural block diagram of a digital watermark extraction device provided by an embodiment of the present disclosure;

[0029] FIG12 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure; and

[0030] FIG13 is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present disclosure without making any creative efforts shall fall within the scope of protection of the present disclosure.

[0032] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0033] The following explains the application scenarios of the embodiments of the present disclosure:

[0034] FIG1 illustrates an application scenario of the digital watermark extraction method provided by an embodiment of the present disclosure. The digital watermark extraction method provided by an embodiment of the present disclosure can be applied to applications with watermark extraction capabilities, and more specifically, can be applied to application scenarios for extracting and identifying watermarks from screen capture images. The execution entity of this embodiment can be a terminal device running the aforementioned application with watermark extraction capabilities, a server providing watermark extraction and identification services, or other electronic devices that perform similar functions. Referring to FIG1 , taking a server as an example, a camera captures a display device to obtain a screen capture image. The content displayed on the display device (e.g., confidential images, documents, etc.) is embedded with a digital watermark. The digital watermark can be a texture with a specific shape and distribution pattern. By extracting and decoding the digital watermark (texture), a logo or text representing a specific meaning can be mapped. The display device (or the content displayed on the display device) is the source of the information leakage. Foreground watermarks, for example, are watermarks set in a separate watermark layer on the display interface of the display device. Foreground watermarks are widely used in various anti-leakage scenarios because they do not require access to the displayed content on the screen and their algorithms run quickly. At the same time, the foreground watermark has high transparency, so it is not noticeable to the human eye and has high security. Afterwards, after obtaining the screen shot image, the terminal device operated by the user sends the screen shot image to the server that provides watermark extraction service. Afterwards, the server processes the screen shot image through the digital watermark extraction method provided in this embodiment, extracts the digital watermark therein, and sends the content of the digital watermark (watermark extraction result) to the terminal device, completing the digital watermark extraction process. Afterwards, the terminal device or server can further identify the content of the digital watermark to obtain the source of information leakage, such as the device identification that characterizes the above-mentioned display device, thereby achieving the purpose of information tracing and the like.

[0035] For example, the screen capture images obtained by the screen photography method are affected by factors such as the shooting environment and the screen display effect, such as changes in the shooting angle, light interference during shooting, and interference from the screen moiré, resulting in poor clarity of the screen capture images. As a result, in the subsequent watermark extraction process, the digital watermark in the screen capture image cannot be accurately and completely obtained, increasing the difficulty of tracking the source of information leakage.

[0036] The embodiments of the present disclosure provide a digital watermark extraction method to solve the above problems.

[0037] Refer to Figure 2, which is a flow chart of a digital watermark extraction method provided by an embodiment of the present disclosure. The method of this embodiment can be applied to electronic devices such as terminal devices and servers. Taking the server as an example, the digital watermark extraction method includes:

[0038] Step S101: Acquire a screen shot image of a target display interface, where a foreground watermark is embedded in the target display interface.

[0039] Step S102: determining the target color channel where the foreground watermark is located according to the watermark parameter information, and performing feature enhancement on the watermark features in the screen shot image based on the target color channel to obtain a first enhanced image.

[0040] Exemplarily, referring to the application scenario diagram shown in FIG1 , a screen shot image is an image generated by shooting the screen of a display device. The screen shot image includes a target display interface displayed on the screen of the display device, and a foreground watermark is embedded in the image. More specifically, the target display interface can be a program interface, an operating system interface, etc. of an application running on the display device. A foreground watermark is a digital watermark displayed through an independent display layer. After the associated program is run, the foreground watermark will be displayed in the target display interface on the display device. The watermark content corresponding to the foreground watermark can be an identifier that represents the display device or the corresponding device account, for example, the result of encoding the device identifier and account identifier of the display device. Tracing the source of a specific device or account can be achieved by identifying the foreground watermark. For example, the implementation method of the foreground watermark can be set according to actual conditions, and the embodiments of the present disclosure do not limit the implementation method of the foreground watermark.

[0041] Furthermore, after the server obtains the screen capture image uploaded by the terminal device, it needs to first parse the screen capture image. Since the screen capture image is generated after other image capture devices (such as cameras) capture the image of the display device screen, which is equivalent to secondary capture, there is a certain difference between the screen capture image and the original image displayed on one side of the display device and embedded with the above-mentioned foreground watermark. In addition, the foreground watermark and the image content are superimposed on each other during the shooting process, and it is impossible to directly extract the accurate watermark layer from the image file. The server obtains channel data of multiple data channels by parsing the screen capture image into multiple data channels. Among them, since the image is usually composed of pixels of different colors, the above-mentioned data channels can also be called color channels. For example, the screen capture image is an RGB image, that is, an image based on the RGB color space, then the server can obtain the channel data of the R (red) channel, the channel data of the G (green) channel, and the channel data of the B (blue) channel respectively.

[0042] The server then obtains the watermark parameter information to determine the target color channel among the multiple color channels and obtains the channel data corresponding to the target color channel. The target color channel is the color channel where the foreground watermark resides. Therefore, the watermark parameter information acts as a priori information about a specific foreground watermark. Using this watermark parameter information, the server can determine the color channel where the foreground watermark resides in advance and then enhance that color channel to produce a first enhanced image, thereby enhancing the watermark features in the captured image and making them more pronounced.

[0043] FIG3 is a schematic diagram of a process for generating a first enhanced image provided by an embodiment of the present disclosure. As shown in FIG3 , exemplarily, after the server obtains the screen shot image P1, it first performs content recognition on the image content in the screen shot image P1 to obtain a corresponding content identifier, such as the content identifier Tag_1 representing the project information of project A. Afterwards, the watermark parameter information Info_1 corresponding to the content identifier Tag_1 is obtained, and the target color channel indicated by the watermark parameter information Info_1 is the R color channel based on the RGB color space. Afterwards, the server converts the screen shot image P1 to the RGB color space to obtain image P2, and then enhances the target color channel of image P2, that is, the target channel data D1 in the R color channel, to obtain the corresponding enhanced target channel data D1r. Finally, based on the target data D2, it is combined with the channel data D2 in the G color channel and the channel data D3 in the B color channel to form a first enhanced image. The specific implementation method for enhancing the watermark feature is, for example, to perform contrast enhancement on the channel data of the R color channel or perform logarithmic coordinate conversion, so that the signal in the R color channel can be amplified, thereby achieving the purpose of enhancing the watermark feature. Of course, feature enhancement can also be performed based on other implementation methods, and the specific implementation method can be set as needed, which will not be detailed here.

[0044] Step S103: extracting watermark features from the first enhanced image to obtain a watermark extraction result, which is used to characterize the watermark content of the foreground watermark.

[0045] For example, after obtaining the first enhanced image after the watermark feature enhancement, the watermark features in the first enhanced image are extracted in combination with the positioning information of the foreground watermark to obtain a watermark extraction result. The positioning information of the foreground watermark is included in the watermark parameter information and is used to describe the positioning characteristics such as the position and distribution of the foreground watermark in the image.

[0046] More specifically, the positioning information of the foreground watermark can be a mask image used to characterize the location of the foreground watermark. The specific implementation method of extracting watermark features in combination with the positioning information of the foreground watermark is not limited by the embodiments of the present disclosure. Furthermore, the watermark extraction result is used to characterize the watermark content of the foreground watermark. Specifically, it can be a set of specific character strings used to characterize the information source, such as file identification, account identification, etc. The specific expression of the watermark extraction result can be determined based on the specific encoding method of the foreground watermark, and will not be repeated here with examples.

[0047] In one possible implementation, after obtaining the first enhanced image, the first enhanced image can be further processed to further improve the significance of the watermark feature, thereby achieving the purpose of improving the accuracy of the watermark extraction result. Specifically, as shown in FIG4 , the specific implementation of step S103 includes:

[0048] Step S1031: binarizing the first enhanced image to obtain a second enhanced image, wherein the second enhanced image includes binarized pixels and is used to represent the watermark texture constituting the watermark content.

[0049] Step S1032: performing watermark feature extraction on the second enhanced image to obtain a watermark extraction result.

[0050] For example, binarization refers to the process of converting a numerical value into 0 and 1 (or Boolean value). There are various specific implementations of binarization, which can be achieved using a preset binarization function. The specific implementation of the binarization function includes, for example, comparing an input value with a preset threshold value, where a value greater than the threshold value is set to 1, and a value less than or equal to the threshold value is set to 0, or vice versa. The specific implementation of the binarization function can be configured as needed, and examples are provided here one by one.

[0051] In the steps of this embodiment, after obtaining the first enhanced image, the first enhanced image is binarized to obtain an image consisting only of binary pixels 0 and 1, namely the second enhanced image. Among them, the 0 or 1 in the second enhanced image is used to represent the watermark texture concave part and the watermark texture protrusion part, and the watermark content is formed by the above-mentioned watermark texture protrusion. Figure 5 is a schematic diagram of a second enhanced image provided by the embodiment of the present disclosure. As shown in Figure 5, exemplarily, the second enhanced image is an image with an image size of N*M, and each pixel in the second enhanced image is a binary pixel, that is, the pixel value of each pixel is 0 or 1. Among them, exemplarily, 1 represents the watermark texture protrusion and 0 represents the watermark texture concave part, then the watermark feature is represented by the set of all pixels with a pixel value of 1 in the second enhanced image. Afterwards, watermark feature extraction is performed on the second enhanced image to obtain a watermark extraction result, such as a texture, character, or text composed of a binary pixel value of 1. Through this watermark extraction result, the information source corresponding to the foreground watermark can be traced.

[0052] In the disclosed embodiment, a screen shot of a target display interface is obtained, wherein the target display interface has a foreground watermark embedded therein; the target color channel where the foreground watermark is located is determined based on the watermark parameter information, and based on the target color channel, the watermark features in the screen shot are enhanced to obtain a first enhanced image; the watermark features in the first enhanced image are extracted to obtain a watermark extraction result, which is used to characterize the watermark content of the foreground watermark. By using the watermark parameter information as prior knowledge to determine the target color channel where the foreground watermark is located, and then enhancing the watermark features based on the target color channel, a first enhanced image with more significant watermark features is obtained, and then watermark extraction is performed based on the first enhanced image to obtain a watermark extraction result, thereby achieving the effect of reducing the difficulty of watermark extraction and improving the accuracy and efficiency of watermark extraction.

[0053] Referring to FIG6 , FIG6 is a second flow chart of the digital watermark extraction method provided by the embodiment of the present disclosure. Based on the embodiment shown in FIG2 , this embodiment further refines step S102 and step S103. The digital watermark extraction method includes:

[0054] Step S201: Acquire a screen shot image of a target display interface, where a foreground watermark is embedded in the target display interface.

[0055] Step S202: performing color space conversion on the screen capture image to generate an adapted screen capture image based on the second color space.

[0056] In one possible implementation, the screen capture image obtained by the server corresponds to a color space itself. In this case, it can be subjected to color space conversion as needed, thereby improving the effect of feature enhancement in subsequent steps. Specifically, for example, the screen capture image obtained by the server is based on the HSV (Hue, Saturation, Value) color space, that is, the content of the color image is expressed in hue, saturation, and brightness. In this case, the screen capture image can be first subjected to color space conversion to convert the screen capture image into a color space that is more suitable for extracting watermark features, that is, the second color space. The image generated by the color space conversion is the adapted screen capture image. In one possible implementation, the second color space is the RGB color space.

[0057] Of course, it can be understood that the above-mentioned step of converting the color space of the screen capture image is optional. In other possible embodiments, the above-mentioned step 202 can be omitted and the subsequent steps can be performed directly using the screen capture image. The subsequent processing process is the same and will not be repeated here.

[0058] Step S203: extracting channel data of the target color channel of the adapted screen shot image according to the watermark parameter information to obtain target channel data.

[0059] Step S204: converting the adapted screen shot image into a first color space having a brightness channel, and acquiring brightness channel data corresponding to the brightness channel.

[0060] Exemplarily, watermark parameter information corresponding to the captured image is then obtained, indicating the target color channel where the foreground watermark is located. Channel data is extracted from the captured image or adapted captured image using the watermark parameter information to obtain target channel data corresponding to the target color channel. The specific implementation of the target channel data extraction process described above has been detailed in the embodiment shown in FIG2 and will not be repeated here.

[0061] On the other hand, the obtained adapted screen shot image is subjected to color space conversion and converted into a first color space having a brightness channel, such as a YUV color space. Similar to the RGB color space, the YUV color space is also a color encoding method that describes the image content of a color image by brightness (luma) and chrominance (Chrominance). The RGB color space and the YUV color space can be converted to each other. In the steps of this embodiment, the adapted screen shot image is subjected to color space conversion to obtain a first color space, and the data of the brightness channel of the first color space, such as the channel data corresponding to the brightness (luma) channel of the YUV space, is used to perform feature enhancement. Since brightness can characterize the outline of object elements in the image to a certain extent, selecting the brightness channel for subsequent residual operation can improve the clarity of the watermark outline in the image.

[0062] In a possible implementation, the first color space is a YUV color space, the second color space is an RGB color space, and the target color channel includes any one of an R channel, a G channel, and a B channel.

[0063] Step S205: Obtain a first enhanced image through the residual between the target channel data and the brightness channel data.

[0064] For example, residual calculation is performed using the target channel data and luminance channel data obtained in the above steps. Both the target channel data and the luminance channel data are generated based on the screen capture image and have the same number of data points. Therefore, point-by-point subtraction can be performed to obtain a residual map with the same number of data points, i.e., the first enhanced image. After performing residual calculation based on the luminance channel data, the purpose of eliminating image noise and interference and enhancing the outline of the foreground watermark can be achieved, thereby improving the effectiveness of subsequent watermark feature extraction.

[0065] For example, as shown in FIG7 , the specific implementation of step S205 includes:

[0066] Step S2051: performing a residual operation on the target channel data and the brightness channel data to obtain a first residual map.

[0067] Step S2052: normalize the first residual map to obtain a normalized residual map.

[0068] Step S2053: performing histogram equalization on the normalized residual image to obtain a first enhanced image.

[0069] Exemplarily, referring to the previous introduction, FIG8 is a schematic diagram of a process for generating a first enhanced image provided by an embodiment of the present disclosure. The above steps will be further introduced below in conjunction with FIG8. As shown in FIG8, after the server obtains the screen capture image P1, it performs color space conversion on the screen capture image P1 to generate an adapted screen capture image P2. Afterwards, based on the adapted screen capture image P2, the watermark parameter information is used to extract the channel data of the target color channel of the adapted screen capture image P2 to obtain the target channel data P3, and the color space of the adapted screen capture image P2 is converted to generate a YUV image. The YUV image pair is subjected to data extraction of the brightness channel to obtain the brightness channel data P4. Finally, a point-by-point residual operation is performed on the target channel data P3 and the brightness channel data P4 to obtain the first residual map P5.

[0070] Afterwards, the first residual map is normalized, i.e., each value in the first residual map is normalized so that it is within a fixed numerical range, such as between 0 and 1, or between 0 and 255, thereby obtaining a normalized residual map P6. The embodiments of the present disclosure do not limit the implementation method of the normalization processing of the dataset.

[0071] After that, the normalized residual image is histogram equalized to obtain a first enhanced image. Among them, histogram equalization, also known as histogram equalization, is a method of adjusting the contrast using the image histogram in the field of image processing. Through this method, the brightness can be better distributed on the histogram, while reducing the impact of uneven lighting in the screen shot. This can be used to enhance the local contrast without affecting the overall contrast. Histogram equalization achieves this function by effectively expanding the commonly used brightness. In the steps of this embodiment, the purpose of enhancing the contrast of the image is achieved by performing histogram equalization on the normalized normalized residual image, thereby increasing the details of the watermark features in the normalized residual image and strengthening the watermark features.

[0072] Step S206: Obtain a target filter kernel size according to image content features of the screen shot image.

[0073] Step S207: Based on the target filter kernel size, perform mean filtering on the watermark features in the first enhanced image to obtain a filter feature map.

[0074] Furthermore, after obtaining the first enhanced image, the first enhanced image can be further mean filtered to reduce image noise in the first enhanced image, reduce noise introduced during the capture process, and improve the clarity of the watermark features. Specifically, first, a corresponding target filter kernel size is obtained based on the image content features of the captured image. The image content features of the captured image can be achieved by performing image feature extraction and content recognition on the captured image. This step can be the same pre-step as obtaining watermark parameter information, namely, obtaining watermark parameter information and the corresponding target filter kernel size by identifying the image content features of the captured image. Then, based on the target filter kernel size, the watermark features in the first enhanced image are mean filtered to obtain a filter feature map, which represents non-watermark features in the image. The filtering result of the mean filter is affected by the target filter kernel size. The larger the target filter kernel size, the more surrounding pixel information is referenced, and the corresponding filtering effect is stronger. Conversely, the smaller the target filter kernel size, the less surrounding pixel information is referenced, and the corresponding filtering effect is weaker. By setting the target filter kernel size that matches the image content characteristics, the filtering strength is controlled, so that the filtering effect of the generated filtering feature map is better and the significance of the watermark feature is improved.

[0075] Step S208: Obtain a second residual map according to the residual of the filtered feature map and the first enhanced image.

[0076] Step S209: obtaining a second enhanced image according to the second residual image, wherein the second enhanced image includes binary pixels and is used to represent the watermark texture constituting the watermark content.

[0077] For example, after generating the filter feature map, the residual between the filter feature map and the first enhanced image is further calculated to obtain a second residual map. By calculating the residual between the filter feature map and the first enhanced image, the non-watermark features represented in the filter feature map can be filtered out, thereby enhancing the watermark features in the first enhanced image. Further, as shown in FIG9 , the specific implementation of step S209 includes:

[0078] Step S2091: Obtain a residual threshold value according to the image content features of the screen shot image.

[0079] Step S2092: Obtain the residual value corresponding to each pixel in the second residual image, and compare it with the residual threshold to obtain a second enhanced image.

[0080] For example, for the second residual map, similar to the previous step, the image content features of the screen shot image are obtained. The specific implementation method has been introduced before and will not be repeated here. For another example, the image content features obtain the corresponding residual threshold, so that the size of the residual threshold matches the image content. The image content features can characterize factors such as the distance between the target display interface in the image and the shooting point, and the brightness of the light. This avoids the problem of unclear watermark features due to unreasonable residual thresholds, thereby further improving the significance of the watermark features, reducing the difficulty of subsequent identification of foreground watermarks based on watermark features, and improving the recognition rate.

[0081] For example, FIG10 is a schematic diagram of generating a second enhanced image provided by an embodiment of the present disclosure. The above steps are described below in conjunction with FIG10. For example, after obtaining the first enhanced image P1, the first enhanced image is filtered according to the image content features of the screen capture image, that is, the target filter kernel size is determined based on the image content features of the screen capture image, and filtering is performed based on the target filter kernel size. A filter feature map is then obtained. Thereafter, a residual operation is performed using the filter feature map and the first enhanced image to obtain a second residual map. The second residual map is then binarized to generate a second enhanced image.

[0082] Step S210: performing watermark feature extraction on the second enhanced image to obtain a watermark extraction result.

[0083] In this embodiment, the implementation of step S201 and step S210 is the same as the implementation of step S101 and step S103 in the embodiment shown in FIG. 2 of the present disclosure, and will not be described in detail here.

[0084] Corresponding to the digital watermark extraction method of the above embodiment, FIG11 is a structural block diagram of the digital watermark extraction device provided by the embodiment of the present disclosure. For the sake of convenience, only the parts related to the embodiment of the present disclosure are shown. Referring to FIG11, the digital watermark extraction device 3 includes:

[0085] An acquisition module 31 is configured to acquire a screen shot image of a target display interface, wherein the target display interface has a foreground watermark embedded therein;

[0086] The enhancement module 32 is configured to determine the target color channel where the foreground watermark is located based on the watermark parameter information, and enhance the watermark features in the screen shot image based on the target color channel to obtain a first enhanced image;

[0087] The extraction module 33 is configured to extract the watermark features in the first enhanced image to obtain a watermark extraction result, which is used to represent the watermark content of the foreground watermark.

[0088] In one embodiment of the present disclosure, the enhancement module 32 is specifically configured to: extract channel data of the target color channel of the screen capture image according to the watermark parameter information to obtain target channel data; convert the screen capture image to a first color space having a brightness channel, and obtain brightness channel data corresponding to the brightness channel; and obtain a first enhanced image through the residual between the target channel data and the brightness channel data.

[0089] In one embodiment of the present disclosure, when the enhancement module 32 obtains the first enhanced image through the residual between the target channel data and the luminance channel data, it is specifically configured to: perform residual operation on the target channel data and the luminance channel data to obtain a first residual map; normalize the first residual map to obtain a normalized residual map; and perform histogram equalization on the normalized residual map to obtain the first enhanced image.

[0090] In one embodiment of the present disclosure, the enhancement module 32 is further configured to: perform color space conversion on the screen capture image to generate an adapted screen capture image based on the second color space; when the enhancement module 32 extracts channel data on the target color channel of the screen capture image according to the watermark parameter information to obtain the target channel data, the enhancement module 32 is specifically configured to: perform channel data extraction on the adapted screen capture image based on the second color space according to the target color channel indicated by the watermark parameter information to obtain the target channel data.

[0091] In one embodiment of the present disclosure, the first color space is a YUV color space, the second color space is an RGB color space, and the target color channel includes any one of an R channel, a G channel, and a B channel.

[0092] In one embodiment of the present disclosure, the extraction module 33 is specifically configured to: binarize the first enhanced image to obtain a second enhanced image, wherein the second enhanced image includes binarized pixels, and the second enhanced image is used to represent the watermark texture constituting the watermark content; perform watermark feature extraction on the second enhanced image to obtain a watermark extraction result.

[0093] In one embodiment of the present disclosure, when the extraction module 33 performs binarization on the first enhanced image to obtain the second enhanced image, it is specifically configured to: obtain the target filter kernel size based on the image content characteristics of the screen shot image; based on the target filter kernel size, perform mean filtering on the watermark features in the first enhanced image to obtain a filter feature map; obtain a second residual map based on the residual between the filter feature map and the first enhanced image; and obtain the second enhanced image based on the second residual map.

[0094] In one embodiment of the present disclosure, when the extraction module 33 obtains the second enhanced image based on the second residual map, it is specifically configured to: obtain a residual threshold based on the image content characteristics of the screen shot image; obtain the residual value corresponding to each pixel point in the second residual map, and compare it with the residual threshold to obtain the second enhanced image.

[0095] The acquisition module 31, enhancement module 32 and extraction module 33 are connected in sequence. The digital watermark extraction device 3 provided in this embodiment can implement the technical solution of the above method embodiment, and its implementation principle and technical effect are similar, which will not be repeated in this embodiment.

[0096] FIG12 is a schematic structural diagram of an electronic device provided by an embodiment of the present disclosure. As shown in FIG12 , the electronic device 4 includes:

[0097] A processor 41, and a memory 42 communicatively connected to the processor 41;

[0098] Memory 42 stores computer-executable instructions;

[0099] The processor 41 executes the computer-executable instructions stored in the memory 42 to implement the digital watermark extraction method in the embodiments shown in FIG. 2 to FIG. 10 .

[0100] Optionally, the processor 41 and the memory 42 are connected via a bus 43 .

[0101] The relevant explanations can be understood by referring to the relevant descriptions and effects corresponding to the steps in the embodiments corresponding to Figures 2 to 10, and no further details will be given here.

[0102] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the digital watermark extraction method provided in any one of the embodiments corresponding to FIG. 2 to FIG. 10 of the present disclosure.

[0103] In order to implement the above embodiment, the embodiment of the present disclosure further provides an electronic device.

[0104] Referring to FIG13 , a schematic diagram of the structure of an electronic device 900 suitable for implementing an embodiment of the present disclosure is shown. The electronic device 900 may be a terminal device or a server. The terminal device may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, personal digital assistants (PDAs), tablet computers (Portable Android Devices, PADs), portable multimedia players (PMPs), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in FIG13 is merely an example and should not limit the functionality and scope of use of the embodiments of the present disclosure.

[0105] As shown in FIG13 , the electronic device 900 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 901, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 902 or a program loaded from a storage device 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the electronic device 900 are also stored in the RAM 903. The processing device 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0106] Typically, the following devices can be connected to the I / O interface 905: an input device 906 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 907 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 908 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 909. The communication device 909 can allow the electronic device 900 to communicate with other devices wirelessly or by wire to exchange data. Although FIG13 shows an electronic device 900 with various devices, it should be understood that it is not required to implement or have all of the devices shown. More or fewer devices may be implemented or have alternatively.

[0107] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication device 909, or installed from the storage device 908, or installed from the ROM 902. When the computer program is executed by the processing device 901, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0108] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0109] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0110] The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device executes the method shown in the above embodiment.

[0111] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0113] The units involved in the embodiments described in this disclosure may be implemented in software or hardware. In some cases, the name of a unit does not limit the unit itself. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses."

[0114] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0115] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] In a first aspect, according to one or more embodiments of the present disclosure, a digital watermark extraction method is provided, comprising:

[0117] A screen shot of a target display interface is obtained, wherein the target display interface has a foreground watermark embedded therein; based on the watermark parameter information, a target color channel in which the foreground watermark is located is determined, and based on the target color channel, the watermark features in the screen shot are enhanced to obtain a first enhanced image; the watermark features in the first enhanced image are extracted to obtain a watermark extraction result, which is used to characterize the watermark content of the foreground watermark.

[0118] According to one or more embodiments of the present disclosure, based on watermark parameter information, the target color channel where the foreground watermark is located is determined, and based on the target color channel, the watermark features in the screen-captured image are feature enhanced to obtain a first enhanced image, including: extracting channel data of the target color channel of the screen-captured image based on the watermark parameter information to obtain target channel data; converting the screen-captured image to a first color space having a brightness channel, and obtaining brightness channel data corresponding to the brightness channel; and obtaining the first enhanced image through the residual between the target channel data and the brightness channel data.

[0119] According to one or more embodiments of the present disclosure, a first enhanced image is obtained by using the residual between the target channel data and the luminance channel data, including: performing a residual operation on the target channel data and the luminance channel data to obtain a first residual map; normalizing the first residual map to obtain a normalized residual map; and performing histogram equalization on the normalized residual map to obtain the first enhanced image.

[0120] According to one or more embodiments of the present disclosure, it also includes: performing color space conversion on the screen capture image to generate an adapted screen capture image based on the second color space; extracting channel data on the target color channel of the screen capture image according to the watermark parameter information to obtain target channel data, including: extracting channel data on the adapted screen capture image based on the second color space according to the target color channel indicated by the watermark parameter information to obtain target channel data.

[0121] According to one or more embodiments of the present disclosure, the first color space is a YUV color space, the second color space is an RGB color space, and the target color channel includes any one of an R channel, a G channel, and a B channel.

[0122] According to one or more embodiments of the present disclosure, watermark features in a first enhanced image are extracted to obtain a watermark extraction result, including: binarizing the first enhanced image to obtain a second enhanced image, wherein the second enhanced image includes binarized pixels, and the second enhanced image is used to represent the watermark texture constituting the watermark content; and extracting watermark features from the second enhanced image to obtain a watermark extraction result.

[0123] According to one or more embodiments of the present disclosure, a first enhanced image is binarized to obtain a second enhanced image, including: obtaining a target filter kernel size based on image content features of the screen shot image; performing mean filtering on watermark features in the first enhanced image based on the target filter kernel size to obtain a filter feature map; obtaining a second residual map based on a residual between the filter feature map and the first enhanced image; and obtaining a second enhanced image based on the second residual map.

[0124] According to one or more embodiments of the present disclosure, a second enhanced image is obtained based on the second residual map, including: obtaining a residual threshold based on image content features of the screen shot image; obtaining the residual value corresponding to each pixel point in the second residual map, and comparing it with the residual threshold to obtain the second enhanced image.

[0125] In a second aspect, according to one or more embodiments of the present disclosure, a digital watermark extraction device is provided, comprising:

[0126] an acquisition module configured to acquire a screen shot image of a target display interface, wherein the target display interface has a foreground watermark embedded therein;

[0127] an enhancement module configured to determine a target color channel where the foreground watermark is located based on the watermark parameter information, and enhance the watermark features in the screen shot image based on the target color channel to obtain a first enhanced image;

[0128] The extraction module is configured to extract the watermark features in the first enhanced image to obtain a watermark extraction result, and the watermark extraction result is used to characterize the watermark content of the foreground watermark.

[0129] According to one or more embodiments of the present disclosure, the enhancement module is specifically configured to: extract channel data of the target color channel of the screen capture image according to the watermark parameter information to obtain target channel data; convert the screen capture image to a first color space having a brightness channel, and obtain brightness channel data corresponding to the brightness channel; and obtain a first enhanced image through the residual between the target channel data and the brightness channel data.

[0130] According to one or more embodiments of the present disclosure, when the enhancement module obtains the first enhanced image through the residual between the target channel data and the luminance channel data, it is specifically configured to: perform a residual operation on the target channel data and the luminance channel data to obtain a first residual map; normalize the first residual map to obtain a normalized residual map; and perform histogram equalization on the normalized residual map to obtain the first enhanced image.

[0131] According to one or more embodiments of the present disclosure, the enhancement module is further configured to: perform color space conversion on the screen capture image to generate an adapted screen capture image based on the second color space; when the enhancement module 32 extracts channel data on the target color channel of the screen capture image according to the watermark parameter information to obtain the target channel data, the enhancement module is specifically configured to: perform channel data extraction on the adapted screen capture image based on the second color space according to the target color channel indicated by the watermark parameter information to obtain the target channel data.

[0132] According to one or more embodiments of the present disclosure, the first color space is a YUV color space, the second color space is an RGB color space, and the target color channel includes any one of an R channel, a G channel, and a B channel.

[0133] According to one or more embodiments of the present disclosure, the extraction module is specifically configured to: binarize the first enhanced image to obtain a second enhanced image, wherein the second enhanced image includes binarized pixels, and the second enhanced image is used to represent the watermark texture constituting the watermark content; perform watermark feature extraction on the second enhanced image to obtain a watermark extraction result.

[0134] According to one or more embodiments of the present disclosure, when the extraction module binarizes the first enhanced image to obtain the second enhanced image, the extraction module is specifically configured to: obtain a target filter kernel size based on the image content features of the screen shot image; perform mean filtering on the watermark features in the first enhanced image based on the target filter kernel size to obtain a filter feature map; obtain a second residual map based on the residual between the filter feature map and the first enhanced image; and obtain a second enhanced image based on the second residual map.

[0135] According to one or more embodiments of the present disclosure, when the extraction module obtains the second enhanced image based on the second residual map, it is specifically configured to: obtain a residual threshold based on the image content characteristics of the screen shot image; obtain the residual value corresponding to each pixel point in the second residual map, and compare it with the residual threshold to obtain the second enhanced image.

[0136] In a third aspect, according to one or more embodiments of the present disclosure, there is provided an electronic device, comprising: at least one processor and a memory;

[0137] Memory stores computer-executable instructions;

[0138] At least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the digital watermark extraction method of the first aspect and various possible designs of the first aspect.

[0139] In a fourth aspect, according to one or more embodiments of the present disclosure, a computer-readable storage medium is provided, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the digital watermark extraction method as described in the first aspect and various possible designs of the first aspect are implemented.

[0140] In a fifth aspect, according to one or more embodiments of the present disclosure, a computer program product is provided, including a computer program, which, when executed by a processor, implements the digital watermark extraction method of the first aspect and various possible designs of the first aspect.

[0141] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0142] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0143] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A digital watermark extraction method, comprising: Acquire a screen shot image of a target display interface, wherein the target display interface has a foreground watermark embedded therein; Determine, according to the watermark parameter information, a target color channel where the foreground watermark is located, and enhance the watermark feature in the screen shot image based on the target color channel to obtain a first enhanced image; The watermark features in the first enhanced image are extracted to obtain a watermark extraction result, wherein the watermark extraction result is used to characterize the watermark content of the foreground watermark.

2. The method according to claim 1, wherein: The step of determining the target color channel where the foreground watermark is located according to the watermark parameter information, and enhancing the watermark feature in the screen shot image based on the target color channel to obtain a first enhanced image includes: Extracting channel data of a target color channel of the screen shot image according to the watermark parameter information to obtain target channel data; Convert the screen shot image into a first color space having a brightness channel, and obtain brightness channel data corresponding to the brightness channel; The first enhanced image is obtained through the residual between the target channel data and the brightness channel data.

3. The method according to claim 2, wherein: The step of obtaining the first enhanced image by using the residual between the target channel data and the brightness channel data includes: Performing a residual operation on the target channel data and the brightness channel data to obtain a first residual map; Normalizing the first residual map to obtain a normalized residual map; Performing histogram equalization on the normalized residual image to obtain the first enhanced image.

4. The method according to claim 2, further comprising: Performing color space conversion on the screen shot image to generate an adapted screen shot image based on a second color space; The step of extracting channel data of a target color channel of the screen shot image according to the watermark parameter information to obtain target channel data includes: According to the target color channel indicated by the watermark parameter information, channel data is extracted from the adapted screen shot image based on the second color space to obtain target channel data.

5. The method according to claim 4, wherein: The first color space is a YUV color space, the second color space is an RGB color space, and the target color channel includes any one of an R channel, a G channel, and a B channel.

6. The method according to claim 1, wherein: The step of extracting the watermark feature from the first enhanced image to obtain a watermark extraction result includes: Binarizing the first enhanced image to obtain a second enhanced image, wherein the second enhanced image includes binary pixels, and the second enhanced image is used to represent a watermark texture constituting the watermark content; Perform watermark feature extraction on the second enhanced image to obtain the watermark extraction result.

7. The method according to claim 6, wherein: The binarization of the first enhanced image to obtain a second enhanced image includes: Obtaining a target filter kernel size according to image content features of the screen shot image; Based on the target filter kernel size, performing mean filtering on the watermark features in the first enhanced image to obtain a filter feature map; Obtaining a second residual map according to a residual of the filtering feature map and the first enhanced image; The second enhanced image is obtained according to the second residual image.

8. The method according to claim 7, wherein: The step of obtaining the second enhanced image according to the second residual image includes: Obtaining a residual threshold value according to image content features of the screen shot image; The residual value corresponding to each pixel in the second residual image is obtained, and compared with the residual threshold to obtain the second enhanced image.

9. A digital watermark extraction device, comprising: An acquisition module is configured to acquire a screen shot image of a target display interface, wherein the target display interface is embedded with a foreground watermark; an enhancement module, configured to determine, according to the watermark parameter information, a target color channel where the foreground watermark is located, and to perform feature enhancement on the watermark feature in the screen shot image based on the target color channel to obtain a first enhanced image, wherein the watermark parameter information is used to indicate the target color channel where the foreground watermark is located, and the feature enhancement of the watermark feature is achieved based on the target color channel of the screen shot image; and The extraction module is configured to extract the watermark features in the first enhanced image to obtain a watermark extraction result, wherein the watermark extraction result is used to characterize the watermark content of the foreground watermark.

10. An electronic device, comprising: Processor and memory; Wherein, the memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor executes the digital watermark extraction method according to any one of claims 1 to 8.

11. A computer-readable storage medium, wherein: The computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, the digital watermark extraction method according to any one of claims 1 to 8 is implemented.

12. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the digital watermark extraction method according to any one of claims 1 to 8 is implemented.

Images