CN111476090A

CN111476090A - Watermark identification method and device

Info

Publication number: CN111476090A
Application number: CN202010145315.0A
Authority: CN
Inventors: 宋烈金; 赵秀慧; 黄雪原
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2020-03-04
Filing date: 2020-03-04
Publication date: 2020-07-31
Anticipated expiration: 2040-03-04
Also published as: CN111476090B

Abstract

The application discloses a watermark identification method and a watermark identification device, which relate to the technical field of image identification in the technical field of computers, wherein the method comprises the following steps: acquiring function information of a target image, and identifying a content area in the target image; matching the function information with the content in the content area, and determining a function sub-area where the function information is located; determining candidate sub-regions outside the functional sub-regions in the content region; watermark detection is performed in the candidate sub-regions. Therefore, the accuracy and efficiency of watermark identification are improved, and the technical problem of difficulty in identification caused by watermark diversification in the prior art is solved.

Description

Watermark identification method and device

Technical Field

The present application relates to the field of image recognition technology in computer technology, and in particular, to a watermark recognition method and apparatus.

Background

Generally, intelligent authentication refers to that an individual or an organization submits a qualification certificate image representing the individual or the organization, and an authentication platform judges whether the authentication requirement passes or not, and mainly comprises two aspects of qualification authentication and qualification anti-cheating, wherein the qualification anti-cheating is to verify whether counterfeiting or falsifying exists or not. At present, the validity of a certificate of qualification is mainly detected according to the detection of a watermark in the certificate of qualification.

In the related art, the main solution of watermark detection is manual review, and the existing problem is that the authentication waiting time is long, and generally several hours or even several days are needed. The manual review not only needs to consume huge labor cost, but also causes long authentication time to influence the user experience.

Disclosure of Invention

A first object of the present application is to propose a watermark identification method.

A second object of the present application is to provide a watermark identification apparatus.

A third object of the present application is to provide an electronic device.

A fourth object of the present application is to propose a non-transitory computer readable storage medium storing computer instructions.

In order to achieve the above object, an embodiment of a first aspect of the present application provides a watermark identification method, including: acquiring function information of the target image, and identifying a content area in the target image; matching the function information with the content in the content area, and determining a function sub-area where the function information is located; determining candidate sub-regions in the content region outside of the functional sub-regions; and carrying out watermark detection in the candidate subarea.

In order to achieve the above object, a second aspect of the present application provides a watermark identification apparatus, including: the acquisition module is used for acquiring the functional information of the target image; the identification module is used for identifying a content area in the target image; the first determining module is used for matching the function information with the content in the content area and determining a function sub-area where the function information is located; a second determining module, configured to determine a candidate sub-region in the content region other than the functional sub-region; a detection module, configured to perform watermark detection in the candidate sub-region.

To achieve the above object, a third aspect of the present application provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the watermark identification method described in the above embodiments.

To achieve the above object, a fourth aspect of the present application provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the watermark identification method described in the above embodiment.

One embodiment in the above application has the following advantages or benefits:

the method comprises the steps of obtaining function information of a target image, identifying a content area in the target image, further matching the function information with content in the content area, determining a function sub-area where the function information is located, determining a candidate sub-area outside the function sub-area in the content area, and finally carrying out watermark detection in the candidate sub-area. Therefore, the candidate subareas where the watermarks are possibly located are screened out firstly, watermark detection is carried out in the candidate subareas, the accuracy and efficiency of watermark identification are improved, and the technical problem of identification difficulty caused by watermark diversification in the prior art is solved.

Other effects of the above-described alternative will be described below with reference to specific embodiments.

Drawings

The drawings are included to provide a better understanding of the present solution and are not intended to limit the present application. Wherein:

fig. 1 is a flowchart of a watermark identification method according to a first embodiment of the present application;

FIG. 2 is a schematic illustration of a target image according to a second embodiment of the present application;

FIG. 3 is a diagram illustrating a functional sub-region determination scenario according to a third embodiment of the present application;

fig. 4 is a schematic view of a scene of a watermark identification method according to a fourth embodiment of the present application;

fig. 5 is a schematic diagram of a watermark identification application scenario according to a fifth embodiment of the present application;

fig. 6 is a schematic structural diagram of a watermark identification apparatus according to a sixth embodiment of the present application; and

fig. 7 is a block diagram of an electronic device for implementing a watermark identification method according to an embodiment of the present application.

Detailed Description

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

The watermark identification method and apparatus of the embodiments of the present application are described below with reference to the drawings.

The method for identifying the watermark comprises the steps of identifying a watermark, and identifying the watermark according to the watermark identification.

In the application, it is considered that the watermark does not have a fixed format and a fixed pattern, and is generally a watermark form that is randomly printed or handwritten by an individual or an organization in order to limit a certain authorization, and the flexible watermark mode leads to complex and various qualified watermarks.

If the watermark is detected simply by learning the watermark characteristics, on one hand, a large number of standard samples need to be trained, the workload is huge, and on the other hand, the method is only applied to the condition that the image and the watermark have obvious distinguishing characteristics, such as: the image utilizes the watermark to indicate the source information, the watermark has great difference with the image, and a model is easy to construct for distinguishing. In practical application, the watermark may be a machine-printed character with any font format, or may be a handwritten character in one or more lines, and uncertainty of various direction inclinations also exists, so that the difficulty of detecting the watermark is high. According to the watermark identification method, the areas without watermarks are eliminated firstly, watermark detection is carried out in the rest areas, workload and interference of watermark identification are reduced, and accuracy and efficiency of watermark identification are improved.

Specifically, as shown in fig. 1, a flow chart of a watermark identification method according to an embodiment of the present application is shown in fig. 1, where the method includes:

step 101, acquiring function information of a target image, and identifying a content area in the target image.

The target image may be a qualification image such as a degree certificate, a teacher qualification certificate, and the like, and the functional information of the target image refers to original information fixedly existing in the corresponding target image, such as title information, seal information, content information, corresponding layout information, and the like.

In different application scenarios, the manner of obtaining the function information of the target images is different, and as a possible example, since the layout structure information of each type of target images is different, for example, as shown in fig. 2, in the access certification, the layout structure information is specified to be divided into an area a as a title, an area B as a content, an area C as company information, and the like, where the layout structure information may include a position corresponding to the corresponding layout area, a function information type, and the like.

Furthermore, a preset database can be queried, in which the corresponding relationship between the image type information and the layout structure information is stored, the layout structure information corresponding to the image type information is obtained by querying the preset database, the corresponding function information can be determined according to the layout structure information, for example, the title content corresponding to the title area is determined according to the layout structure information, the keyword content and the like are determined according to the layout structure information, the image feature corresponding to the two-dimensional code is determined according to the layout structure information, and the image feature and the area size and the like corresponding to the national emblem are determined according to the layout structure information.

In some application scenarios, the webpage uploaded by the target image may perform operations such as adding a two-dimensional code to the target image as needed, so that a preset database may be queried according to the webpage identifier to obtain functional information corresponding to the webpage identifier, where the functional information may be two-dimensional code information or barcode information, and the information added to the webpage and displayed in the target image is obtained as the functional information.

In the embodiment of the present application, it is further required to identify a content region in the target image, and extract a region containing content first, so as to further screen out sub-regions possibly containing watermarks in the content region, where the content region may be understood as all non-blank regions containing content in the non-background region in the image. In this embodiment, the content in the target image may be identified, and the content area may be determined according to the position where the beauty is located.

It should be noted that, in different application scenarios, the manner of identifying the content area in the target image is different, and the following example is given:

example one:

in this example, the text region in the target image is identified according to a text recognition algorithm, wherein the text recognition algorithm may be an algorithm that can clearly detect text, such as an OCR recognition algorithm, and further, considering that the text recognition algorithm may not recognize every word in the target image, and it is more difficult that a watermark may have non-text, and further, the text watermark has different gray levels and arbitrary angles, and it is difficult for OCR recognition, therefore, as a supplement, the candidate content region in the target image is detected according to a region detection algorithm, for example, the region detection algorithm is a mser algorithm, and the mser algorithm detects speckles in the image based on the concept of watershed, and in processing the target image into a gray level image, the mser algorithm performs binarization processing on the target image that has been processed into gray levels, and the threshold value of this processing is increased from 0 to 255, the increment of the threshold is similar to the process of making a water level rise on a piece of land, and as the water level rises, land areas with uneven height are continuously submerged, namely a watershed algorithm, and the difference of the height is the difference of gray values in images. On the other hand, on an image containing characters, some regions (such as characters) are consistent due to color (gray value), and therefore cannot be covered in a period of time when a horizontal plane (threshold) continuously increases, and are not submerged until the threshold increases to the gray value of the characters, and these regions are called stable regions, and can also be understood as candidate content regions in the application, and the candidate content regions can detect character regions and regions containing other contents in a target image, so that the situation of missing of OCR regions can be compensated, and content regions can be generated according to the combination of the character regions and the candidate content regions.

Certainly, in practical applications, the target image may be obtained by photographing by a user, and due to dual influences of a photographing angle of the user and a placing angle of a qualification certificate corresponding to the target image, the target image generally submitted will have a certain inclination, and although the current OCR recognition technology can tolerate a certain inclination, the recognition effect will be affected, so that firstly, the qualification image needs to be subjected to inclination correction, for example, an outer edge of the image can be recognized, the inclination of the image is determined according to a contour of the outer edge, and then, the image is corrected according to the inclination of the image.

In an actual implementation process, the effect of watermark detection is not that the larger the image size is, the higher the recognition effect is, and the image size may affect the detection time, so that the target image may be reduced to a certain extent, and the detection speed is increased.

And 102, matching the function information with the content in the content area, and determining a function sub-area where the function information is located.

It is understood that the function information is an area where original information in the image is located, and the content area includes both the function information and the watermark information.

In an embodiment of the application, when the functional information is text information, keyword matching is performed on the text information and content in the content area, if the content area contains target content successfully matched, first text composition information of the text information is obtained, the first text composition information includes a sequence of each text in the text information, a font size relationship of the text, a word number of the text information, and the like, and further, second text composition information of the target content is obtained, the second text composition information includes a spacing distance of the target content, the contained text information, a font size, a word number, and the like, and the functional sub-area is determined according to the first text composition information and the second text composition information.

In this example, when determining the text information, the position of the desired keyword in the target image is determined in the content region obtained by the above recognition according to the keyword recognition technology, because OCR text recognition may have omission and not completely recognize all the text and positions in the whole keyword, the layout information is required to determine the functional sub-region.

For example, as shown in fig. 3, when the text information is "examinee name", according to the keyword matching technique, the target content in the identified content area is "name", the first typesetting information of the acquired "examinee name" is "four texts, the sequence is" test, birth, last name, and first name ", and the font size is the same", the second typesetting information of the acquired "name" is "two words, the sequence is" name ", the interval between words is a, the font size is b", and the functional sub-area in the content area can be calculated according to a and b.

In an embodiment of the application, when the function information includes image information, such as stamp information, two-dimensional code information, barcode information, and the like, first image feature information in the content area may be extracted, second image feature information of the image information may be acquired, and the first image feature information and the second image feature information may be matched, so as to find an area where the image information in the target image is located according to a matching result. That is, if the successfully matched target image feature information is determined in the first image feature information, the region where the target image feature information is located is determined as the functional sub-region.

In this embodiment, the type of the image information may also be predetermined, and the corresponding recognition tool is matched for each type of the image information, for example, when the image information is a two-dimensional code, the corresponding two-dimensional code may be recognized according to the two-dimensional code recognition tool.

In this embodiment, for image information such as a national emblem and a seal, since such image information is relatively fixed, an object detection technology can be adopted, and an image marked with a position of the national emblem and a position of the seal pattern is used as a training set to train and obtain an object detection model, which is applied to detection of qualified national emblems and seals.

In step 103, candidate sub-regions other than the functional sub-region in the content region are determined.

And 104, carrying out watermark detection in the candidate subarea.

It is easy to understand that the candidate sub-region outside the content region is a region where the watermark exists, and therefore, in the content region, the candidate sub-region outside the functional sub-region is determined to perform watermark detection in the candidate sub-region, so that on one hand, the watermark detection efficiency is improved, each region of the target image does not need to be detected, and on the other hand, the watermark detection accuracy is improved.

In an embodiment of the application, image features of candidate sub-regions are identified, the identified image features are matched with preset watermark image features, and if the candidate sub-regions contain image features matched with the preset watermark image features, the existence of a watermark image in the candidate sub-regions is indicated. Considering that in the direct execution process, the possible watermark is an invisible watermark, under the condition, a component image is obtained from a candidate sub-area, the component image is divided to obtain pixel blocks, the pixel blocks containing the invisible watermark information are selected from the pixel blocks, further, the pixel blocks containing the invisible watermark information are subjected to QRC decomposition to obtain an upper triangular matrix, binary sequence information of the invisible watermark is extracted from the fourth column of the first line of the upper triangular matrix, watermark component information is obtained according to the binary sequence information of the invisible watermark, and the watermark component information is processed to obtain an invisible watermark extraction image; and decoding the invisible watermark extraction image to identify the invisible watermark.

Since the watermarks are all concentrated in the core portion of the target image, the area outside the frame is complex, such as the image background, which is easily recognized as the watermark by mistake, and therefore, in an embodiment of the present application, in order to further improve the accuracy and efficiency of watermark recognition, the image frame of the target image is detected, for example, the boundary of the identified functional sub-area can be used as an initial frame, and the frame of the target image has the characteristics of surrounding and being continuous, so the area outside the initial boundary can be circled out as the image frame of the target image by the mser algorithm, and further, the target sub-area located in the image frame is determined in the candidate sub-area, and watermark detection is performed in the target sub-area, in some possible examples, the area outside the image frame of the target image can also be directly blackened, and then the image frame becomes a completely black condition, and then, respectively extending the initial boundaries upwards, downwards, leftwards and rightwards, and determining the initial boundaries as the boundaries of the image frame when the initial boundaries are contacted with the closed black lines.

In order to make it more clear to those skilled in the art, the watermark identification method according to the embodiment of the present application is described below with reference to specific embodiments, where in this example, the target image is a business license:

in this example, as shown in fig. 4, after the target image is acquired, the target image is subjected to tilt correction and image scaling processing, the target image is processed so as to be correctly placed and have an appropriate image size, a character region in the target image is identified by an OCR character recognition algorithm, a stable region in the target image is identified by an Mser algorithm, and a content region in the image is identified by performing two-dimensional code detection, barcode detection, and the like.

Further, the original function information in the license, for example, the region titled "license" keyword, the national emblem and seal region, the frame region, etc. are acquired, and further, referring to fig. 4 and 5, region screening is performed to screen out a content region (thin solid line region in fig. 5) other than the function region (broken line region in fig. 5) in which the function information in the license is located as a candidate sub-region (thick solid line region in fig. 5), and watermark detection is performed in the candidate sub-region.

However, the above watermark identification method is intended to detect candidate sub-regions where watermarks may exist, when watermarks are overlaid on part of functional information, in order to accurately extract watermarks, when a functional sub-region is detected, whether watermark information exists in the functional sub-region may also be identified, if a watermark exists, the functional information of the functional sub-region is erased, and an erased region is used as a candidate sub-region, and if a part of watermarks is overlaid on the functional information, the region is retained, and functional information that is not overlaid by the watermarks is erased.

In summary, the watermark detection method of the embodiment of the application obtains the function information of the target image, identifies the content area in the target image, further matches the function information with the content in the content area, determines the function sub-area where the function information is located, determines the candidate sub-area in the content area except the function sub-area, and finally performs watermark detection in the candidate sub-area. Therefore, the candidate subareas where the watermarks are possibly located are screened out firstly, watermark detection is carried out in the candidate subareas, the accuracy and efficiency of watermark identification are improved, and the technical problem of identification difficulty caused by watermark diversification in the prior art is solved.

In order to implement the foregoing embodiment, the present application further provides a watermark identification apparatus, and fig. 6 is a schematic structural diagram of the watermark identification apparatus according to an embodiment of the present application, as shown in fig. 6, where the watermark identification includes: an acquisition module 10, an identification module 20, a first determination module 30, a second determination module 40 and a detection module 50, wherein,

and the acquisition module 10 is used for acquiring the function information of the target image.

And the identifying module 20 is used for identifying the content area in the target image.

And a first determining module 30, configured to match the function information with the content in the content area, and determine a function sub-area where the function information is located.

A second determining module 40 for determining candidate sub-areas out of the functional sub-areas in the content area.

A detection module 50 for performing watermark detection in the candidate sub-region.

In an embodiment of the application, when the function information includes text information, the first determining module 30 is specifically configured to:

matching the character information with the content in the content area by keywords;

if the content area contains the target content which is successfully matched, acquiring first character typesetting information of the character information;

and acquiring second character typesetting information of the target content, and determining a functional sub-area according to the first character typesetting information and the second character typesetting information.

In an embodiment of the application, when the function information includes image information, the first determining module 30 is specifically configured to:

extracting first image characteristic information in the content area, and acquiring second image characteristic information of the image information;

matching the first image characteristic information with the second image characteristic information, and determining target image characteristic information which is successfully matched in the first image characteristic information;

and determining the area where the target image characteristic information is located as a functional subarea.

In an embodiment of the present application, the obtaining module 10 is specifically configured to: acquiring image type information corresponding to the target image;

inquiring a preset database to obtain typesetting structure information corresponding to the image type information, wherein the typesetting structure information comprises a function information type and position information corresponding to the function information type;

and determining the functional information according to the typesetting structure information.

It should be noted that the foregoing explanation of the watermark identification method is also applicable to the watermark identification apparatus in the embodiment of the present invention, and the implementation principle is similar, and is not described herein again.

In summary, the watermark detection apparatus of the embodiment of the present application obtains the function information of the target image, identifies the content region in the target image, further matches the function information with the content in the content region, determines the function sub-region where the function information is located, determines the candidate sub-region outside the function sub-region in the content region, and finally performs watermark detection in the candidate sub-region. Therefore, the candidate subareas where the watermarks are possibly located are screened out firstly, watermark detection is carried out in the candidate subareas, the accuracy and efficiency of watermark identification are improved, and the technical problem of identification difficulty caused by watermark diversification in the prior art is solved.

According to an embodiment of the present application, an electronic device and a readable storage medium are also provided.

Fig. 7 is a block diagram of an electronic device according to an embodiment of the present application. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present application that are described and/or claimed herein.

As shown in fig. 7, the electronic apparatus includes: one or more processors 701, a memory 702, and interfaces for connecting the various components, including a high-speed interface and a low-speed interface. The various components are interconnected using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions for execution within the electronic device, including instructions stored in or on the memory to display graphical information of a GUI on an external input/output apparatus (such as a display device coupled to the interface). In other embodiments, multiple processors and/or multiple buses may be used, along with multiple memories and multiple memories, as desired. Also, multiple electronic devices may be connected, with each device providing portions of the necessary operations (e.g., as a server array, a group of blade servers, or a multi-processor system). In fig. 7, one processor 701 is taken as an example.

The memory 702 is a non-transitory computer readable storage medium as provided herein. Wherein the memory stores instructions executable by at least one processor to cause the at least one processor to perform the methods provided herein. The non-transitory computer readable storage medium of the present application stores computer instructions for causing a computer to perform the methods provided herein.

The memory 702 serves as a non-transitory computer-readable storage medium, and may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as program instructions/modules corresponding to the method for identifying the validity of parking bit data in the embodiment of the present application (for example, the acquisition module 10, the identification module 20, the first determination module 30, the second determination module 40, and the detection module 50 shown in fig. 6). The processor 701 executes various functional applications of the server and data processing, i.e., implements the method of watermark identification in the above-described method embodiments, by executing the non-transitory software programs, instructions, and modules stored in the memory 702.

The memory 702 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of the electronic device, and the like. Further, the memory 702 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 702 may optionally include memory located remotely from the processor 701, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The electronic device performing the method of watermark identification may further include: an input device 703 and an output device 704. The processor 701, the memory 702, the input device 703 and the output device 704 may be connected by a bus or other means, and fig. 7 illustrates an example of a connection by a bus.

The input devices 703 may receive input numeric or character information and generate key signal inputs related to user settings and function control of the electronic device, such as a touch screen, keypad, mouse, track pad, touch pad, pointing stick, one or more mouse buttons, track ball, joystick, etc. the output devices 704 may include a display device, auxiliary lighting devices (e.g., L ED), and tactile feedback devices (e.g., vibration motor), etc.

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

As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and/or device (e.g., magnetic discs, optical disks, memory, programmable logic devices (P L D)) used to provide machine instructions and/or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal.

The systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or L CD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer for providing interaction with the user.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., AN application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with AN implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components.

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

In order to implement the above embodiments, the present application also proposes a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the above-described watermark recognition method.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present application may be executed in parallel, sequentially, or in different orders, and the present invention is not limited thereto as long as the desired results of the technical solutions disclosed in the present application can be achieved.

The above-described embodiments should not be construed as limiting the scope of the present application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method of watermark identification, comprising:

acquiring function information of the target image, and identifying a content area in the target image;

matching the function information with the content in the content area, and determining a function sub-area where the function information is located;

determining candidate sub-regions in the content region outside of the functional sub-regions;

and carrying out watermark detection in the candidate subarea.

2. The method of claim 1, wherein the acquiring the functional information of the target image comprises:

acquiring image type information corresponding to the target image;

determining typesetting structure information corresponding to the image type information, wherein the typesetting structure information comprises a function information type and position information corresponding to the function information type;

3. The method of claim 1, wherein when the function information includes text information, the matching the function information with the content in the content area to determine the function sub-area where the function information is located includes:

carrying out keyword matching on the text information and the content in the content area;

and acquiring second character typesetting information of the target content, and determining the functional sub-area according to the first character typesetting information and the second character typesetting information.

4. The method of claim 1, wherein when the function information includes image information, the matching the function information with content in the content area to determine a function sub-area where the function information is located comprises:

and determining the region where the target image characteristic information is located as the functional sub-region.

5. The method of claim 1, wherein the identifying the content region in the target image comprises:

recognizing a character area in the target image according to a character recognition algorithm;

detecting a candidate content area in the target image according to an area detection algorithm;

and generating the content area according to the character area and the candidate content area.

6. The method of claim 1, wherein the performing watermark detection in the candidate sub-region comprises:

detecting an image frame of the target image;

determining a target sub-region located within the image border among the candidate sub-regions;

and carrying out watermark detection in the target sub-area.

7. A watermark identification apparatus, comprising:

the acquisition module is used for acquiring the functional information of the target image;

the identification module is used for identifying a content area in the target image;

the first determining module is used for matching the function information with the content in the content area and determining a function sub-area where the function information is located;

a second determining module, configured to determine a candidate sub-region in the content region other than the functional sub-region;

a detection module, configured to perform watermark detection in the candidate sub-region.

8. The apparatus of claim 7, wherein the obtaining module is specifically configured to:

acquiring image type information corresponding to the target image;

9. The apparatus of claim 7, wherein when the functional information includes text information, the first determining module is specifically configured to:

10. The apparatus of claim 7, wherein when the functional information includes image information, the first determining module is specifically configured to:

11. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of watermark identification of any one of claims 1-6.

12. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the watermark identification method of any one of claims 1 to 6.