Video processing method, device, computer equipment and storage medium

Abstract

The present application discloses a video processing method, apparatus, computer equipment and storage medium, which relate to certificate recognition in cloud security technology, wherein the method comprises: after acquiring a target video obtained by multi-angle shooting of a certificate including a light-sensitive anti-counterfeiting area, processing the target video to obtain a sequence of image frames to be processed; extracting features of the certificate light-sensitive anti-counterfeiting area of ​​each image frame, and extracting features of the certificate background area of ​​each image frame, to obtain a first feature sequence set corresponding to the certificate light-sensitive anti-counterfeiting area of ​​each image frame and a second feature sequence set corresponding to the certificate background area of ​​each image frame; determining a feature difference sequence set based on the first feature sequence set and the second feature sequence set, and then determining a target authenticity recognition result of the certificate in the target video based on the feature difference sequence set. By using this method, the accuracy of certificate authenticity recognition can be effectively improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a video processing method, apparatus, computer equipment and storage medium. Background Art

[0002] In the era of rapid development of information technology, certificates are the best passes. Every citizen can have different types of certificates at the same time, such as identity certificates, qualification certificates, etc. All kinds of certificates are for the convenience of citizens to carry out various social activities. Certificate authenticity identification is to identify the authenticity of certificates. Certificate authenticity identification can help relevant departments better maintain social order. Therefore, an accurate certificate authenticity identification method is particularly important. Summary of the invention

[0003] The embodiments of the present application provide a video processing method, apparatus, computer equipment and storage medium, which can effectively improve the accuracy of document authenticity identification.

[0004] On the one hand, an embodiment of the present application discloses a video processing method, the method comprising:

[0005] Acquire a target video, and acquire a sequence of image frames to be processed from the target video, wherein the target video is obtained by shooting a certificate including a light-sensitive anti-counterfeiting area at multiple angles;

[0006] Extracting features of the photosensitive anti-counterfeiting area of ​​each image frame in the sequence of image frames to be processed, respectively, to obtain a first feature sequence set corresponding to the photosensitive anti-counterfeiting area of ​​each image frame;

[0007] Extracting features of the document background region of each image frame in the sequence of image frames to be processed respectively, and obtaining a second feature sequence set corresponding to the document background region of each image frame;

[0008] Determine a feature difference sequence set according to the first feature sequence set and the second feature sequence set, wherein the feature difference values ​​in the feature difference sequence set are determined according to the matching feature values ​​in the first feature sequence set and the second feature sequence set;

[0009] The target authenticity recognition result of the certificate in the target video is determined according to the feature difference sequence set.

[0010] The present application discloses a video processing device, which includes:

[0011] An acquisition unit, used to acquire a target video and obtain a sequence of image frames to be processed from the target video, wherein the target video is obtained by shooting a certificate including a light-sensitive anti-counterfeiting area at multiple angles;

[0012] A processing unit is used to extract features from the photosensitive anti-counterfeiting area of ​​the certificate of each image frame in the sequence of image frames to be processed, and obtain a first feature sequence set corresponding to the photosensitive anti-counterfeiting area of ​​the certificate of each image frame; extract features from the background area of ​​the certificate of each image frame in the sequence of image frames to be processed, and obtain a second feature sequence set corresponding to the background area of ​​the certificate of each image frame;

[0013] A determination unit is used to determine a feature difference sequence set based on the first feature sequence set and the second feature sequence set, wherein the feature difference values ​​in the feature difference sequence set are determined based on the matching feature values ​​in the first feature sequence set and the second feature sequence set; and determine a target authenticity recognition result of the certificate in the target video based on the feature difference sequence set.

[0014] On the one hand, an embodiment of the present application discloses a computer device, including an input interface and an output interface. The computer device also includes a processor suitable for implementing one or more computer programs; and a computer storage medium, wherein the computer storage medium stores one or more computer programs, and the one or more computer programs are suitable for being loaded by the processor and executed with the above-mentioned video processing method.

[0015] In one aspect, the present application discloses a computer-readable storage medium storing one or more computer programs, wherein the one or more computer programs are suitable for being loaded by a processor and executing the above-mentioned video processing method.

[0016] The present application discloses a computer program product, which includes a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program, so that the computer device executes the above-mentioned video processing method.

[0017] In the embodiment of the present application, after the computer device obtains the target video obtained by multi-angle shooting of the certificate including the light-sensitive anti-counterfeiting area, it first processes the target video to obtain all the image frames, and then obtains the sequence of image frames to be processed from all the image frames. The computer device then extracts features of the certificate light-sensitive anti-counterfeiting area of ​​each image frame in the sequence of image frames to be processed, and extracts features of the certificate background area of ​​each image frame in the sequence of image frames to be processed, thereby obtaining a first feature sequence set corresponding to the certificate light-sensitive anti-counterfeiting area of ​​each image frame and a second feature sequence set corresponding to the certificate background area of ​​each image frame. Finally, the computer device determines each feature difference value in the feature difference sequence set based on the matching feature values ​​in the first feature sequence set and the second feature sequence set, and then obtains the authenticity recognition parameters based on the feature difference sequence set to determine the target authenticity recognition result of the certificate in the target video. Through this method, multiple features of the certificate in the video are dynamically analyzed, thereby effectively improving the accuracy of certificate authenticity recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 is a schematic diagram of the architecture of a video processing system disclosed in an embodiment of the present application;

[0020] Figure 2 It is a flowchart of a video processing method disclosed in an embodiment of the present application;

[0021] Figure 3 It is a flowchart of another video processing method disclosed in an embodiment of the present application;

[0022] Figure 4 is a module schematic diagram of a video processing system disclosed in an embodiment of the present application;

[0023] Figure 5 is a structural schematic diagram of a video processing device disclosed in an embodiment of the present application;

[0024] Figure 6 It is a structural schematic diagram of a computer device disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0026] In order to effectively improve the accuracy of document recognition, the embodiment of the present application proposes a video processing solution. The video processing method provided by the present application involves cloud technology and cloud security technology in cloud technology. Specifically: Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network in a wide area network or a local area network to realize data calculation, storage, processing, and sharing. Cloud technology is a general term for network technology, information technology, integration technology, management platform technology, application technology, etc. based on the application of cloud computing business model. It can form a resource pool, which is used on demand and is flexible and convenient. Cloud computing technology will become an important support. The background services of the technical network system require a large amount of computing and storage resources, such as video websites, picture websites, and more portal websites. With the high development and application of the Internet industry, in the future, each item may have its own identification mark, which needs to be transmitted to the background system for logical processing. Data of different levels will be processed separately. All kinds of industry data require strong system backing support, which can only be achieved through cloud computing.

[0027] Cloud security refers to the general term for security software, hardware, users, organizations, and security cloud platforms based on cloud computing business model applications. Cloud security integrates emerging technologies and concepts such as parallel processing, grid computing, and unknown virus behavior judgment. Through a large number of networked clients, it monitors abnormal software behavior in the network, obtains the latest information on Trojans and malicious programs on the Internet, and sends it to the server for automatic analysis and processing, and then distributes virus and Trojan solutions to each client.

[0028] The main research directions of cloud security include: 1. Cloud computing security, which mainly studies how to ensure the security of the cloud itself and various applications on the cloud, including cloud computer system security, secure storage and isolation of user data, user access authentication, information transmission security, network attack protection, compliance auditing, etc.; 2. Cloudification of security infrastructure, which mainly studies how to use cloud computing to build and integrate security infrastructure resources and optimize security protection mechanisms, including building a large-scale security event, information collection and processing platform through cloud computing technology, realizing the collection and correlation analysis of massive information, and improving the control ability of security events and risk control capabilities of the entire network; 3. Cloud security services, which mainly studies various security services provided to users based on cloud computing platforms, such as antivirus services.

[0029] See also Figure 1 As shown, it is a schematic diagram of the architecture of a video processing system disclosed in an embodiment of the present application. The video processing system 100 may at least include: one or more terminal devices 101 and a computer device 102, wherein the terminal device 101 can be mainly used to send a target video obtained by shooting a certificate including a light-sensitive anti-counterfeiting area of ​​the certificate at multiple angles to the computer device 102, and the computer device 102 can be mainly used to identify the authenticity of the certificate in the target video, and return the target authenticity identification result to the terminal device 101. The so-called identification of the authenticity of the certificate is to determine the authenticity of the certificate. Among them, one or more terminal devices 101 can realize communication connection with the computer device 102, and the corresponding connection mode may include wired connection and wireless connection, which is not limited.

[0030] It should be noted that the terminal device 101 mentioned above can be a smart phone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, smart car, etc., but is not limited to this. Any of the computer devices 102 mentioned above can be a server, which can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Figure 1 The system architecture of the video processing system is merely exemplified and is not intended to be limiting. Figure 1 The computer device 101 can be deployed as a node in the blockchain network, or the computer device 101 can be connected to the blockchain network, so that the computer device 101 can upload internal data to the blockchain network for storage to prevent the internal data from being tampered with, thereby ensuring data security.

[0031] In a specific implementation, the identification scheme of the certificate in the video proposed by the embodiment of the present application is implemented by the above-mentioned video processing system. The general process is as follows: after the computer device obtains the target video obtained by multi-angle shooting of the certificate including the light-sensitive anti-counterfeiting area of ​​the certificate, it first processes the target video to obtain all image frames, and then obtains the image frame sequence to be processed from all the image frames. Further, the computer device extracts features of the certificate light-sensitive anti-counterfeiting area of ​​each image frame in the image frame sequence to be processed, and extracts features of the certificate background area of ​​each image frame in the image frame sequence to be processed, thereby obtaining the first feature sequence set corresponding to the certificate light-sensitive anti-counterfeiting area of ​​each image frame and the second feature sequence set corresponding to the certificate background area of ​​each image frame. Finally, the computer device determines each feature difference value in the feature difference sequence set according to the matching feature values ​​in the first feature sequence set and the second feature sequence set, and then obtains the authenticity recognition parameter according to the feature difference sequence set to determine the target authenticity recognition result of the certificate in the target video.

[0032] Based on the above description, the video processing method provided in the embodiment of the present application uses multi-angle shooting of the certificate to obtain the target video, and then extracts the dynamic image features of the light-sensitive anti-counterfeiting area of ​​the target certificate in the target video, and identifies the features of the light-sensitive anti-counterfeiting area of ​​the certificate by analyzing the dynamic features, thereby determining the authenticity of the certificate. The video-based method can extract richer dynamic features, thereby effectively improving the accuracy of document authenticity identification.

[0033] Based on the above description of the video processing system, the present application embodiment discloses a video processing method, see Figure 2 , is a flow chart of a video processing method disclosed in an embodiment of the present application, and the video processing method can be executed by a computer device. Specifically, the video processing method can include steps S201 to S205:

[0034] S201, obtaining a target video, and obtaining a sequence of image frames to be processed from the target video.

[0035] In a possible implementation, a computer device acquires a target video, and the target video may be sent to the computer device by a user of a terminal device using the terminal device when the user needs to authenticate the authenticity of a certificate. In some possible embodiments, the target video may also be actively acquired by the computer device from a database. Optionally, after acquiring the target video, the computer device may perform a preliminary screening of the target video to filter out the target video that does not include the photosensitive anti-counterfeiting area of ​​the certificate. The computer device then uses video processing technology to decode the target video to obtain all image frames of the target video, and then samples all image frames, and obtains one or more image frames based on the sampling results to determine a sequence of image frames to be processed, and the sequence of image frames to be processed includes multiple image frames. In an embodiment of the present application, the target video is processed to obtain a sequence of image frames to be processed, so it can be assumed that the number of image frames to be processed included in the sequence of image frames to be processed is N, where N is an integer greater than 1. Among them, the sampling method can be random sampling or timed sampling (sampling a certain number of frames at certain intervals); the obtained sequence of image frames to be processed can be arranged according to the time sequence of the recorded video, or can be arranged randomly, or can be arranged according to the similarity of angles, for example, the same or similar angles are arranged together.

[0036] Among them, the target video is obtained by shooting at multiple angles of the certificate including the light-sensitive anti-counterfeiting area of ​​the certificate. It can be understood that the target video is obtained by the user using a terminal device, such as a camera, a mobile phone and other devices with a recording function, to shoot the certificate at multiple angles (referring to different azimuths). The certificate can refer to an identification document, such as an identity card, a passport, etc., and the certificate can also refer to a qualification certificate, such as a business qualification certificate, a driver's license, etc. Regardless of the type of certificate, there will be a preset area for identifying the authenticity of the certificate, which we can call the certificate light-sensitive anti-counterfeiting area (or the certificate light-sensitive anti-counterfeiting point).

[0037] S202 , extracting features from the photosensitive anti-counterfeiting area of ​​each image frame in the sequence of image frames to be processed, respectively, to obtain a first feature sequence set corresponding to the photosensitive anti-counterfeiting area of ​​each image frame.

[0038] In one possible implementation, a computer device may utilize a feature extraction module to perform feature extraction on the photosensitive anti-counterfeiting area of ​​each image frame in the sequence of image frames to be processed, thereby obtaining a first feature sequence set corresponding to the photosensitive anti-counterfeiting area of ​​each image frame. The photosensitive anti-counterfeiting area of ​​the certificate is the area used to distinguish the authenticity of the certificate. The first feature sequence set may include at least one or more of the following: a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence, each feature sequence representing a feature of the photosensitive anti-counterfeiting area of ​​the certificate. Assuming that the first feature sequence set includes a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence, it is equivalent to a computer device extracting the color, brightness, and contrast of each image frame in the sequence of image frames to be processed. There are two ways of extraction here:

[0039] First, the computer device can first extract the color features of each image frame in the image frame sequence to be processed to obtain a first color feature sequence, such as (y1, y2, ..., yN), where y represents the color feature; then extract the brightness features of each image frame in the image frame sequence to be processed to obtain a first brightness feature sequence, such as (l1, l2, ..., lN), where l represents the brightness feature; then extract the contrast features of each image frame in the image frame sequence to be processed to obtain a first contrast feature sequence, such as (d1, d2, ..., dN), where d represents the contrast feature; finally, all feature sequences are combined together to obtain a first feature sequence set, such as {(y1, y2, ..., yN), (l1, l2, ..., lN), (d1, d2, ..., dN)}.

[0040] Second, the computer device can first extract the first color feature, the first brightness feature, and the first contrast feature of the first image frame in the image frame sequence to be processed to obtain (y1, l1, d1); then extract the first color feature, the first brightness feature, and the first contrast feature of the second image frame in the image frame sequence to be processed to obtain (y2, l2, d2); extract in sequence, and finally extract the first color feature, the first brightness feature, and the first contrast feature of the Nth image frame in the image frame sequence to be processed to obtain (yN, lN, dN); finally, combine all feature sequences to obtain a first feature sequence set, that is, {(y1, l1, d1), (y2, l2, d2), …, (yN, lN, dN)}, where (y1, y2, …, yN) represents the first color feature sequence, (l1, l2, …, lN) represents the first brightness sequence, and (d1, d2, …, dN) represents the first contrast feature sequence.

[0041] S203 , extracting features from the document background region of each image frame in the image frame sequence to be processed, respectively, to obtain a second feature sequence set corresponding to the document background region of each image frame.

[0042] In a possible implementation, the computer device can use the feature extraction module to perform feature extraction on the document background area of ​​each image frame in the image frame sequence to be processed, so as to obtain a second feature sequence set corresponding to the document background area of ​​each image frame. Among them, the document background area can be understood as other areas of the document except the light-sensitive anti-counterfeiting area of ​​the document. The second feature sequence set can include at least one or more of the following: a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence, each feature sequence representing a feature of the document background area. Assuming that the second feature sequence set includes a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence, it is equivalent to the computer device extracting the color, brightness, and contrast of each image frame in the image frame sequence to be processed. The extraction method here can also include two methods, which are the same as the two methods described in step S202, and will not be repeated here.

[0043] In a possible implementation, the execution order of step S202 and step S203 is not fixed, and step S202 may be executed first and then step S203, or step S203 may be executed first and then step S202, or step S202 and step S203 may be executed simultaneously, which is not limited here. At the same time, the "first" and "second" in the first feature sequence set and the second feature sequence set do not have sequential meanings, but are only used to represent feature sequence sets of two different regions.

[0044] S204. Determine a feature difference sequence set according to the first feature sequence set and the second feature sequence set.

[0045] In a possible implementation, the specific implementation of the computer device determining the feature difference sequence set according to the first feature sequence set and the second feature sequence set can be: the computer device determines each feature difference value according to the feature values ​​matched in the first feature sequence set and the second feature sequence set. For example, if the first feature sequence set includes the first color feature sequence, the first brightness feature sequence and the first contrast feature sequence, and the second feature sequence set includes the second color feature sequence, the second brightness feature sequence and the second contrast feature sequence, the computer device calculates the color feature difference sequence according to the first color feature sequence and the second color feature sequence, calculates the brightness feature difference sequence according to the first brightness feature sequence and the second brightness feature sequence, and calculates the contrast feature difference sequence according to the first contrast feature sequence and the second contrast feature sequence. Correspondingly, the feature difference sequence set includes the color feature difference sequence, the brightness feature difference sequence and the contrast feature difference sequence. For another example, if the first feature sequence set includes one or two of the first color feature sequence, the first brightness feature sequence and the first contrast feature sequence, and the second feature sequence set also includes one or two of the second color feature sequence, the second brightness feature sequence and the second contrast feature sequence, the computer device calculates the respective feature difference sequences according to the corresponding feature sequences. When the feature difference is calculated, the feature difference between the photosensitive anti-counterfeiting area of ​​the document and the background area of ​​the document in the same image frame is calculated.

[0046] S205: Determine the target authenticity recognition result of the certificate in the target video according to the feature difference sequence set.

[0047] In a possible implementation, the feature difference sequence set includes one or more feature difference sequences, each feature difference sequence corresponds to the same feature category of each image frame, and different feature difference sequences correspond to different feature categories of each image frame. The computer device may first determine the authenticity identification parameters of each feature difference sequence included in the feature difference sequence set, and then determine the reference authenticity identification results corresponding to each feature category based on the authenticity identification parameters. If the target feature category is taken as an example, the target feature category is any one of the one or more feature categories corresponding to each feature difference sequence, and the computer device determines the reference authenticity identification result corresponding to the target feature category, which may specifically include: if the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is greater than the reference threshold, then the reference authenticity identification result corresponding to the target feature category is determined to be the first identification result, and the first identification result indicates that the certificate is true; if the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is less than or equal to the reference threshold, then the reference authenticity identification result corresponding to the target feature category is determined to be the second identification result, and the second identification result indicates that the certificate is false. Correspondingly, the determination results of the reference authenticity identification results corresponding to the feature categories of each feature difference sequence included in the feature difference sequence set are consistent. For different feature categories, the corresponding reference thresholds may be the same or different. The reference authenticity recognition result corresponding to the feature category can be represented by "0" or "1". If it is true, it can be represented by "1", and if it is false, it can be represented by "0".

[0048] Furthermore, the computer device determines a target authenticity recognition result of the certificate in the target video based on the reference authenticity recognition results corresponding to each feature category, which may specifically include: the computer device may determine the number of first feature categories and the number of second feature categories based on the reference authenticity recognition results corresponding to each feature category, wherein the first feature category is a feature category whose corresponding authenticity recognition result indicates that the certificate is authentic, and the second feature category is a feature category whose corresponding authenticity recognition result indicates that the certificate is fake; and then determine the target authenticity recognition result of the certificate in the target video based on the number of the first feature categories and the number of the second feature categories. Specifically, if the number of the first feature categories is greater than the number of the second feature categories, it can be determined that the light-sensitive anti-counterfeiting area of ​​the certificate in the target video is authentic, and then determine that the certificate in the target video is authentic; otherwise, if the number of the first feature categories is less than or equal to the number of the second feature categories, it can be determined that the light-sensitive anti-counterfeiting area of ​​the certificate in the target video is fake, and then determine that the certificate in the target video is fake.

[0049] In the embodiment of the present application, after the computer device obtains the target video obtained by multi-angle shooting of the certificate including the light-sensitive anti-counterfeiting area of ​​the certificate, it first processes the target video to obtain all image frames, and then obtains the sequence of image frames to be processed from all the image frames. Further, the computer device extracts features of the certificate light-sensitive anti-counterfeiting area of ​​each image frame in the sequence of image frames to be processed, and extracts features of the certificate background area of ​​each image frame in the sequence of image frames to be processed, thereby obtaining a first feature sequence set corresponding to the certificate light-sensitive anti-counterfeiting area of ​​each image frame and a second feature sequence set corresponding to the certificate background area of ​​each image frame. Finally, the computer device determines each feature difference value in the feature difference sequence set based on the matching feature values ​​in the first feature sequence set and the second feature sequence set, and then obtains the authenticity recognition parameters based on the feature difference sequence set to determine the target authenticity recognition result of the certificate in the target video. Through this method, multiple features of the certificate in the video are dynamically analyzed, thereby effectively improving the accuracy of certificate authenticity recognition.

[0050] According to the above description, it can be known that the first feature sequence set includes one or more of the following: a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence; the second feature sequence set includes one or more of the following: a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence; the feature difference sequence set can be obtained by corresponding to the feature sequence included in the first feature sequence set and the feature sequence included in the second feature sequence set. Similarly, the feature difference sequence set includes one or more of the following: a color feature difference sequence, a brightness feature difference sequence, and a contrast feature difference sequence. For example, the first feature sequence set includes a first color feature sequence and a first brightness feature sequence, and the second feature sequence set includes a second color feature sequence and a second brightness feature sequence. Correspondingly, the feature difference sequence set includes a color feature difference sequence and a brightness feature difference sequence.

[0051] Assuming that the first feature sequence set includes a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence, and the second feature sequence set includes a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence, correspondingly, the feature difference sequence set includes a color feature difference sequence, a brightness feature difference sequence, and a contrast feature difference sequence. Based on this, the embodiment of the present application discloses another video processing method, see Figure 3 , is a flow chart of another video processing method disclosed in an embodiment of the present application, and the video processing method can be executed by a computer device. The video processing method can specifically include steps S301 to S307:

[0052] S301: Acquire a target video, and acquire a sequence of image frames to be processed from the target video.

[0053] Some feasible implementations of step S301 can be found in Figure 2 The description of step S201 in will not be repeated here.

[0054] S302 , extracting features from the photosensitive anti-counterfeiting area of ​​each image frame in the image frame sequence to be processed, and obtaining a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence corresponding to the photosensitive anti-counterfeiting area of ​​each image frame.

[0055] S303 , extracting features from the document background region of each image frame in the image frame sequence to be processed, respectively, to obtain a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence corresponding to the document background region of each image frame.

[0056] Among them, step S302 and the method for determining the color features in step S303 can directly extract the RGB mean of the image frame, that is, [red, green, blue], where R is red, G is green, and B (Blue) is blue. RGB represents the colors of the three channels of red, green, and blue. Various colors are obtained by changing the three color channels of red (R), green (G), and blue (B) and superimposing them on each other. In addition to using the RGB color space to determine the color features, the HSV color space can also be used to determine the color features, where H is hue, S is saturation, and V is lightness, or the LAB color space can be used to determine the color features, where L represents lightness, A represents red-green difference, and B (Blue-yellow difference) represents blue-yellow difference.

[0057] The method for determining the brightness feature is to directly take the average of the above color feature parameters [red, green, blue], that is, brightness = (red + green + blue) / 3, to obtain the brightness feature of a certain image frame; or the brightness feature can be calculated by weighted average, for example, the brightness feature is R*0.299+G*0.587+B*0.114.

[0058] The method for determining the contrast feature can be to convert the image frame into a grayscale image and calculate the variance of the grayscale image pixel values; or the formula can be used in, Refers to the grayscale difference between adjacent pixels. Refers to the adjacent grayscale difference The probability distribution of , C represents the contrast feature.

[0059] It should be noted that the above-mentioned methods for determining color features, brightness features and contrast features are some of the methods listed in the embodiments of the present application. In some feasible embodiments, other methods may also be used, which are not listed one by one here.

[0060] S304: Determine a color feature difference sequence according to the first color feature sequence and the second color feature sequence, determine a brightness feature difference sequence according to the first brightness feature sequence and the second brightness feature sequence, and determine a contrast feature difference sequence according to the first contrast feature sequence and the second contrast feature sequence.

[0061] In a possible implementation, after determining each color feature in the first color feature sequence and the second color feature sequence, the color feature difference of each image frame can be determined based on this, thereby obtaining a color feature difference sequence. Correspondingly, the color feature difference (i.e., color difference) determination method can be to perform difference calculation on two RGB mean vectors (r11, g11, b11) and (r21, g21, b21), wherein (r11, g11, b11) is the color feature of the photosensitive anti-counterfeiting area of ​​the document in the first image frame, and (r21, g21, b21) is the color feature of the background area of ​​the document in the first image frame. Then, the color feature difference of the first image frame can be The color features of the photosensitive anti-counterfeiting area of ​​each image frame and the color features of the background area of ​​the document are calculated bit by bit to obtain a color feature difference sequence; or other methods can be used to determine the color feature difference. If it is for the LAB color space, the color difference can be Among them, ΔL, ΔA, and ΔB represent the differences between two color features in different components.

[0062] In a possible implementation, after determining each brightness feature in the first brightness feature sequence and the second brightness feature sequence, the brightness feature difference of each image frame can be determined based on this, and then a brightness feature difference sequence can be obtained. Correspondingly, the brightness feature difference determination method can be to subtract the brightness feature of the photosensitive anti-counterfeiting area of ​​the certificate from the brightness feature of the background area of ​​the certificate in each image frame in sequence, that is, the brightness feature difference of the first image frame can be |D11-D21|, and the brightness feature difference of the Nth image frame can be |D1N-D2N|, and the brightness feature difference sequence is obtained by combination, wherein D11 is the brightness feature of the photosensitive anti-counterfeiting area of ​​the certificate of the first image frame, D21 is the brightness feature of the background area of ​​the certificate of the first image frame, D1N is the brightness feature of the photosensitive anti-counterfeiting area of ​​the certificate of the Nth image frame, and D2N is the brightness feature of the background area of ​​the certificate of the Nth image frame.

[0063] In a possible implementation, after determining each contrast feature in the first contrast feature sequence and the second contrast feature sequence, the contrast feature difference of each image frame can be determined based on this, and then a contrast feature difference sequence can be obtained. Correspondingly, the contrast feature difference determination method can be to subtract the contrast feature of the photosensitive anti-counterfeiting area of ​​the document from the contrast feature of the background area of ​​the document in each image frame in sequence, that is, the contrast feature difference of the first image frame can be |C11-C21|, and the brightness feature difference of the Nth image frame can be |C1N-C2N|, and the contrast feature difference sequence is obtained by combination, wherein C11 is the contrast feature of the photosensitive anti-counterfeiting area of ​​the document of the first image frame, C21 is the contrast feature of the background area of ​​the document of the first image frame, C1N is the contrast feature of the photosensitive anti-counterfeiting area of ​​the document of the Nth image frame, and C2N is the contrast feature of the background area of ​​the document of the Nth image frame.

[0064] S305 , respectively determining the authenticity identification parameters of the color feature difference sequence, the authenticity identification parameters of the brightness feature difference sequence, and the authenticity identification parameters of the contrast feature difference sequence.

[0065] Among them, the authenticity identification parameter may refer to a statistical value, including but not limited to: mean, standard deviation, median, etc. Therefore, after determining the color feature difference sequence, brightness feature difference sequence, and contrast feature difference sequence, the computer device can perform weighted averaging according to each color feature difference in the color feature difference sequence to obtain the authenticity identification parameter of the color feature difference sequence; similarly, the same method is used to obtain the authenticity identification parameter of the brightness feature difference sequence and the authenticity identification parameter of the contrast feature difference sequence.

[0066] S306. Determine a reference authenticity recognition result of the color feature according to the authenticity recognition parameters and reference threshold of the color feature difference sequence, determine a reference authenticity recognition result of the brightness feature according to the authenticity recognition parameters and reference threshold of the brightness feature difference sequence, and determine a reference authenticity recognition result of the contrast feature according to the authenticity recognition parameters and reference threshold of the contrast feature difference sequence.

[0067] The reference threshold is derived a priori or set by the developer based on demand. The reference thresholds corresponding to the authenticity identification parameters can be the same or different. If they are the same, they are all called reference thresholds; if they are different, it can be assumed that there are first reference thresholds, second reference thresholds, and third reference thresholds.

[0068] In a possible implementation, the computer device compares the authenticity identification parameter of the color feature difference sequence with a reference threshold value. If the authenticity identification reference of the color feature difference sequence is greater than the reference threshold value, the reference authenticity identification result of the color feature can be determined to be true, which can be represented by "1". Otherwise, the reference authenticity identification result of the color feature is determined to be false, which can be represented by "0". Similarly, the authenticity identification parameter of the brightness feature difference sequence is compared with the reference threshold value. If the authenticity identification parameter of the brightness feature difference sequence is greater than the reference threshold value, the reference authenticity identification result of the brightness feature can be determined to be true, which can be represented by "1". Otherwise, the reference authenticity identification result of the brightness feature is determined to be false, which can be represented by "0". The authenticity identification parameter of the contrast feature difference sequence is compared with the reference threshold value. If the authenticity identification parameter of the contrast feature difference sequence is greater than the reference threshold value, the reference authenticity identification result of the contrast feature can be determined to be true, which can be represented by "1". Otherwise, the reference authenticity identification result of the contrast feature is determined to be false, which can be represented by "0".

[0069] To summarize the above description, when the feature categories are more than color, brightness and contrast, the corresponding general processing method may be, assuming the target feature category as an example, if the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is greater than the reference threshold, then the reference authenticity identification result corresponding to the target feature category is determined to be the first identification result, and the first identification result indicates that the target feature category is true, and the target feature category is any one of the one or more feature categories corresponding to each feature difference sequence; if the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is less than or equal to the reference threshold, then the reference authenticity identification result corresponding to the target feature category is determined to be the second identification result, and the second identification result indicates that the target feature category is false.

[0070] S307, determining a target authenticity recognition result of the certificate in the target video according to the number of authenticity in the reference authenticity recognition result in the color feature, the brightness feature and the contrast feature.

[0071] In a possible implementation, after the reference authenticity recognition results of the color feature, the brightness feature, and the contrast feature are determined, the target authenticity recognition result of the certificate in the target video is determined according to the number of true and false. Based on the description in step S306, the number of the first feature category can be determined according to the reference authenticity recognition results corresponding to each feature category, and the number of the second feature category can be determined. The first feature category is the feature category whose corresponding authenticity recognition result indicates that the certificate is true, which can be understood as the feature represented by "1" above, and the second feature category is the feature category whose corresponding authenticity recognition result indicates that the certificate is false, which can be understood as the feature represented by "0" above. If the number of the first feature category is greater than the number of the second feature category, that is, the number of 1s is greater than the number of 0s, then the target authenticity recognition result indicating that the certificate in the target video is true is obtained. On the contrary, if the number of the first feature category is less than or equal to the number of the second feature category, that is, the number of 1s is less than or equal to the number of 0s, then the target authenticity recognition result indicating that the certificate in the target video is false is obtained.

[0072] In an embodiment of the present application, the steps of how a computer device determines the authenticity of a certificate in a target video when the first feature sequence set includes a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence, and the second feature sequence set includes a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence are described in detail, and the accuracy of authenticity identification of the certificate is effectively improved by analyzing multiple features in the video.

[0073] according to Figure 2 as well as Figure 3 The description of the video processing method in the related embodiments can be understood as a video processing system that is executed by three modules, namely, a video frame extraction module, a feature extraction module, and a feature analysis module. Figure 4As shown. Among them, the video frame extraction module mainly splits the target video to obtain all video image frames, randomly samples the video image frames, and forms a sequence after the sampling is completed, so as to obtain the sequence of image frames to be processed; the feature extraction module mainly processes the image frames to be processed, and each image frame extracts the image features of the photosensitive anti-counterfeiting area of ​​the certificate and the image features of the background area of ​​the certificate in turn. The image features include color features, brightness features, contrast features, etc., and finally outputs two image feature sequences, which can be respectively called the first feature sequence set and the second feature sequence set; the feature analysis module mainly matches each feature sequence in the first feature sequence set and the second feature sequence set, and then calculates each sequence. For example, the color feature calculates the color difference between the two areas, the brightness feature calculates the brightness difference between the two areas, and the contrast feature calculates the contrast difference between the two areas. For example, for a color feature difference sequence, further analysis of the color feature difference sequence can calculate the statistical value of the color feature difference sequence, such as the mean, standard deviation, median and other statistical values, and compare them with the preset threshold. If it is greater than the threshold, the color feature is judged to be true, and if it is lower than or equal to the threshold, the color feature is judged to be false. Then other features are processed in the same way, and finally a vote is made based on the authenticity, and finally the authenticity of the document is output. This method identifies the photosensitive anti-counterfeiting area of ​​the document based on video, extracts the dynamic image features of the photosensitive anti-counterfeiting points of the document, and identifies the features of the photosensitive anti-counterfeiting area of ​​the document by analyzing the dynamic features, thereby effectively improving the accuracy of document authenticity recognition.

[0074] Based on the above method embodiment, the present application embodiment also provides a structural diagram of a video processing device. Figure 5 , is a structural schematic diagram of an image processing device provided in an embodiment of the present application. Figure 5 The video processing device 500 shown can run the following units:

[0075] An acquisition unit 501 is used to acquire a target video and obtain a sequence of image frames to be processed from the target video, wherein the target video is obtained by shooting a document including a light-sensitive anti-counterfeiting area at multiple angles;

[0076] The processing unit 502 is used to extract features from the photosensitive anti-counterfeiting area of ​​each image frame in the sequence of image frames to be processed, and obtain a first feature sequence set corresponding to the photosensitive anti-counterfeiting area of ​​each image frame; extract features from the background area of ​​each image frame in the sequence of image frames to be processed, and obtain a second feature sequence set corresponding to the background area of ​​each image frame;

[0077] A determination unit 503 is used to determine a feature difference sequence set based on the first feature sequence set and the second feature sequence set, wherein the feature difference values ​​in the feature difference sequence set are determined based on the matching feature values ​​in the first feature sequence set and the second feature sequence set; and determine a target authenticity recognition result of the certificate in the target video based on the feature difference sequence set.

[0078] In a possible implementation, the acquisition unit 501 acquires the image frame sequence to be processed from the target video, specifically for:

[0079] Decoding the target video to obtain a decoded image frame sequence;

[0080] Sampling is performed on the decoded image frame sequence, and a to-be-processed image frame sequence is determined according to one or more image frames obtained from the sampling result.

[0081] In a possible implementation, the feature difference sequence set includes one or more feature difference sequences, each feature difference sequence corresponds to the same feature category of each image frame, and different feature difference sequences correspond to different feature categories of each image frame. The determination unit 503 determines the target authenticity recognition result of the certificate in the target video according to the feature difference sequence set, specifically for:

[0082] Determining the authenticity identification parameters of each feature difference sequence included in the feature difference sequence set;

[0083] The target authenticity recognition result of the certificate in the target video is determined according to the authenticity recognition parameters of each feature difference sequence.

[0084] In a possible implementation, the determining unit 503 determines the target authenticity recognition result of the certificate in the target video according to the authenticity recognition parameters of each feature difference sequence, including:

[0085] Determining the reference authenticity recognition result corresponding to each feature category according to the authenticity recognition parameters of each feature difference sequence;

[0086] Determine the number of first feature categories and the number of second feature categories according to the reference authenticity identification results corresponding to the feature categories; the first feature category is a feature category whose corresponding authenticity identification result indicates that the certificate is authentic, and the second feature category is a feature category whose corresponding authenticity identification result indicates that the certificate is fake;

[0087] A target authenticity recognition result of the certificate in the target video is determined according to the number of the first feature categories and the number of the second feature categories.

[0088] In a possible implementation, the determining unit 503 determines the reference authenticity recognition result corresponding to each feature category according to the authenticity recognition parameters of each feature difference sequence, specifically for:

[0089] For a target feature category, if the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is greater than a reference threshold, then the reference authenticity identification result corresponding to the target feature category is determined to be a first identification result, and the first identification result indicates that the certificate is authentic; the target feature category is any one of the one or more feature categories corresponding to each feature difference sequence;

[0090] If the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is less than or equal to the reference threshold, the reference authenticity identification result corresponding to the target feature category is determined to be the second identification result, and the second identification result indicates that the certificate is fake.

[0091] In a possible implementation, the determining unit 503 determines the target authenticity recognition result of the certificate in the target video according to the number of the first feature categories and the number of the second feature categories, specifically for:

[0092] Detecting a magnitude relationship between the number of the first feature category and the number of the second feature category;

[0093] If the number of the first feature categories is greater than the number of the second feature categories, a target authenticity recognition result indicating that the certificate in the target video is authentic is obtained;

[0094] If the number of the first feature categories is less than or equal to the number of the second feature categories, a target authenticity recognition result is obtained for indicating that the certificate in the target video is fake.

[0095] In a possible implementation, the first feature sequence set includes one or more of the following: a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence; the second feature sequence set includes one or more of the following: a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence; the feature difference sequence set includes one or more of the following: a color feature difference sequence, a brightness feature difference sequence, and a contrast feature difference sequence.

[0096] According to one embodiment of the present application, Figure 2 as well as Figure 3 The various steps involved in the video processing method shown can be Figure 5 The video processing device shown in the figure is executed by each unit. For example, Figure 2 In the video processing method shown in FIG. 1 , step S201 can be performed by Figure 5The acquisition unit 501 in the video processing device shown in FIG. 1 is used to perform the steps S202 and S203. Figure 5 The processing unit 502 in the video processing device shown in FIG. 1 is used to perform the steps S204 and S205. Figure 5 The determination unit 503 in the video processing device shown in the figure is executed; for example, Figure 3 In the video processing method shown in FIG. 1 , step S301 can be performed by Figure 5 The acquisition unit 501 in the video processing device shown in FIG. 1 is used to perform the steps S302 to S303. Figure 5 The processing unit 502 in the video processing device shown in FIG. 1 is used to perform the steps S304 to S307. Figure 5 The determination unit 503 in the video processing device shown is executed.

[0097] According to another embodiment of the present application, Figure 5 The various units in the video processing device shown can be respectively or completely merged into one or several other units to constitute, or some of the units (some) can also be split into multiple smaller units in function to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the functions of one unit can also be realized by multiple units, or the functions of multiple units can be realized by one unit. In other embodiments of the present application, other units can also be included based on the video processing device. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0098] According to another embodiment of the present application, the program can be executed by running on a general computing device such as a computer including a central processing unit (CPU), a random access memory medium (RAM), a read-only memory medium (ROM), and other processing elements and storage elements. Figure 2 as well as Figure 3 A computer program (including program code) for each step involved in the corresponding method shown in FIG. Figure 5 The video processing device shown in the embodiment of the present application is used to implement the video processing method of the embodiment of the present application. The computer program can be recorded on a computer-readable storage medium, for example, and loaded into the above-mentioned computing device through the computer-readable storage medium and run therein.

[0099] In an embodiment of the present application, after the acquisition unit 501 acquires the target video obtained by multi-angle shooting of the certificate including the light-sensitive anti-counterfeiting area of ​​the certificate, it processes the target video to obtain a sequence of image frames to be processed; the processing unit 502 then performs feature extraction on the light-sensitive anti-counterfeiting area of ​​the certificate in each image frame in the sequence of image frames to be processed, and performs feature extraction on the background area of ​​the certificate in each image frame in the sequence of image frames to be processed, thereby obtaining a first feature sequence set corresponding to the light-sensitive anti-counterfeiting area of ​​the certificate in each image frame and a second feature sequence set corresponding to the background area of ​​the certificate in each image frame; the determination unit 503 determines each feature difference value in the feature difference sequence set according to the matching feature values ​​in the first feature sequence set and the second feature sequence set, and then obtains the authenticity recognition parameters according to the feature difference sequence set to determine the target authenticity recognition result of the certificate in the target video. Through this method, multiple features of the certificate in the video are dynamically analyzed, thereby effectively improving the accuracy of authenticity recognition of the certificate.

[0100] Based on the above method and device embodiments, the present application embodiment provides a computer device. Figure 6 , is a structural diagram of a computer device provided in an embodiment of the present application. Figure 6 The computer device 600 shown includes at least a processor 601, an input interface 602, an output interface 603, a computer storage medium 604, and a memory 605. The processor 601, the input interface 602, the output interface 603, the computer storage medium 604, and the memory 605 may be connected via a bus or other means.

[0101] The computer storage medium 604 may be stored in the memory 605 of the computer device 600, the computer storage medium 604 is used to store a computer program, the computer program includes program instructions, and the processor 601 is used to execute the program instructions stored in the computer storage medium 604. The processor 601 (or CPU (Central Processing Unit)) is the computing core and control core of the computer device 600, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more computer instructions to implement the corresponding method flow or corresponding function.

[0102] The embodiment of the present application also provides a computer storage medium (Memory), which is a memory device in the computer device 600 for storing programs and data. It is understandable that the computer storage medium here can include both the built-in storage medium in the computer device 600 and the extended storage medium supported by the computer device 600. The computer storage medium provides a storage space, which stores the operating system of the computer device 600. In addition, one or more computer programs (including program codes) suitable for being loaded and executed by the processor 601 are also stored in the storage space. It should be noted that the computer storage medium here can be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk storage; optionally, it can also be at least one computer storage medium located away from the aforementioned processor.

[0103] In one embodiment, the computer storage medium can be loaded by the processor 601 and execute one or more computer programs stored in the computer storage medium to implement the above-mentioned Figure 2 as well as Figure 3 In a specific implementation, one or more instructions in the computer storage medium are loaded by the processor 601 and execute the following steps:

[0104] Acquire a target video, and acquire a sequence of image frames to be processed from the target video, wherein the target video is obtained by shooting a certificate including a light-sensitive anti-counterfeiting area at multiple angles;

[0105] Extracting features of the photosensitive anti-counterfeiting area of ​​each image frame in the sequence of image frames to be processed, respectively, to obtain a first feature sequence set corresponding to the photosensitive anti-counterfeiting area of ​​each image frame;

[0106] Extracting features of the document background region of each image frame in the sequence of image frames to be processed respectively, and obtaining a second feature sequence set corresponding to the document background region of each image frame;

[0107] Determine a feature difference sequence set according to the first feature sequence set and the second feature sequence set, wherein the feature difference values ​​in the feature difference sequence set are determined according to the matching feature values ​​in the first feature sequence set and the second feature sequence set;

[0108] The target authenticity recognition result of the certificate in the target video is determined according to the feature difference sequence set.

[0109] In a possible implementation, the processor 601 obtains a sequence of image frames to be processed from the target video, specifically for:

[0110] Decoding the target video to obtain a decoded image frame sequence;

[0111] Sampling is performed on the decoded image frame sequence, and a to-be-processed image frame sequence is determined according to one or more image frames obtained from the sampling result.

[0112] In a possible implementation, the feature difference sequence set includes one or more feature difference sequences, each feature difference sequence corresponds to the same feature category of each image frame, and different feature difference sequences correspond to different feature categories of each image frame. The processor 601 determines the target authenticity recognition result of the certificate in the target video according to the feature difference sequence set, specifically for:

[0113] Determining the authenticity identification parameters of each feature difference sequence included in the feature difference sequence set;

[0114] The target authenticity recognition result of the certificate in the target video is determined according to the authenticity recognition parameters of each feature difference sequence.

[0115] In a possible implementation, the processor 601 determines the target authenticity recognition result of the certificate in the target video according to the authenticity recognition parameters of each feature difference sequence, specifically for:

[0116] Determining the reference authenticity recognition result corresponding to each feature category according to the authenticity recognition parameters of each feature difference sequence;

[0117] Determine the number of first feature categories and the number of second feature categories according to the reference authenticity identification results corresponding to the feature categories; the first feature category is a feature category whose corresponding authenticity identification result indicates that the certificate is authentic, and the second feature category is a feature category whose corresponding authenticity identification result indicates that the certificate is fake;

[0118] A target authenticity recognition result of the certificate in the target video is determined according to the number of the first feature categories and the number of the second feature categories.

[0119] In a possible implementation, the processor 601 determines the reference authenticity recognition result corresponding to each feature category according to the authenticity recognition parameters of each feature difference sequence, specifically for:

[0120] For a target feature category, if the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is greater than a reference threshold, then the reference authenticity identification result corresponding to the target feature category is determined to be a first identification result, and the first identification result indicates that the certificate is authentic; the target feature category is any one of the one or more feature categories corresponding to each feature difference sequence;

[0121] If the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is less than or equal to the reference threshold, the reference authenticity identification result corresponding to the target feature category is determined to be the second identification result, and the second identification result indicates that the certificate is fake.

[0122] In a possible implementation, the processor 601 determines the target authenticity recognition result of the certificate in the target video according to the number of the first feature categories and the number of the second feature categories, specifically for:

[0123] Detecting a magnitude relationship between the number of the first feature category and the number of the second feature category;

[0124] If the number of the first feature categories is greater than the number of the second feature categories, a target authenticity recognition result indicating that the certificate in the target video is authentic is obtained;

[0125] If the number of the first feature categories is less than or equal to the number of the second feature categories, a target authenticity recognition result is obtained for indicating that the certificate in the target video is fake.

[0126] In a possible implementation, the first feature sequence set includes one or more of the following: a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence; the second feature sequence set includes one or more of the following: a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence; the feature difference sequence set includes one or more of the following: a color feature difference sequence, a brightness feature difference sequence, and a contrast feature difference sequence.

[0127] In the example of the present application, after the processor 601 of the computer device obtains the target video obtained by multi-angle shooting of the certificate including the light-sensitive anti-counterfeiting area of ​​the certificate, it processes the target video to obtain a sequence of image frames to be processed; then, feature extraction is performed on the light-sensitive anti-counterfeiting area of ​​the certificate of each image frame in the sequence of image frames to be processed, and feature extraction is performed on the background area of ​​the certificate of each image frame in the sequence of image frames to be processed, so as to obtain a first feature sequence set corresponding to the light-sensitive anti-counterfeiting area of ​​the certificate of each image frame and a second feature sequence set corresponding to the background area of ​​the certificate of each image frame; each feature difference value in the feature difference sequence set is determined according to the matching feature values ​​in the first feature sequence set and the second feature sequence set, and then the authenticity recognition parameters are obtained according to the feature difference sequence set to determine the target authenticity recognition result of the certificate in the target video. Through this method, multiple features of the certificate in the video are dynamically analyzed, thereby effectively improving the accuracy of authenticity recognition of the certificate.

[0128] According to one aspect of the present application, an embodiment of the present application further provides a computer product, the computer product includes a computer program, the computer program is stored in a computer-readable storage medium. The processor 501 reads the computer program from the computer-readable storage medium, and the processor 601 executes the computer program, so that the computer device 600 executes Figure 2 as well as Figure 3 The video processing method shown.

[0129] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0130] In the several embodiments provided in this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, and the division of the modules described above is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed.

[0131] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A video processing method, characterized in that: The method comprises: Acquire a target video, and acquire a sequence of image frames to be processed from the target video, wherein the target video is obtained by shooting a certificate including a light-sensitive anti-counterfeiting area at multiple angles; Extracting features of the photosensitive anti-counterfeiting area of ​​each image frame in the sequence of image frames to be processed, respectively, to obtain a first feature sequence set corresponding to the photosensitive anti-counterfeiting area of ​​each image frame; Extracting features of the document background region of each image frame in the sequence of image frames to be processed respectively, and obtaining a second feature sequence set corresponding to the document background region of each image frame; Determine a feature difference sequence set according to the first feature sequence set and the second feature sequence set, wherein the feature difference values ​​in the feature difference sequence set are determined according to the matching feature values ​​in the first feature sequence set and the second feature sequence set; the feature difference sequence set includes one or more feature difference sequences, each feature difference sequence corresponds to the same feature category of each of the image frames, and different feature difference sequences correspond to different feature categories of each of the image frames; Determining the authenticity identification parameters of each feature difference sequence included in the feature difference sequence set; Determine the reference authenticity identification results corresponding to each feature category according to the authenticity identification parameters of each feature difference sequence; determine the number of first feature categories and the number of second feature categories according to the reference authenticity identification results corresponding to each feature category; the first feature category is a feature category whose corresponding authenticity identification result indicates that the certificate is authentic, and the second feature category is a feature category whose corresponding authenticity identification result indicates that the certificate is fake; A target authenticity recognition result of the certificate in the target video is determined according to the number of the first feature categories and the number of the second feature categories.

2. The method according to claim 1, characterized in that The step of obtaining a sequence of image frames to be processed from the target video includes: Decoding the target video to obtain a decoded image frame sequence; Sampling is performed on the decoded image frame sequence, and a to-be-processed image frame sequence is determined according to one or more image frames obtained from the sampling result.

3. The method according to claim 1, characterized in that Determining the reference authenticity recognition result corresponding to each feature category according to the authenticity recognition parameters of each feature difference sequence includes: For a target feature category, if the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is greater than a reference threshold, then the reference authenticity identification result corresponding to the target feature category is determined to be a first identification result, and the first identification result indicates that the certificate is authentic; the target feature category is any one of the one or more feature categories corresponding to each feature difference sequence; If the authenticity identification parameter of the feature difference sequence corresponding to the target feature category is less than or equal to the reference threshold, the reference authenticity identification result corresponding to the target feature category is determined to be the second identification result, and the second identification result indicates that the certificate is fake.

4. The method according to claim 1, characterized in that: The determining the target authenticity recognition result of the certificate in the target video according to the number of the first feature categories and the number of the second feature categories includes: Detecting a magnitude relationship between the number of the first feature category and the number of the second feature category; If the number of the first feature categories is greater than the number of the second feature categories, a target authenticity recognition result indicating that the certificate in the target video is authentic is obtained; If the number of the first feature categories is less than or equal to the number of the second feature categories, a target authenticity recognition result is obtained for indicating that the certificate in the target video is fake.

5. The method according to any one of claims 1 to 4, characterized in that: The first feature sequence set includes one or more of the following: a first color feature sequence, a first brightness feature sequence, and a first contrast feature sequence; the second feature sequence set includes one or more of the following: a second color feature sequence, a second brightness feature sequence, and a second contrast feature sequence; the feature difference sequence set includes one or more of the following: a color feature difference sequence, a brightness feature difference sequence, and a contrast feature difference sequence.

6. A video processing device, characterized in that: The device comprises: An acquisition unit, used to acquire a target video and obtain a sequence of image frames to be processed from the target video, wherein the target video is obtained by shooting a certificate including a light-sensitive anti-counterfeiting area at multiple angles; A processing unit is used to extract features from the photosensitive anti-counterfeiting area of ​​the certificate of each image frame in the sequence of image frames to be processed, and obtain a first feature sequence set corresponding to the photosensitive anti-counterfeiting area of ​​the certificate of each image frame; extract features from the background area of ​​the certificate of each image frame in the sequence of image frames to be processed, and obtain a second feature sequence set corresponding to the background area of ​​the certificate of each image frame; a determining unit, configured to determine a feature difference sequence set according to the first feature sequence set and the second feature sequence set, wherein the feature difference values ​​in the feature difference sequence set are determined according to the matching feature values ​​in the first feature sequence set and the second feature sequence set; the feature difference sequence set includes one or more feature difference sequences, each feature difference sequence corresponds to the same feature category of each of the image frames, and different feature difference sequences correspond to different feature categories of each of the image frames; The determination unit is also used to: determine the authenticity identification parameters of each feature difference sequence included in the feature difference sequence set; determine the reference authenticity identification results corresponding to each feature category according to the authenticity identification parameters of each feature difference sequence; determine the number of first feature categories according to the reference authenticity identification results corresponding to each feature category, and determine the number of second feature categories; the first feature category is a feature category whose corresponding authenticity identification result indicates that the certificate is authentic, and the second feature category is a feature category whose corresponding authenticity identification result indicates that the certificate is fake; determine the target authenticity identification result of the certificate in the target video according to the number of the first feature categories and the number of the second feature categories.

7. A computer device, characterized in that: Including an input interface and an output interface, the computer device also includes: a processor adapted to implement one or more computer programs; and, A computer storage medium storing one or more computer programs, wherein the one or more computer programs are suitable for being loaded by the processor and executing the video processing method according to any one of claims 1 to 5.

8. A computer storage medium, characterized in that: The computer storage medium stores one or more computer programs, and the one or more computer programs are suitable for being loaded by a processor and executing the video processing method according to any one of claims 1 to 5.

9. A computer program product, characterized in that The computer program product comprises a computer program, wherein the computer program is stored in a computer-readable storage medium, a processor reads the computer program from the computer-readable storage medium, and the processor executes the computer program to perform the video processing method according to any one of claims 1 to 5.

Images