Object authenticity identification method and device, storage medium and electronic equipment

Abstract

The present disclosure relates to an object authenticity identification method, an object authenticity identification device, a storage medium and an electronic device. The object authenticity identification method comprises: acquiring shooting data of an object to be identified collected by a shooting device at different shooting distances; wherein the shooting data comprises picture data and / or video data; determining image information corresponding to each shooting distance according to the shooting data; performing authenticity identification on the image information corresponding to each shooting distance by using a classifier corresponding to each shooting distance, to obtain authenticity identification results corresponding to each shooting distance; and obtaining a final authenticity identification result of the object to be identified according to the authenticity identification results corresponding to each shooting distance. The object authenticity identification method can solve the problems of low accuracy and poor user experience in authenticity identification.

Description

Technical Field

[0001] This disclosure relates to the field of data processing, specifically to a method, device, storage medium, and electronic device for identifying the authenticity of objects. Background Technology

[0002] Document authentication refers to distinguishing genuine documents from counterfeit documents, such as paper prints of various materials and documents reproduced from screens.

[0003] Existing technologies can identify anti-counterfeiting features by detecting dynamic and static anti-counterfeiting points in multiple images of the target document. However, this requires rotating the document, resulting in a poor user experience, and at larger angles, the document may not be detected. Another method involves acquiring at least two images under different acquisition conditions, such as different types of light sources, light sources of different intensities, and different shooting angles, and identifying anti-counterfeiting marks from these images to obtain anti-counterfeiting features for identification. However, the acquisition conditions are mainly controlled by the external environment and are easily interfered with by external light sources.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] The purpose of this disclosure is to provide a method, device, storage medium, and electronic device for identifying the authenticity of objects, aiming to solve the problems of low accuracy and poor user experience in authenticity identification.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to one aspect of the present disclosure, a method for object authenticity identification is provided, comprising: acquiring shooting data of an object to be identified collected by a shooting device at different shooting distances; wherein the shooting data includes image data and / or video data; determining image information corresponding to each shooting distance based on the shooting data; performing authenticity identification on the image information using classifiers corresponding to each shooting distance to obtain authenticity identification results corresponding to each shooting distance; and obtaining the final authenticity identification result of the object to be identified based on the authenticity identification results corresponding to each shooting distance.

[0008] According to some embodiments of this disclosure, based on the foregoing scheme, the method further includes: configuring at least two shooting distances of the shooting device; configuring shooting prompt information corresponding to each shooting distance in the user interface of the shooting device, so as to obtain the shooting data based on the shooting prompt information.

[0009] According to some embodiments of this disclosure, based on the foregoing scheme, when the captured data is image data, the step of acquiring the captured data of the object to be identified collected by the shooting device at different shooting distances includes: the user interface displays shooting prompt information corresponding to a shooting distance; when the object to be identified is detected to meet the collection conditions of the shooting distance, a shooting operation is performed to collect image data corresponding to the shooting distance; the user interface displays shooting prompt information corresponding to the next shooting distance; the above display, detection and execution process is repeated until the image data corresponding to all shooting distances is obtained.

[0010] According to some embodiments of this disclosure, based on the foregoing scheme, when the captured data is video data, the step of acquiring the captured data of the object to be identified collected by the shooting device at different shooting distances includes: in response to a touch operation on the start recording button in the user interface, starting video recording and displaying a shooting prompt message corresponding to a shooting distance in the user interface; when it is detected that the object to be identified meets the acquisition condition of the shooting distance, the user interface displays a shooting prompt message corresponding to the next shooting distance; repeating the above display and detection process until in response to a touch operation on the end recording button in the user interface, ending video recording and obtaining the video data.

[0011] According to some embodiments of this disclosure, based on the foregoing scheme, determining the image information corresponding to each of the shooting distances based on the shooting data includes: extracting video keyframes corresponding to each of the shooting distances in the video data as the image information.

[0012] According to some embodiments of this disclosure, based on the foregoing scheme, when the captured data is image data and video data, the step of acquiring the captured data of the object to be identified by the shooting device at different shooting distances includes: in response to a touch operation on the start recording button in the user interface, starting video recording and displaying a shooting prompt message corresponding to a shooting distance in the user interface; when it is detected that the object to be identified meets the acquisition condition of the shooting distance, performing a shooting operation to acquire image data corresponding to the shooting distance; the user interface displays a shooting prompt message corresponding to the next shooting distance; repeating the above display, detection and execution process until in response to a touch operation on the end recording button in the user interface, ending video recording and obtaining the video data.

[0013] According to some embodiments of this disclosure, based on the foregoing scheme, the method further includes: using a classifier corresponding to a shooting distance to perform authenticity identification on the image information corresponding to the shooting distance, and obtaining the authenticity identification result corresponding to the shooting distance; the step of using a classifier corresponding to a shooting distance to perform authenticity identification on the image information corresponding to the shooting distance, and obtaining the authenticity identification result corresponding to the shooting distance, includes: inputting the image information into the classifier to obtain the authenticity prediction value output by the classifier; comparing the authenticity prediction value with a threshold corresponding to the classifier to obtain a comparison result; and determining the authenticity identification result based on the comparison result.

[0014] According to some embodiments of this disclosure, based on the foregoing scheme, the method further includes: extracting data features based on sample data corresponding to the shooting distance; and training a model based on the data features to obtain the classifier and the threshold corresponding to the classifier.

[0015] According to some embodiments of this disclosure, based on the foregoing scheme, the method further includes: at a first shooting distance, the data features include edge region features; at a second shooting distance, the data features include one or more of screen reflection features, paper embossing features, and material features; at a third shooting distance, the data features include anti-counterfeiting features.

[0016] According to some embodiments of this disclosure, based on the foregoing scheme, obtaining the final authenticity identification result of the object to be identified based on the authenticity identification results corresponding to each of the shooting distances includes: determining the weight information corresponding to each of the shooting distances based on a pre-trained weight model; and calculating the final authenticity identification result based on the weight information and the authenticity identification results.

[0017] According to some embodiments of this disclosure, based on the foregoing scheme, obtaining the final authenticity identification result of the object to be identified based on the authenticity identification results corresponding to each of the shooting distances includes: performing logical judgment on the authenticity identification results corresponding to each of the shooting distances to obtain the final authenticity identification result.

[0018] According to some embodiments of this disclosure, based on the foregoing scheme, obtaining the final authenticity identification result of the object to be identified based on the authenticity identification results corresponding to each of the shooting distances includes: calculating the confidence value corresponding to each of the shooting distances based on the authenticity identification results corresponding to each of the shooting distances and the threshold; and taking the authenticity identification result corresponding to the maximum confidence value as the final authenticity identification result.

[0019] According to a second aspect of the present disclosure, an object authenticity recognition device is provided, comprising: an acquisition module for acquiring shooting data of an object to be identified collected by a shooting device at different shooting distances; a determination module for determining image information corresponding to each shooting distance based on the shooting data; a classification recognition module for performing authenticity recognition on the image information using a classifier corresponding to each shooting distance to obtain authenticity recognition results corresponding to each shooting distance; and an overall recognition module for obtaining the final authenticity recognition result of the object to be identified based on the authenticity recognition results corresponding to each shooting distance.

[0020] According to a third aspect of the present disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the object authenticity recognition method as described in the above embodiments.

[0021] According to a fourth aspect of the present disclosure, an electronic device is provided, characterized in that it includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the object authenticity recognition method as described in the above embodiments.

[0022] The exemplary embodiments disclosed herein may have some or all of the following beneficial effects:

[0023] In some embodiments of this disclosure, the object to be identified is stationary. By moving the shooting device to different shooting distances, shooting data of the object to be identified is obtained at different shooting distances. Then, for each shooting distance, the corresponding classifier is used to perform authenticity identification on the image information. Finally, the authenticity identification results obtained from all shooting distances are fused to obtain the final authenticity identification result. Through this method, on the one hand, the shooting conditions remain constant; only the shooting device is moved to different shooting distances. Compared to moving or rotating the object to be identified, or creating different types and intensities of light sources, the shooting process is relatively simple and provides a high user experience. On the other hand, it supports authenticity identification of the object to be identified in the form of video data, which can capture the entire shooting process, prevent replacement of the object to be identified, and prevent HOOK attacks, making authenticity identification more stable.

[0024] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0025] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0026] Figure 1 The schematic diagram illustrates a flowchart of an object authenticity identification method according to an exemplary embodiment of the present disclosure;

[0027] Figure 2 This schematic diagram illustrates an interface for providing a shooting prompt message in an exemplary embodiment of the present disclosure;

[0028] Figure 3 This schematic diagram illustrates another interface for shooting prompts in an exemplary embodiment of the present disclosure;

[0029] Figure 4 This schematic diagram illustrates another interface for a shooting prompt message in an exemplary embodiment of the present disclosure;

[0030] Figure 5 The illustration shows a flowchart of a method for acquiring shooting data in an exemplary embodiment of the present disclosure;

[0031] Figure 6 This schematic diagram illustrates the composition of an object authenticity identification device according to an exemplary embodiment of the present disclosure;

[0032] Figure 7 This schematic diagram illustrates a computer-readable storage medium according to an exemplary embodiment of the present disclosure;

[0033] Figure 8 The schematic diagram illustrates the structure of a computer system of an electronic device according to an exemplary embodiment of the present disclosure. Detailed Implementation

[0034] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art.

[0035] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0036] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0037] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0038] In real life, it is often necessary to identify the authenticity of an item, such as document authentication, which means distinguishing genuine documents from counterfeit ones. Counterfeit documents include paper printouts of various materials and documents reproduced from screens.

[0039] Taking document authenticity verification as an example, one existing technology identifies documents by detecting dynamic and static anti-counterfeiting points in multiple images of the target document. These multiple images are captured from different angles. During document verification, the document needs to be rotated, resulting in a poor user experience. Furthermore, at larger angles, the document may fail to be detected.

[0040] Another method involves capturing at least two images under different acquisition conditions (different types of light sources, different intensities of light sources, and different shooting angles), identifying anti-counterfeiting marks from these images, and obtaining anti-counterfeiting features for identification. The different types and intensities of light sources are mainly controlled by the external environment or the flash of the shooting equipment. Because this method is related to the light source, it is easily interfered with by external light sources, such as artificial lighting.

[0041] Therefore, in view of the shortcomings of the existing technology, this disclosure provides a method for object authenticity recognition, which only moves the shooting device to change the distance between the shooting device and the object to be identified, and obtains the shooting data during the entire movement process for authenticity recognition, which improves the user experience while ensuring high accuracy.

[0042] The implementation details of the technical solutions of the embodiments of this disclosure are described in detail below.

[0043] Figure 1 This illustration schematically depicts a flowchart of an object authenticity identification method according to an exemplary embodiment of this disclosure. For example... Figure 1 As shown, the object authenticity identification method includes steps S101 to S104:

[0044] Step S101: Acquire shooting data of the object to be identified by the shooting device at different shooting distances; wherein, the shooting data includes image data and / or video data;

[0045] Step S102: Determine the image information corresponding to each of the shooting distances based on the shooting data;

[0046] Step S103: Use the classifiers corresponding to each shooting distance to perform authenticity identification on the image information, and obtain the authenticity identification results corresponding to each shooting distance;

[0047] Step S104: Based on the authenticity recognition results corresponding to each shooting distance, the final authenticity recognition result of the object to be identified is obtained.

[0048] In some embodiments of this disclosure, the object to be identified is stationary. By moving the shooting device to different shooting distances, shooting data of the object to be identified is obtained at different shooting distances. Then, for each shooting distance, the corresponding classifier is used to perform authenticity identification on the image information. Finally, the authenticity identification results obtained from all shooting distances are fused to obtain the final authenticity identification result. Through this method, on the one hand, the shooting conditions remain constant; only the shooting device is moved to different shooting distances. Compared to moving or rotating the object to be identified, or creating different types and intensities of light sources, the shooting process is relatively simple and provides a high user experience. On the other hand, it supports authenticity identification of the object to be identified in the form of video data, which can capture the entire shooting process, prevent replacement of the object to be identified, and prevent HOOK attacks, making authenticity identification more stable.

[0049] The following will describe in more detail each step of the object authenticity identification method in this example embodiment, with reference to the accompanying drawings and embodiments.

[0050] In step S101, the shooting data of the object to be identified collected by the shooting device at different shooting distances is obtained; wherein, the shooting data includes image data and / or video data.

[0051] Among them, the shooting device refers to the device used to collect shooting data of the object to be identified. Generally speaking, the shooting device is a mobile device, such as a mobile phone or a handheld PDA (Personal Digital Assistant), or it can be a mobile collection part of a fixed device, such as a mobile camera connected to a PC (Personal Computer).

[0052] The object to be identified is an item whose authenticity needs to be verified, such as documents, paper, or artwork.

[0053] Capture data refers to data collected using a camera, including the object to be identified. This can include image data, video data, or both. It's important to note that the capture data must include data collected by the camera at different shooting distances; that is, the camera must collect data from at least two different shooting distances.

[0054] In one embodiment of this disclosure, in order to facilitate the user to move the shooting device to different shooting distances, corresponding shooting prompts can be displayed in the user interface corresponding to the shooting device.

[0055] Therefore, the method further includes: configuring at least two shooting distances of the shooting device; configuring shooting prompt information corresponding to each shooting distance in the user interface of the shooting device, so as to obtain the shooting data based on the shooting prompt information.

[0056] Specifically, first, you need to set which shooting distances you want to collect data from. For example, you can collect data at a first distance that is relatively far away and a second distance that is relatively close, or you can set it to collect data at a first distance that is relatively far away, a second distance that is relatively close, and a third distance that is closest. In actual operation, you can set it as needed, and this disclosure does not make any specific limitations here.

[0057] After configuring the shooting distance, corresponding shooting prompts need to be configured for each shooting distance. Specifically, the edge lines of the object to be identified can be displayed in the user interface of the shooting device to prompt the user to move the device until the object to be identified is aligned with the edge lines.

[0058] Figure 2 This schematic diagram illustrates an interface for providing a shooting prompt message in an exemplary embodiment of this disclosure, with reference to... Figure 2 As shown, in the user interface 201, the object to be identified should be placed in area 202.

[0059] Figure 3This schematic diagram illustrates another interface diagram for shooting prompts in an exemplary embodiment of the present disclosure, with reference to... Figure 3 As shown, in the user interface 301, the object to be identified should be placed in area 302.

[0060] Figure 4 This schematic diagram illustrates another interface diagram for providing a shooting prompt message in an exemplary embodiment of the present disclosure, with reference to... Figure 4 As shown, in the user interface 401, the object to be identified should be placed in area 402.

[0061] By comparison Figures 2 to 4 As can be seen, the farther the shooting distance, the smaller the target object to be identified in the shooting prompt information becomes.

[0062] In one embodiment of this disclosure, when the captured data can be image data, the step of acquiring the captured data of the object to be identified collected by the capturing device at different capturing distances includes:

[0063] Step 1: The user interface displays a shooting prompt message corresponding to a shooting distance;

[0064] Step 2: When the object to be identified is detected to meet the acquisition conditions of the shooting distance, a shooting operation is performed to acquire the image data corresponding to the shooting distance;

[0065] Step 3: The user interface displays shooting prompts for the next shooting distance;

[0066] Step four: Repeat the above display, detection, and execution process until the image data corresponding to all the shooting distances is obtained.

[0067] Based on the above scheme, a shooting prompt message corresponding to a shooting distance is displayed in the user interface. At this time, the user can move the shooting device according to the shooting prompt message to check whether the collection conditions are met.

[0068] For example, the acquisition condition could be that the edge contour of the object to be identified matches the edge contour of the placement area in the shooting prompt information. For instance, a matching value greater than 0.8 is considered a match. Of course, the acquisition condition can also be other information, such as detecting that the occupied area of ​​the captured object to be identified meets a certain ratio, or detecting a pattern with a certain size. In this case, it can be determined that the acquisition condition is met, and the shooting device can be considered to have moved to a certain shooting distance from the object to be identified, thus enabling the acquisition of shooting data.

[0069] Once the acquisition conditions are met, a shooting operation can be performed to collect image data. After acquisition, the above process is repeated to obtain image data corresponding to all shooting distances. In this way, a set of multiple images is obtained as the acquisition data for the object to be identified.

[0070] Of course, to ensure the accuracy of the captured data, the captured images can also be checked for blurriness, obstruction, etc. If such issues are found, a shooting prompt message corresponding to the shooting distance will be displayed to allow the image to be taken again.

[0071] In one embodiment of this disclosure, the captured data may also be video data. The step of acquiring captured data of the object to be identified by the capturing device at different capturing distances includes:

[0072] Step 1: In response to a touch operation on the start recording button in the user interface, start video recording and display a shooting prompt message corresponding to a shooting distance in the user interface.

[0073] Step 2: When the object to be identified is detected to meet the acquisition conditions of the shooting distance, the user interface displays the shooting prompt information corresponding to the next shooting distance;

[0074] Step 3: Repeat the above display and detection process until the video recording ends and the video data is obtained in response to a touch operation on the end recording button in the user interface.

[0075] The above methods are similar to those for capturing image data. Both require displaying shooting prompts in the user interface and detecting whether the object to be identified meets the shooting distance acquisition conditions. Therefore, they will not be elaborated on here.

[0076] Unlike image data, since video data is being collected, it needs to respond to touch operations such as starting the recording button to begin recording and stopping the recording by responding to touch operations such as stopping the recording button.

[0077] In addition, when the object to be identified is detected to meet the acquisition conditions, since the image at that moment has already been recorded in the video, the shooting operation can be skipped, and the process can directly proceed to the stage of acquiring shooting data for the next shooting distance.

[0078] In one embodiment of this disclosure, the captured data can also be image data and video data. The acquisition of captured data of the object to be identified by the capturing device at different shooting distances includes:

[0079] Step 1: In response to a touch operation on the start recording button in the user interface, start video recording and display a shooting prompt message corresponding to a shooting distance in the user interface.

[0080] Step 2: When the object to be identified is detected to meet the acquisition conditions of the shooting distance, a shooting operation is performed to acquire the image data corresponding to the shooting distance;

[0081] Step 3: The user interface displays shooting prompts for the next shooting distance;

[0082] Step four: Repeat the above display, detection and execution process until the video recording ends and the video data is obtained in response to a touch operation on the end recording button in the user interface.

[0083] The method described above combines the two approaches, meaning that during video recording, when the acquisition conditions are met, a shooting operation is also performed simultaneously. For details, please refer to the previous method description; further elaboration will not be provided here.

[0084] To ensure higher accuracy in the captured data, some additional operations can be added. For example, when the capture conditions are met, a "Stay still for 2 seconds" prompt can be displayed on the user interface. After the waiting time is satisfied, a shooting prompt for the next shooting distance can be displayed.

[0085] Based on the above method, the authenticity of the object to be identified is determined by collecting video data. The advantage is that it can capture the entire process of the mobile phone running and reflecting it on the document, preventing document replacement and also preventing HOOK attacks.

[0086] Figure 5 This illustration schematically depicts a flowchart of a method for acquiring captured data according to an exemplary embodiment of this disclosure. (Reference) Figure 5 As shown, in step S501, according to the user interface (UI), the user adjusts the shooting device to the first distance and acquires the corresponding data. Then, in step S502, it is determined whether the conditions for entering the second distance are met, that is, whether the data acquisition at the first distance is completed. If yes, step S503 is executed; otherwise, step S501 is returned. After the conditions for entering the second distance are met in step S503, the UI changes, that is, it provides shooting prompts for the second distance. The user enters the second distance according to the prompts and acquires the corresponding data. Then, step S504 is executed to determine whether the data processing for the second distance is completed. If yes, step S505 is executed, and the data acquisition ends; otherwise, it jumps to step S503 to acquire the corresponding data for the second distance again.

[0087] In step S102, image information corresponding to each shooting distance is determined based on the shooting data.

[0088] In this disclosure, the methods for determining the image information corresponding to each shooting distance are different depending on the content of the shooting data.

[0089] If the captured data contains image information, then the acquired captured data already contains image information corresponding to multiple shooting distances, and can be directly extracted.

[0090] If the shooting data does not include image information and only contains video data, then it is necessary to extract the video keyframes corresponding to each shooting distance from the video data as image information.

[0091] Therefore, to facilitate the extraction of keyframes from the video, additional operations can be performed during video recording. For example, when the acquisition conditions are met, the recording time can be recorded. Upon completion of recording and obtaining the video data, marker frames can be added to the video based on the recorded recording time. In this way, the corresponding keyframes can be extracted as image information based on the marker frames.

[0092] Of course, the methods for extracting keyframes from a video are not limited to this. We can also analyze the video data frame by frame to determine which frame in the video matches the image of the object to be identified taken at a certain shooting distance, and thus determine the keyframe of the video.

[0093] In step S103, the image information is identified as genuine or fake using classifiers corresponding to each shooting distance, and the identification results corresponding to each shooting distance are obtained.

[0094] In one embodiment of this disclosure, image information corresponding to different shooting distances should be identified as genuine or fake using different classifiers. Therefore, step S103 includes using a classifier corresponding to a shooting distance to identify the genuine or fake image information at the shooting distance, and obtaining a genuine or fake identification result corresponding to the shooting distance. Specifically, the process involves the following steps: inputting the image information into the classifier to obtain a genuine or fake prediction value output by the classifier; comparing the genuine or fake prediction value with a threshold corresponding to the classifier to obtain a comparison result; and determining the genuine or fake identification result based on the comparison result.

[0095] In other words, for a given shooting distance, the image information corresponding to that shooting distance is input into a classifier corresponding to that shooting distance to obtain a true / false prediction value. Then, the true / false prediction value of the classifier is compared with the classifier's threshold. If the true / false prediction value is greater than or equal to the threshold, the classifier's result can be considered as "the object to be identified is true"; conversely, if the true / false prediction value is less than the threshold, the classifier's result can be considered as "the object to be identified is false".

[0096] In one embodiment of this disclosure, the method further includes: extracting data features based on sample data corresponding to the shooting distance; and training a model based on the data features to obtain the classifier and the threshold corresponding to the classifier.

[0097] In other words, multiple models are trained in advance to obtain classifiers corresponding to different shooting distances, and then these classifiers are used for recognition. It should be noted that the classifiers here still have a one-to-one correspondence with different shooting distances.

[0098] For example, classifiers can be configured for three different shooting distances: a first distance (farther), a second distance (closer), and a third distance (closest). The corresponding data features will differ accordingly. At the first shooting distance, the data features include edge region features; at the second shooting distance, the data features include one or more of the following: screen reflection features, paper embossing features, and material features; and at the third shooting distance, the data features include anti-counterfeiting features.

[0099] At greater distances, the acquired images not only contain the full picture of the object to be identified but also some background information. Therefore, many object edge regions, screen edge regions, or other discriminative features can be discovered. Using these edge region features, a classifier with high robustness and generalization ability can be trained.

[0100] At close range, the acquired image should include the entire area of ​​the object to be identified, while minimizing the inclusion of background areas. This ensures the integrity of the object while still capturing detailed information. The reflective surface of the screen, the texture of the paper, or other material characteristics can be used to distinguish the captured image.

[0101] At the closest distance, the acquired image represents a unique local region of the object to be identified. This region possesses certain special characteristics and also serves as an anti-counterfeiting feature. Extracting the anti-counterfeiting features from a high-resolution image containing this region allows for the training of a high-precision classifier.

[0102] Of course, the types of classifiers can also be adjusted according to the number of shooting distances set. For example, it is possible to train only a classifier that recognizes the first distance between the background and the object to be recognized, and a classifier that recognizes the complete features of the object to be recognized at the second distance. In this case, there is no need to set a third distance. In this way, only the true and false recognition results at two shooting distances need to be processed, reducing the amount of data transmitted and processed, and improving the efficiency of true and false recognition.

[0103] In step S104, the final authenticity identification result of the object to be identified is obtained based on the authenticity identification results corresponding to each shooting distance.

[0104] Specifically, in step S103, the authenticity recognition result corresponding to each shooting distance can be obtained. At this time, it is necessary to perform a result fusion on all the authenticity recognition results to obtain a final authenticity recognition result.

[0105] There are many ways to fuse data. In one embodiment of this disclosure, step S104 may include: determining the weight information corresponding to each of the shooting distances based on a pre-trained weight model; and calculating the final authenticity recognition result based on the weight information and the authenticity recognition result.

[0106] In other words, a corresponding weight value is assigned to the authenticity recognition result for each shooting distance. Then, the authenticity prediction values ​​obtained by each classifier and the weight value are weighted and summed. Finally, the weighted sum is compared with the overall threshold. If it is greater than or equal to the configured overall threshold, the final authenticity recognition result is "the object to be identified is true". Otherwise, the final authenticity recognition result is "the object to be identified is false".

[0107] In one embodiment of this disclosure, step S104 may further include: performing logical judgment on the authenticity identification results corresponding to each of the shooting distances to obtain the final authenticity identification result.

[0108] Specifically, if any of the authenticity identification results is "the object to be identified is false", then the final authenticity identification result is "the object to be identified is false". If all the authenticity identification results are "the object to be identified is true", then the final authenticity identification result is "the object to be identified is true".

[0109] In one embodiment of this disclosure, step S104 may further include: calculating a confidence value corresponding to each shooting distance based on the authenticity recognition result corresponding to each shooting distance and the threshold; and taking the authenticity recognition result corresponding to the maximum confidence value as the final authenticity recognition result.

[0110] In other words, by calculating a confidence value, the authenticity verification result corresponding to the maximum confidence value is taken as the final authenticity verification result. Specifically, when calculating the confidence value p corresponding to a certain shooting distance:

[0111] When y is to the left of the threshold, formula (1) is shown:

[0112]

[0113] Where y is the true / false prediction value, and a is the threshold of the classifier.

[0114] When y is to the right of the threshold, as shown in formula (2):

[0115]

[0116] Where y is the true / false prediction value, and a is the threshold of the classifier.

[0117] In step S104, the true / false identification results output by each classifier are fused according to the actual situation, and the final true / false identification result is output. Therefore, the true / false identification results can be fused according to classifiers with different distance settings, which will result in a higher accuracy rate compared to a single true / false judgment.

[0118] Based on the above method, on the one hand, it eliminates the need to move the object to be identified during shooting; only the shooting device is moved to change the distance between the shooting device and the object to be identified to collect shooting data, avoiding operations such as object rotation and changing the shooting light source. At the same time, corresponding shooting prompts are displayed on the user interface, making the authenticity identification operation simpler and improving the user experience. On the other hand, it supports the authenticity identification of the object to be identified in the form of video data, which can capture the entire shooting process, prevent the replacement of the object to be identified, and prevent HOOK attacks, making the authenticity identification more stable. Furthermore, by combining the authenticity identification results obtained from different shooting distances, the accuracy of authenticity identification can be improved.

[0119] Figure 6 This schematic diagram illustrates the composition of an object authenticity identification device according to an exemplary embodiment of the present disclosure, such as... Figure 6 As shown, the object authenticity identification device 600 may include an acquisition module 601, a determination module 602, a classification identification module 603, and an overall identification module 604. Wherein:

[0120] The acquisition module 601 is used to acquire the shooting data of the object to be identified collected by the shooting device at different shooting distances;

[0121] The determining module 602 is used to determine the image information corresponding to each of the shooting distances based on the shooting data;

[0122] The classification and recognition module 603 is used to perform authenticity recognition on the image information using classifiers corresponding to each of the shooting distances, and to obtain authenticity recognition results corresponding to each of the shooting distances.

[0123] The overall recognition module 604 is used to obtain the final authenticity recognition result of the object to be identified based on the authenticity recognition results corresponding to each of the shooting distances.

[0124] According to an exemplary embodiment of this disclosure, the object authenticity identification device 600 further includes a prompting module, configured to configure at least two shooting distances of the shooting device; and to configure shooting prompt information corresponding to each shooting distance in the user interface of the shooting device, so as to obtain the shooting data based on the shooting prompt information.

[0125] According to an exemplary embodiment of this disclosure, when the captured data is image data, the acquisition module 601 is used to display a shooting prompt message corresponding to a shooting distance on the user interface; when it is detected that the object to be identified meets the acquisition condition of the shooting distance, a shooting operation is performed to acquire image data corresponding to the shooting distance; the user interface displays a shooting prompt message corresponding to the next shooting distance; the above display, detection and execution process is repeated until all the image data corresponding to the shooting distance are obtained.

[0126] According to an exemplary embodiment of this disclosure, when the captured data is video data, the acquisition module 601 is configured to start video recording in response to a touch operation on the start recording button in the user interface, and display a shooting prompt message corresponding to a shooting distance in the user interface; when it is detected that the object to be identified meets the acquisition condition of the shooting distance, the user interface displays a shooting prompt message corresponding to the next shooting distance; the above display and detection process is repeated until the video recording ends and the video data is obtained in response to a touch operation on the end recording button in the user interface.

[0127] According to an exemplary embodiment of this disclosure, when the captured data is video data, the determining module 602 is used to extract video keyframes corresponding to each captured distance in the video data as the image information.

[0128] According to an exemplary embodiment of this disclosure, when the captured data is image data and video data, the acquisition module 601 is configured to start video recording in response to a touch operation on the start recording button in the user interface, and display a shooting prompt message corresponding to a shooting distance in the user interface; when it is detected that the object to be identified meets the acquisition condition of the shooting distance, a shooting operation is performed to acquire image data corresponding to the shooting distance; the user interface displays a shooting prompt message corresponding to the next shooting distance; the above display, detection and execution process is repeated until the video recording ends and the video data is obtained in response to a touch operation on the end recording button in the user interface.

[0129] According to an exemplary embodiment of this disclosure, the classification and recognition module 603 is used to perform authenticity recognition on image information corresponding to the shooting distance using a classifier corresponding to the shooting distance, and obtain an authenticity recognition result corresponding to the shooting distance; including: inputting the image information into the classifier to obtain the authenticity prediction value output by the classifier; comparing the authenticity prediction value with a threshold corresponding to the classifier to obtain a comparison result; and determining the authenticity recognition result based on the comparison result.

[0130] According to an exemplary embodiment of this disclosure, the classification and recognition module 603 further includes a training unit, which is used to extract data features based on sample data corresponding to the shooting distance; and to train a model based on the data features to obtain the classifier and the threshold corresponding to the classifier.

[0131] According to an exemplary embodiment of this disclosure, when the shooting distance is a first distance, the data feature includes edge region features; when the shooting distance is a second distance, the data feature includes one or more of screen reflection features, paper embossing features, and material features; when the shooting distance is a third distance, the data feature includes anti-counterfeiting features.

[0132] According to an exemplary embodiment of this disclosure, the overall recognition module 604 is used to determine the weight information corresponding to each of the shooting distances based on a pre-trained weight model; and to calculate the final authenticity recognition result based on each of the weight information and each of the authenticity recognition results.

[0133] According to an exemplary embodiment of this disclosure, the overall identification module 604 is used to perform logical judgment on the authenticity identification results corresponding to each of the shooting distances to obtain the final authenticity identification result.

[0134] According to an exemplary embodiment of this disclosure, the overall identification module 604 is used to calculate a confidence value corresponding to each of the shooting distances based on the authenticity identification results corresponding to each of the shooting distances and the threshold; and to take the authenticity identification result corresponding to the maximum confidence value as the final authenticity identification result.

[0135] The specific details of each module in the aforementioned object authenticity identification device 600 have been described in detail in the corresponding object authenticity identification method, so they will not be repeated here.

[0136] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0137] In an exemplary embodiment of this disclosure, a storage medium capable of implementing the above-described method is also provided. Figure 7 This schematic diagram illustrates a computer-readable storage medium according to an exemplary embodiment of the present disclosure, such as... Figure 7 As shown, a program product 700 for implementing the above-described method according to an embodiment of the present disclosure is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a mobile phone. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0138] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided. Figure 8 The schematic diagram illustrates the structure of a computer system of an electronic device according to an exemplary embodiment of the present disclosure.

[0139] It should be noted that, Figure 8 The computer system 800 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0140] like Figure 8As shown, the computer system 800 includes a Central Processing Unit (CPU) 801, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 802 or programs loaded from storage section 808 into Random Access Memory (RAM) 803. The RAM 803 also stores various programs and data required for system operation. The CPU 801, ROM 802, and RAM 803 are interconnected via a bus 804. An Input / Output (I / O) interface 805 is also connected to the bus 804.

[0141] The following components are connected to I / O interface 805: an input section 806 including a keyboard, mouse, etc.; an output section 807 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to I / O interface 805 as needed. A removable medium 811, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 810 as needed so that computer programs read from it can be installed into storage section 808 as needed.

[0142] In particular, according to embodiments of this disclosure, the processes described below with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 809, and / or installed from removable medium 811. When the computer program is executed by central processing unit (CPU) 801, it performs various functions defined in the system of this disclosure.

[0143] It should be noted that the computer-readable medium shown in the embodiments of this disclosure can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this disclosure, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this disclosure, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0144] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0145] The units described in the embodiments of this disclosure can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the unit itself.

[0146] In another aspect, this disclosure also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or it may exist independently and not assembled into the electronic device. The computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to perform the methods described in the above embodiments.

[0147] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0148] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, touch terminal, or network device, etc.) to execute the method according to the embodiments of this disclosure.

[0149] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein.

[0150] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A method for identifying the authenticity of an object, characterized in that, include: At least two shooting distances should be configured for the shooting equipment; Configure the corresponding shooting prompt information for each shooting distance in the user interface of the shooting device; Based on the shooting prompt information, the shooting data of the object to be identified collected by the shooting device at different shooting distances is obtained; wherein, the shooting data includes image data and / or video data; When the captured data is video data, the step of obtaining the captured data of the object to be identified by the shooting device at different shooting distances based on the shooting prompt information includes: in response to a touch operation of the start recording button in the user interface, starting video recording and displaying shooting prompt information corresponding to a shooting distance in the user interface; when it is detected that the object to be identified meets the acquisition condition of the shooting distance, the user interface displays shooting prompt information corresponding to the next shooting distance; repeating the above display and detection process until in response to a touch operation of the end recording button in the user interface, ending video recording and obtaining the video data; Based on the shooting data, determine the image information corresponding to each shooting distance; The image information is identified as genuine or fake using classifiers corresponding to each of the aforementioned shooting distances, and the identification results corresponding to each of the aforementioned shooting distances are obtained. Based on the authenticity identification results corresponding to each of the shooting distances, the final authenticity identification result of the object to be identified is obtained; The method further includes: extracting data features based on sample data corresponding to each shooting distance; at the first shooting distance, the data features include edge region features; at the second shooting distance, the data features include one or more of screen reflection features, paper embossing features, and material features; at the third shooting distance, the data features include anti-counterfeiting features; and training a model based on the data features to obtain the classifier and the threshold corresponding to the classifier.

2. The object authenticity identification method according to claim 1, characterized in that, When the captured data is image data, the acquisition of captured data of the object to be identified by the capturing device at different capturing distances includes: The user interface displays shooting prompts corresponding to a shooting distance; When the object to be identified is detected to meet the acquisition conditions of the shooting distance, a shooting operation is performed to acquire image data corresponding to the shooting distance; The user interface displays shooting prompts for the next shooting distance. Repeat the above display, detection, and execution process until the image data corresponding to all the shooting distances is obtained.

3. The object authenticity identification method according to claim 1, characterized in that, The step of determining the image information corresponding to each of the shooting distances based on the shooting data includes: The video keyframes corresponding to each shooting distance in the video data are extracted as the image information.

4. The object authenticity identification method according to claim 1, characterized in that, When the captured data is image data and video data, the acquisition of captured data of the object to be identified by the capturing device at different shooting distances includes: In response to a touch operation on the start recording button in the user interface, video recording is started, and a shooting prompt message corresponding to a shooting distance is displayed in the user interface. When the object to be identified is detected to meet the acquisition conditions of the shooting distance, a shooting operation is performed to acquire image data corresponding to the shooting distance; The user interface displays shooting prompts for the next shooting distance. Repeat the above display, detection, and execution process until a touch operation is performed on the end recording button in the user interface, thereby ending the video recording and obtaining the video data.

5. The object authenticity identification method according to claim 1, characterized in that, The method further includes: using a classifier corresponding to the shooting distance to perform authenticity identification on the image information corresponding to the shooting distance, and obtaining the authenticity identification result corresponding to the shooting distance; The step of using a classifier corresponding to a shooting distance to perform authenticity identification on the image information corresponding to the shooting distance, and obtaining the authenticity identification result corresponding to the shooting distance, includes: The image information is input into the classifier to obtain the true or false prediction value output by the classifier; The true and false predicted values ​​are compared with the threshold corresponding to the classifier to obtain the comparison result; The authenticity identification result is determined based on the comparison result.

6. The object authenticity identification method according to claim 1, characterized in that, The step of obtaining the final authenticity identification result of the object to be identified based on the authenticity identification results corresponding to each of the shooting distances includes: The weight information corresponding to each shooting distance is determined based on a pre-trained weight model; The final authenticity recognition result is obtained by calculating based on the weight information and the authenticity recognition result.

7. The object authenticity identification method according to claim 1, characterized in that, The step of obtaining the final authenticity identification result of the object to be identified based on the authenticity identification results corresponding to each of the shooting distances includes: The final authenticity identification result is obtained by performing logical judgment on the authenticity identification results corresponding to each of the shooting distances.

8. The object authenticity identification method according to claim 1, characterized in that, The step of obtaining the final authenticity identification result of the object to be identified based on the authenticity identification results corresponding to each of the shooting distances includes: Based on the authenticity recognition results and the threshold corresponding to each of the shooting distances, calculate the confidence value corresponding to each of the shooting distances; The authenticity identification result corresponding to the maximum confidence value is taken as the final authenticity identification result.

9. A device for identifying the authenticity of an object, characterized in that, include: The prompt module is used to configure at least two shooting distances for the shooting device; Configure the corresponding shooting prompt information for each shooting distance in the user interface of the shooting device; The acquisition module is used to acquire shooting data of the object to be identified collected by the shooting device at different shooting distances based on the shooting prompt information; When the captured data is video data, the step of obtaining the captured data of the object to be identified by the shooting device at different shooting distances based on the shooting prompt information includes: in response to a touch operation of the start recording button in the user interface, starting video recording and displaying shooting prompt information corresponding to a shooting distance in the user interface; when it is detected that the object to be identified meets the acquisition condition of the shooting distance, the user interface displays shooting prompt information corresponding to the next shooting distance; repeating the above display and detection process until in response to a touch operation of the end recording button in the user interface, ending video recording and obtaining the video data; The determining module is used to determine the image information corresponding to each of the shooting distances based on the shooting data; The classification and recognition module is used to perform authenticity recognition on the image information using classifiers corresponding to each shooting distance, and obtain authenticity recognition results corresponding to each shooting distance; extract data features based on sample data corresponding to each shooting distance; at the first shooting distance, the data features include edge region features; at the second shooting distance, the data features include one or more of screen reflection features, paper texture features, and material features; at the third shooting distance, the data features include anti-counterfeiting features; and train a model based on the data features to obtain the classifier and the threshold corresponding to the classifier. The overall recognition module is used to obtain the final authenticity recognition result of the object to be identified based on the authenticity recognition results corresponding to each of the shooting distances.

10. A computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the object authenticity identification method as described in any one of claims 1 to 8.

11. An electronic device, characterized in that, include: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the one or more processors to implement the object authenticity identification method as described in any one of claims 1 to 8.

Images