Anti-counterfeiting method and device for starting biological recognition verification, equipment and storage medium

Abstract

The embodiment of the invention provides an anti-counterfeiting method and device for starting biological recognition verification, equipment and a storage medium, and belongs to the technical field of image recognition. The method comprises the steps of obtaining a to-be-recognized image, and extracting a to-be-recognized object and to-be-recognized object information in the to-be-recognized image; according to the information of the to-be-identified object, carrying out living body detection on the to-be-identified object, and storing a living body detection result; n times of living body detection results are obtained and input into a preset living body judgment algorithm, if the output result of the preset living body judgment algorithm is a living body, biological recognition verification is started, and if the output result is a non-living body, an anti-fake attack event is output. According to the method and the device, the living body inspection is performed on the to-be-identified object for many times, and the anti-counterfeiting attack or biological identification verification is output according to the plurality of living body inspection results, so that the problem of relatively high misjudgment rate of a single inspection index is effectively solved.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and in particular to an anti-counterfeiting method, device, equipment and storage medium for initiating biometric verification. Background Art

[0002] As technology continues to develop, criminals use high-definition photos, videos or 3D printed masks to carry out fake face attacks, trying to bypass system verification and conduct identity theft or fraud. Currently, most methods for liveness detection rely on infrared light for detection, which has a high rate of misjudgment. Summary of the invention

[0003] In order to solve the above technical problems, the embodiments of the present application provide an anti-counterfeiting method, device, electronic device and readable storage medium for starting biometric verification.

[0004] In a first aspect, an embodiment of the present application provides an anti-counterfeiting method for starting biometric verification, the method comprising: acquiring an image to be identified, extracting an object to be identified and information about the object to be identified in the image to be identified;

[0005] Performing a liveness test on the object to be identified according to the information of the object to be identified, and storing the liveness test result;

[0006] Obtain N liveness detection results and input them into a preset liveness judgment algorithm. If the preset liveness judgment algorithm outputs a liveness result, biometric verification is initiated; if the preset liveness judgment algorithm outputs a non-liveness result, an anti-counterfeiting attack event is output.

[0007] Optionally, the preset living body determination algorithm includes:

[0008] Continuously obtain N liveness detection results, if all are liveness, output the result as liveness, if all are non-liveness, output the result as non-liveness, wherein, if both liveness and non-liveness appear in the N liveness detection results obtained continuously, delete the liveness detection result with the longest storage time, and obtain the latest liveness detection result; or,

[0009] Obtain N liveness detection results. If the proportion of liveness in the liveness detection results is greater than that of non-liveness, the output result is liveness. If the proportion of liveness in the liveness detection results is less than that of non-liveness, the output result is non-liveness.

[0010] Optionally, after starting the biometric verification, the method further includes:

[0011] After the biometric verification is started, the image to be identified is acquired again, and the object to be identified and the information of the object to be identified in the image to be identified are extracted;

[0012] Compare the object to be identified and the information of the object to be identified extracted this time with the object to be identified and the information of the object to be identified extracted last time. If the object to be identified extracted this time is the same as the object to be identified extracted last time, output the liveness detection result as liveness and maintain the biometric verification;

[0013] If the object to be identified extracted this time is different from the object to be identified extracted last time, the stored liveness detection result is cleared and the anti-counterfeiting method of biometric verification is restarted.

[0014] Optionally, performing a liveness test on the object to be identified according to the information of the object to be identified includes:

[0015] The first image recognition strategy, the second image recognition strategy and the third image recognition strategy are executed, and whether the object to be recognized is a living body is determined by a preset living body judgment strategy.

[0016] Optionally, the preset liveness judgment strategy includes: obtaining at least two liveness detection results from three image recognition strategies, and when the number of liveness results in the at least two liveness detection results is greater than the number of non-liveness results, outputting the liveness detection result as liveness, otherwise outputting the liveness detection result as non-liveness; or,

[0017] At least two of the first image recognition strategy, the second image recognition strategy and the third image recognition strategy are executed in sequence, wherein when the output result of the image recognition strategy executed in the previous step is a living body, the next image recognition strategy is executed, until the output of the last image recognition strategy is a living body and the liveness detection result is a live body; if the output result of executing any of the image recognition strategies is a non-living body, the detection result is a non-living body.

[0018] Optionally, the first image recognition strategy includes a contour recognition algorithm, and the contour recognition algorithm is used to identify whether there is square contour information in the image to be recognized, and if there is the square contour information, the liveness detection result is output as non-liveness;

[0019] The second image recognition strategy includes an infrared feature recognition algorithm, and the infrared feature recognition algorithm is used to determine whether the object to be recognized meets the preset living feature index;

[0020] The third image recognition strategy includes detecting whether the second living feature of the object to be recognized is obtained, if not, outputting a living body detection result as non-living body, and if so, outputting a living body detection result as living body.

[0021] Optionally, the executing the first image recognition strategy, the second image recognition strategy and the third image recognition strategy also includes:

[0022] According to the information of the object to be identified, it is determined whether the identified object meets the preset identification type. If not, the liveness detection result is output as non-liveness. If so, the first image recognition strategy, the second image recognition strategy and the third image recognition strategy are executed.

[0023] In a second aspect, an embodiment of the present application provides an anti-counterfeiting device for starting biometric verification, the anti-counterfeiting device for starting biometric verification comprising:

[0024] An acquisition module, used to acquire an image to be identified, and extract an object to be identified and information about the object to be identified from the image to be identified;

[0025] A judgment module, used for performing a liveness test on the object to be identified according to the information of the object to be identified, and storing the liveness test result;

[0026] The output module obtains N liveness detection results and inputs them into a preset liveness judgment algorithm. If the output result of the preset liveness judgment algorithm is liveness, biometric verification is started; if the output result is not liveness, an anti-counterfeiting attack event is output.

[0027] In a third aspect, an embodiment of the present application provides an anti-counterfeiting device for starting biometric verification, comprising a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is run by the processor, the anti-counterfeiting method for starting biometric verification provided in the first aspect is executed.

[0028] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, which, when running on a processor, executes the anti-counterfeiting method for initiating biometric verification provided in the first aspect.

[0029] The anti-counterfeiting method, device, equipment and computer-readable storage medium for starting biometric verification provided by the above application include: obtaining an image to be identified, extracting the object to be identified and the information of the object to be identified in the image to be identified; performing a liveness test on the object to be identified according to the information of the object to be identified, and storing the liveness test results; obtaining N liveness test results and inputting them into a preset liveness judgment algorithm, and starting biometric verification if the output result of the preset liveness judgment algorithm is liveness, and outputting an anti-counterfeiting attack event if the output result is not liveness. The present application effectively solves the problem of high misjudgment rate of a single inspection indicator by performing liveness tests on the object to be identified multiple times, and outputting anti-counterfeiting attacks or biometric verifications according to multiple liveness test results. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solution of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present application and should not be regarded as limiting the scope of protection of the present application. In each of the drawings, similar components are numbered similarly.

[0031] Figure 1 A first flow chart of an anti-counterfeiting method for starting biometric verification provided by an embodiment of the present application is shown;

[0032] Figure 2 A second flow chart of the anti-counterfeiting method for starting biometric verification provided by an embodiment of the present application is shown;

[0033] Figure 3 A third flow chart of the anti-counterfeiting method for starting biometric verification provided by an embodiment of the present application is shown;

[0034] Figure 4 A fourth flow chart of the anti-counterfeiting method for starting biometric verification provided by an embodiment of the present application is shown;

[0035] Figure 5 A fifth flow chart of the anti-counterfeiting method for starting biometric verification provided by an embodiment of the present application is shown;

[0036] Figure 6 A sixth flow chart of the anti-counterfeiting method for starting biometric verification provided by an embodiment of the present application is shown;

[0037] Figure 7 A seventh flow chart of the anti-counterfeiting method for starting biometric verification provided by an embodiment of the present application is shown;

[0038] Figure 8 A schematic diagram of the structure of an anti-counterfeiting device for starting biometric verification provided by an embodiment of the present application is shown;

[0039] Fig. 9 A schematic diagram of the structure of an anti-counterfeiting device for starting biometric verification provided in an embodiment of the present application is shown.

[0040] Icon: 800 - anti-counterfeiting device for starting biometric verification, 801 - acquisition module, 802 - judgment module, 803 - output module, 900 - anti-counterfeiting device for starting biometric verification, 901 - memory, 902 - processor. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0042] The components of the embodiments of the present application generally described and shown in the drawings herein may be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0043] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present application, are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing items.

[0044] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0045] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present application belong. Terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present application.

[0046] Example 1

[0047] The embodiment of the present application provides an anti-counterfeiting method for initiating biometric verification.

[0048] See also Figure 1 , anti-counterfeiting methods for initiating biometric verification include:

[0049] S101, obtaining an image to be identified, and extracting an object to be identified and information about the object to be identified in the image to be identified.

[0050] It should be noted that the user can obtain the image information of the object by uploading pictures through the Internet or by taking photos directly. After that, the image of the object can be placed in front of the biometric verification device by printing or holding a screen to activate the biometric verification device. After the biometric verification device is activated, it will collect the image information in front, which is the image to be identified. The image to be identified is preprocessed in advance, and the preprocessing operations include: grayscale processing, noise removal and binarization processing. Any method can be selected to preprocess the image to be identified and simplify the image to be identified to facilitate subsequent detection.

[0051] In an optional implementation, step S101 further includes: S1011, determining whether the distance between the object to be identified and the identification device is less than or equal to a preset distance, if so, determining whether the object to be identified is a candidate living object, if not, reacquiring the image to be identified.

[0052] It should be noted that in order to ensure the accuracy and security of recognition, the distance range between the object to be recognized and the device must be limited. If the distance is too far, the acquired image may not be clear enough or the features are not obvious, and accurate recognition judgment cannot be made, so the image needs to be acquired again. When the distance is within the preset range, it is determined whether the object to be recognized is a candidate living body, which can effectively eliminate the interference of non-living bodies and improve the reliability of recognition.

[0053] S102, performing a liveness test on the object to be identified according to the information of the object to be identified, and storing the liveness test result.

[0054] In an optional embodiment, if Figure 4 As shown, step S102 includes: S410, executing the first image recognition strategy, the second image recognition strategy and the third image recognition strategy. S420, determining whether the object to be identified is a living body through a preset living body judgment strategy, if yes, proceeding to step S421, if no, proceeding to step S433. S421, outputting a living body detection result of a living body if it is a living body. S422, outputting a living body detection result of a non-living body if it is not a living body.

[0055] In an optional embodiment, the preset living body judgment strategy includes but is not limited to Figure 5 and Figure 6 The process steps shown are Figure 5Including: S510, execute the first image recognition strategy. S511, obtain the liveness detection result of the first image recognition strategy. S520, execute the second image recognition strategy. S521, obtain the liveness detection result of the second image recognition strategy. S530, execute the third image recognition strategy. S531, obtain the liveness detection result of the third image recognition strategy. S540, obtain the liveness detection results of at least two of the above-mentioned image recognition strategies. S550, determine whether the number of live bodies in the obtained liveness detection result is greater than the number of non-live bodies, if not, enter step S551, if yes, enter step S552. S551, the number of live bodies is less than or equal to the number of non-live bodies, and the liveness detection result is output as non-live. S552, the number of live bodies is greater than the number of non-live bodies, and the liveness detection result is output as live. Figure 6 The method includes: S610, executing a first image recognition strategy to obtain a liveness detection result of the first image recognition strategy. S620, determining whether the liveness detection result of the first image recognition strategy is liveness, if yes, proceeding to step S630, if no, proceeding to step S680. S630, executing a second image recognition strategy to obtain a liveness detection result of the second image recognition strategy. S640, determining whether the liveness detection result of the second image recognition strategy is liveness, if yes, proceeding to step S650, if no, proceeding to step S680. S650, executing a third image recognition strategy to obtain a liveness detection result of the third image recognition strategy. S660, determining whether the liveness detection result of the third image recognition strategy is liveness, if yes, proceeding to step S670, if no, proceeding to step S680. S670, outputting a liveness detection result as liveness. S680, outputting a liveness detection result as non-liveness.

[0056] It is understandable that the image recognition strategies adopted in the practical application of the first image recognition strategy, the second image recognition strategy and the third image recognition strategy provided above can be increased or decreased as needed, for example, including the first and second image recognition strategies, including the first, second, third and fourth image recognition strategies, etc. Figure 5 The number of liveness detection results obtained in step S540 can be adjusted as needed, and usually only needs to be greater than or equal to 2. In practical applications, Figure 6 The execution steps shown in are not limited to executing three image recognition strategies, but also include but are not limited to executing 2 image recognition strategies, executing 4 image recognition strategies, etc. The solution of the present application can also be reasonably expanded and extended on the logical thinking recorded above.

[0057] It should be noted that the recognition algorithms specifically adopted in the first image recognition strategy, the second image recognition strategy and the third image recognition strategy provided above can be adjusted as needed, and the same recognition algorithm can also be adopted in some cases.

[0058] The first image recognition strategy includes a contour recognition algorithm, which is used to identify whether there is square contour information in the image to be recognized. If there is square contour information, the liveness detection result is output as non-liveness. For example, the first image recognition strategy is executed to determine whether the object to be recognized is a two-dimensional image according to the information of the object to be recognized. If so, the liveness detection result is output as non-liveness. If not, the second image recognition strategy is executed.

[0059] The second image recognition strategy includes an infrared feature recognition algorithm, and the infrared feature recognition algorithm is used to determine whether the object to be recognized meets the preset live feature index. For example, the second image recognition strategy is executed to determine whether the object to be recognized meets the preset live feature index according to the information of the object to be recognized. If so, the liveness detection result is output as liveness, and if not, the liveness detection result is output as non-liveness.

[0060] The third image recognition strategy includes detecting whether the second liveness feature of the object to be identified is obtained, and if not, outputting the liveness detection result as non-liveness, and if so, outputting the liveness detection result as liveness. The second liveness feature of the object to be identified includes, but is not limited to, using facial activity features such as lip movement, facial movement, and eye movement as the second liveness feature in face recognition, and using palm activity features such as finger movement, grasping movement, and finger flexion and extension movement as the second liveness feature in palmprint recognition.

[0061] In an alternative embodiment, see Figure 7 Before executing step S410, the method further includes: S710, judging whether the object to be identified meets the preset identification type according to the information of the object to be identified, if yes, proceeding to step S410, if no, proceeding to step S720. S720, outputting the liveness detection result as non-liveness.

[0062] It should be noted that the preset recognition types include but are not limited to face recognition, palm print recognition, hand shape recognition, auricle recognition, iris recognition and gait recognition, etc. In some special cases, they can also be used for the recognition of other species, such as animal nose print recognition.

[0063] In this embodiment, the preprocessed image may be used to extract contour information of the object to be identified through a contour detection algorithm, such as using a Canny edge detection algorithm to detect the precise edge position of the object to be identified, or using the findContours function in OPEN CV to find contour information in the image after edge detection.

[0064] It should be noted that when it is detected that the contour information of the object to be identified includes contour edge points of approximately equal width and height, and the four vertices of the contour edge are close to right angles, it is determined that the edge contour of the object to be identified is a square contour, and the object to be identified is determined to be any square contour object, and the object to be identified is determined to be in a non-living state. For example, if the object to be identified is determined to be a printed paper object, the object to be identified is determined to be in a non-living state.

[0065] The present application can quickly perform preliminary screening on the object to be identified by detecting the square contour information in the contour information of the object to be identified, thereby improving the identification efficiency.

[0066] It is further explained that if it is determined that there is no square contour information in the object to be identified, after preliminary screening of the object to be identified, the facial feature information of the candidate living object is further extracted, and the infrared feature recognition algorithm is used to determine whether the object to be identified meets the preset living feature indicators.

[0067] The infrared feature recognition algorithm includes an infrared light feature recognition algorithm and a visible light feature recognition algorithm. The preset living feature indicators include the preset texture threshold and the preset brightness threshold of the visible light feature recognition algorithm and the infrared light feature recognition algorithm. Since the detection effects of visible light and infrared light may be different under different environmental conditions (such as insufficient light or strong light), the judgment of the two light sources is combined to reduce misjudgment caused by specific lighting conditions.

[0068] In this embodiment, the visible light model and the infrared light model are divided into two test results of 0 and 1. If the test result of any model is 0, the object to be identified is determined to be in a non-living state. By setting the preset texture threshold and the preset brightness threshold of the visible light model and the infrared light model respectively, if the texture information value of the face image is less than the preset texture threshold of any model or the brightness information value is less than the preset brightness threshold of any model, the corresponding model outputs 0, and the object to be identified is determined to be non-living.

[0069] This application improves the accuracy of anti-counterfeiting detection by combining the feature thresholds under two different light sources. Using different models under different lighting conditions can increase the robustness of the system, and the thresholds can be adjusted according to the actual application scenarios to adapt to different environmental requirements.

[0070] S103, obtaining N liveness detection results and inputting them into a preset liveness judgment algorithm. If the output result of the preset liveness judgment algorithm is liveness, biometric verification is started; if the output result is not liveness, an anti-counterfeiting attack event is output.

[0071] In the embodiment of the present application, the anti-counterfeiting attack alarm information includes an identification device issuing an alarm, or popping up a warning message to warn the user.

[0072] In an optional embodiment, if Figure 2 As shown, step S103 includes: S210, continuously obtaining N liveness detection results, all of which are liveness. S211, starting biometric verification. S220, continuously obtaining N liveness detection results, all of which are non-liveness. S221, outputting anti-counterfeiting attack events. S230, continuously obtaining N liveness detection results, and both liveness and non-liveness appear at the same time. S231, deleting the liveness detection result with the longest storage time, and obtaining the latest liveness detection result.

[0073] In another optional implementation, step S103 may further include: obtaining N liveness detection results, and if the proportion of liveness in the liveness detection results is greater than that of non-liveness, outputting the result as liveness; if the proportion of liveness in the liveness detection results is less than that of non-liveness, outputting the result as non-liveness.

[0074] It should be noted that in the present application, N liveness detection results are obtained and input into a preset liveness judgment algorithm, wherein the optional preset liveness judgment algorithm is not limited to the two algorithms provided above. In practical applications, other algorithms that comprehensively judge the final liveness result based on multiple liveness detection results can also be used, such as a lottery algorithm, a voting algorithm, a result distribution algorithm, etc. As long as the overall concept is similar to that of the present application, the algorithm is within the protection scope of the present application.

[0075] It should be noted that when the biometric verification device is activated, it will continuously obtain image information in front of it, and each time the image information obtained will be subjected to liveness detection. The N value of the continuous preset number of times can be adjusted according to specific needs. A larger continuous preset number of times means a higher anti-counterfeiting confirmation threshold, which is suitable for scenarios with extremely high anti-counterfeiting requirements. A smaller continuous preset number of times can respond quickly to changes, reduce recognition time, and improve user experience. Therefore, the dynamic adjustment capability is further increased by reasonably setting the value of N.

[0076] In an optional embodiment, if Figure 3 As shown, after step S103, it includes: S211, starting biometric verification. S310, acquiring the image to be identified again, and extracting the object to be identified and the object information to be identified in the image to be identified; S320, comparing the object to be identified and the object information to be identified extracted this time with the object to be identified and the object information to be identified extracted last time. S330, if the object to be identified extracted this time is the same object to be identified as the object to be identified extracted last time. S331, outputting the liveness detection result as liveness, and maintaining biometric verification. S340, if the object to be identified extracted this time is a different object to be identified from the object to be identified extracted last time. S341, clearing the stored liveness detection result, and restarting the anti-counterfeiting method of biometric verification.

[0077] Of course, by the same token, it can be known that S221 outputs an anti-counterfeiting attack event. After step S221, the image to be identified can be obtained again, and the object to be identified and the object information to be identified in the image to be identified can be extracted; the object to be identified and the object information to be identified extracted this time are compared with the object to be identified and the object information to be identified extracted last time. If the object to be identified extracted this time is the same as the object to be identified extracted last time, the output detection result is non-living or an anti-counterfeiting attack event is output; if the object to be identified extracted this time is different from the object to be identified extracted last time, the stored liveness detection result is cleared and the anti-counterfeiting method of biometric verification is restarted.

[0078] It should be noted that when the object to be identified is obtained again, the object to be identified and the object information in the image to be identified this time are compared with the object to be identified and the object information in the image to be identified extracted last time. If the information of the object to be identified is consistent, it is determined that the objects to be identified extracted twice are the same object, and the previous liveness detection result is output, and there is no need to perform liveness anti-counterfeiting detection again, so as to increase the speed of continuous recognition and improve user experience. The same is true after outputting anti-counterfeiting attack events. When the objects detected before and after are consistent, it means that they are the same person. At this time, the detection result can be directly kept as non-live, or the anti-counterfeiting attack event can be directly output.

[0079] The anti-counterfeiting method for starting biometric verification provided in this embodiment includes: obtaining an image to be identified, extracting an object to be identified and information about the object to be identified in the image to be identified; performing a liveness test on the object to be identified according to the information about the object to be identified, and storing the liveness test results; continuously obtaining N liveness test results, if all are liveness, starting biometric verification, and if all are non-liveness, outputting an anti-counterfeiting attack event. This application effectively solves the problem of a high misjudgment rate of a single test indicator by performing liveness tests on the object to be identified multiple times, and outputting an anti-counterfeiting attack or biometric verification based on multiple liveness test results.

[0080] Example 2

[0081] In addition, an embodiment of the present application provides an anti-counterfeiting device for initiating biometric verification.

[0082] like Figure 8 As shown, the anti-counterfeiting device 800 for starting biometric verification includes:

[0083] The acquisition module 801 is used to acquire the image to be identified, and extract the object to be identified and the information of the object to be identified in the image to be identified;

[0084] The judgment module 802 is used to perform a liveness test on the object to be identified according to the information of the object to be identified, and store the liveness test result;

[0085] The output module 803 is used to obtain N liveness detection results and input them into a preset liveness judgment algorithm. If the output result of the preset liveness judgment algorithm is liveness, biometric verification is started; if the output result is not liveness, an anti-counterfeiting attack event is output.

[0086] The anti-counterfeiting device 800 for starting biometric verification provided in this embodiment can implement the anti-counterfeiting method for starting biometric verification provided in Embodiment 1, and will not be described again here to avoid repetition.

[0087] The anti-counterfeiting device for starting biometric verification provided in this embodiment performs liveness tests on the object to be identified multiple times, and outputs anti-counterfeiting attacks or biometric verifications based on multiple liveness test results, thereby effectively solving the problem of high misjudgment rate of a single test indicator.

[0088] Example 3

[0089] The present application also provides an anti-counterfeiting device for starting biometric verification. Fig. 9 , Fig. 9 This is a basic structural block diagram of the anti-counterfeiting device that enables biometric verification in this embodiment.

[0090] The anti-counterfeiting device 900 for starting biometric verification includes a memory 901 and a processor 902 that are connected to each other through a system bus. It should be noted that the figure only shows the anti-counterfeiting device 900 for starting biometric verification with a memory 901 and a processor 902, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the anti-counterfeiting device for starting biometric verification here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASIC), programmable gate arrays (FPGA), digital signal processors (DSP), embedded devices, etc.

[0091] The anti-counterfeiting device that starts biometric verification can be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The anti-counterfeiting device that starts biometric verification can interact with the user through a keyboard, a mouse, a remote control, a touch pad, or a voice control device.

[0092] The memory 901 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or D slot compatibility test memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 901 can be an internal storage unit of the anti-counterfeiting device 900 for starting biometric verification, such as a hard disk or memory of the anti-counterfeiting device 900 for starting biometric verification. In other embodiments, the memory 901 can also be an external storage device of the anti-counterfeiting device 900 for starting biometric verification, such as a plug-in hard disk equipped on the anti-counterfeiting device 900 for starting biometric verification, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Of course, the memory 901 can also include both the internal storage unit of the anti-counterfeiting device 900 for starting biometric verification and its external storage device. In this embodiment, the memory 901 is generally used to store the operating system and various application software installed in the anti-counterfeiting device 900 for starting biometric verification, such as computer-readable instructions of the slot compatibility test method, etc. In addition, the memory 901 can also be used to temporarily store various data that have been output or will be output.

[0093] In some embodiments, the processor 902 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other anti-counterfeiting chip for enabling biometric verification. The processor 902 is generally used to control the overall operation of the anti-counterfeiting device 900 for enabling biometric verification. In this embodiment, the processor 902 is used to run computer-readable instructions or process data stored in the memory 901, such as computer-readable instructions for running a slot compatibility test method.

[0094] The anti-counterfeiting device for starting biometric verification provided in this embodiment can execute the anti-counterfeiting method for starting biometric verification described above. The anti-counterfeiting method for starting biometric verification here can be the anti-counterfeiting method for starting biometric verification of each of the above embodiments.

[0095] Example 4

[0096] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the anti-counterfeiting method for starting biometric verification provided in Example 1 is implemented.

[0097] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0098] The computer-readable storage medium provided in this embodiment can implement the anti-counterfeiting method for starting biometric verification provided in Example 1, and will not be described again here to avoid repetition.

[0099] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0100] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0101] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An anti-counterfeiting method for starting biometric verification, characterized in that: The method comprises: Acquire an image to be identified, and extract the object to be identified and information about the object to be identified from the image to be identified; Performing a liveness test on the object to be identified according to the information of the object to be identified, and storing the liveness test result; Obtain N liveness detection results and input them into a preset liveness judgment algorithm. If the preset liveness judgment algorithm outputs a liveness result, biometric verification is initiated; if the preset liveness judgment algorithm outputs a non-liveness result, an anti-counterfeiting attack event is output.

2. The anti-counterfeiting method for starting biometric verification according to claim 1, characterized in that: The preset living body determination algorithm includes: Continuously obtain N liveness detection results, if all are liveness, output the result as liveness, if all are non-liveness, output the result as non-liveness, wherein, if both liveness and non-liveness appear in the N liveness detection results obtained continuously, delete the liveness detection result with the longest storage time, and obtain the latest liveness detection result; or, Obtain N liveness detection results. If the proportion of liveness in the liveness detection results is greater than that of non-liveness, the output result is liveness. If the proportion of liveness in the liveness detection results is less than that of non-liveness, the output result is non-liveness.

3. The anti-counterfeiting method for initiating biometric verification according to claim 1, characterized in that: After the biometric verification is started, the method further includes: After the biometric verification is started, the image to be identified is acquired again, and the object to be identified and the information of the object to be identified in the image to be identified are extracted; Compare the object to be identified and the information of the object to be identified extracted this time with the object to be identified and the information of the object to be identified extracted last time. If the object to be identified extracted this time is the same as the object to be identified extracted last time, output the liveness detection result as liveness and maintain the biometric verification; If the object to be identified extracted this time is different from the object to be identified extracted last time, the stored liveness detection result is cleared and the anti-counterfeiting method of biometric verification is restarted.

4. The anti-counterfeiting method for starting biometric verification according to any one of claims 1 to 3, characterized in that: The performing a liveness test on the object to be identified according to the information of the object to be identified includes: The first image recognition strategy, the second image recognition strategy and the third image recognition strategy are executed, and whether the object to be recognized is a living body is determined by a preset living body judgment strategy.

5. The anti-counterfeiting method for starting biometric verification according to claim 4, characterized in that: The preset liveness judgment strategy includes: obtaining at least two liveness detection results from three image recognition strategies, and when the number of liveness results in the at least two liveness detection results is greater than the number of non-liveness results, outputting the liveness detection result as liveness, otherwise outputting the liveness detection result as non-liveness; or, At least two of the first image recognition strategy, the second image recognition strategy and the third image recognition strategy are executed in sequence, wherein when the output result of the image recognition strategy executed in the previous step is a living body, the next image recognition strategy is executed, until the output of the last image recognition strategy is a living body and the liveness detection result is a live body; if the output result of executing any of the image recognition strategies is a non-living body, the detection result is a non-living body.

6. The anti-counterfeiting method for initiating biometric verification according to claim 4, characterized in that: The first image recognition strategy includes a contour recognition algorithm, which is used to identify whether there is square contour information in the image to be recognized, and if there is square contour information, outputting a liveness detection result as non-liveness; The second image recognition strategy includes an infrared feature recognition algorithm, and the infrared feature recognition algorithm is used to determine whether the object to be recognized meets the preset living feature index; The third image recognition strategy includes detecting whether the second living feature of the object to be recognized is obtained, if not, outputting a living body detection result as non-living body, and if so, outputting a living body detection result as living body.

7. The anti-counterfeiting method for initiating biometric verification according to claim 4, characterized in that: The executing of the first image recognition strategy, the second image recognition strategy and the third image recognition strategy also includes: According to the information of the object to be identified, it is determined whether the identified object meets the preset identification type. If not, the liveness detection result is output as non-liveness. If so, the first image recognition strategy, the second image recognition strategy and the third image recognition strategy are executed.

8. An anti-counterfeiting device for enabling biometric verification, characterized in that: The device comprises: An acquisition module, used to acquire an image to be identified, and extract an object to be identified and information about the object to be identified from the image to be identified; A judgment module, used for performing a liveness test on the object to be identified according to the information of the object to be identified, and storing the liveness test result; The output module is used to obtain N liveness detection results and input them into a preset liveness judgment algorithm. If the output result of the preset liveness judgment algorithm is liveness, biometric verification is started; if the output result is not liveness, an anti-counterfeiting attack event is output.

9. An anti-counterfeiting device for enabling biometric verification, characterized in that: include: Memory, used to store programs; A processor, configured to implement the anti-counterfeiting method for starting biometric verification as described in any one of claims 1 to 7 by executing the program stored in the memory.

10. A computer-readable storage medium, characterized in that: The invention comprises a program which can be executed by a processor to implement the anti-counterfeiting method for starting biometric authentication as described in any one of claims 1 to 7.

Images