A fingerprint identification method, an electronic device, a storage medium and a program product

Abstract

This application provides a fingerprint recognition method, electronic device, storage medium, and program product, aiming to improve the accuracy of fingerprint recognition. The method is applied to a terminal device, which has a display screen and a fingerprint module located below the display screen. The display screen includes a fingerprint acquisition area with bright and dark areas. The method includes: obtaining a fingerprint image to be recognized for an object above the fingerprint acquisition area when the fingerprint module partially emits light; the bright area being the area where the light-emitting units are in an emitting state when the fingerprint acquisition area partially emits light, and the dark area being the area where the light-emitting units are in an off state when the fingerprint acquisition area partially emits light; and obtaining the object recognition result based on the bright and dark area images contained in the fingerprint image to be recognized, where the bright area image is the image acquired by the fingerprint module for an object above the bright area, and the dark area image is the image acquired by the fingerprint module for an object above the dark area.

Description

Technical Field

[0001] This application relates to the field of fingerprint recognition technology, and in particular to a fingerprint recognition method, electronic device, storage medium, and program product. Background Technology

[0002] With the widespread application of fingerprint recognition technology, the matching technology between the fingerprint to be identified and the fingerprint of the target finger has developed rapidly. The target finger's fingerprint refers to a fingerprint that can successfully pass fingerprint recognition. By comparing whether the fingerprint to be identified and the target finger's fingerprint match, the result of whether the fingerprint to be identified has successfully passed fingerprint recognition can be obtained.

[0003] However, current fingerprint matching technologies only consider whether the fingerprint to be identified matches the fingerprint of the target finger, and there is no particularly effective method for determining the authenticity of the fingerprint to be identified. Therefore, preventing fake fingerprints from passing through fingerprint recognition has become an urgent problem to be solved. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a fingerprint recognition method, an electronic device, a storage medium, and a program product to overcome or at least partially solve the above problems.

[0005] A first aspect of the present invention provides a fingerprint recognition method applied to a terminal device, the terminal device having a display screen and a fingerprint module located below the display screen, the display screen including a fingerprint acquisition area having a bright area and a dark area, the method comprising:

[0006] The fingerprint module acquires a fingerprint image of an object above the fingerprint acquisition area when the fingerprint acquisition area is partially illuminated. The bright area is the area where the light-emitting unit is in the illuminating state when the fingerprint acquisition area is partially illuminated, and the dark area is the area where the light-emitting unit is in the extinguished state when the fingerprint acquisition area is partially illuminated.

[0007] The recognition result of the object is obtained based on the bright area image and dark area image contained in the fingerprint image to be identified. The bright area image is the image captured by the fingerprint module for the object above the bright area, and the dark area image is the image captured by the fingerprint module for the object above the dark area.

[0008] Optionally, the identification result of the object is obtained based on the bright area image and dark area image contained in the fingerprint image to be identified, including:

[0009] Based on the relative relationship between the bright area image and the dark area image, a real / fake identification result for the object is obtained, wherein the real / fake identification result characterizes whether the object is a real finger; and / or

[0010] Based on the fingerprint image to be identified, a matching identification result of the object is obtained, wherein the matching identification result indicates whether the fingerprint of the object matches the fingerprint of the target finger.

[0011] Optionally, the real / fake object identification result is obtained based on the relative relationship between the bright area image and the dark area image, including:

[0012] Determine the brightness ratio between the bright area image and the dark area image;

[0013] If the brightness ratio is within the brightness ratio threshold range, the object is determined to be a real finger. The brightness ratio threshold range is determined based on the brightness ratio of the dark area and the bright area of ​​the real finger image in the fingerprint image collected by the fingerprint module for the real finger.

[0014] If the brightness ratio is outside the brightness ratio threshold range, the object is determined to be a fake finger.

[0015] Optionally, determining the brightness ratio of the bright area image to the dark area image includes:

[0016] Obtain the code values ​​of at least some pixels in the bright area image and the code values ​​of at least some pixels in the dark area image;

[0017] The average code value of the bright region image is obtained based on the code values ​​of at least some pixels in the bright region image, and the average code value of the dark region image is obtained based on the code values ​​of at least some pixels in the dark region image.

[0018] The brightness ratio of the bright area image to the dark area image is obtained based on the average code value of the bright area image and the average code value of the dark area image.

[0019] Optionally, obtaining the matching and identification result of the object based on the fingerprint image to be identified includes:

[0020] The fingerprint image to be identified is processed to obtain a fingerprint image with uniform brightness.

[0021] Based on a uniformly bright fingerprint image to be identified, the matching and identification results of the object are obtained.

[0022] Optionally, it also includes:

[0023] Based on the fingerprint image to be identified, the object is detected as real or fake using a real / fake identification model to obtain the first real / fake identification result of the object;

[0024] Based on the relative relationship between the bright area image and the dark area image, the result of identifying whether the object is real or fake is obtained, including:

[0025] Based on the relative relationship between the bright area image and the dark area image, a second real / fake identification result of the object is obtained;

[0026] Based on the first and second true / false identification results, the true / false identification result of the object is obtained.

[0027] Optionally, obtaining the fingerprint image to be identified, captured by the fingerprint module for an object above the fingerprint acquisition area when the fingerprint acquisition area is partially illuminated, includes:

[0028] The fingerprint module acquires multiple frames of images of an object above the fingerprint acquisition area when the fingerprint acquisition area is partially illuminated.

[0029] The multiple frames of images are fused to obtain the fingerprint image to be identified.

[0030] Optionally, the bright area image and dark area image included in the fingerprint image to be identified are obtained according to the following steps:

[0031] Obtain the code value of each pixel in the fingerprint image to be identified;

[0032] Based on the code value of each pixel and the code values ​​of its neighboring pixels, the boundary line between the bright area image and the dark area image is obtained;

[0033] The bright area image and the dark area image are obtained based on the boundary line between the bright area image and the dark area image.

[0034] Optionally, the bright area surrounds the dark area.

[0035] Optionally, the dark area is located in the central region of the bright area.

[0036] Optionally, the dark region includes multiple non-connected sub-dark regions.

[0037] Optionally, the bright area image is all image regions in the fingerprint image to be identified, excluding the dark area image; or

[0038] The bright area image is the middle image region of the remaining image region in the fingerprint image to be identified, excluding the dark area image.

[0039] Optionally, the size of the dark area satisfies the condition that the fingerprint module has fingerprint texture in the dark area of ​​the real finger fingerprint image collected from the real finger.

[0040] Optionally, the diameter of the dark area is 5-15 light-emitting units; or

[0041] The diameter of the dark area is 0.3-6 mm.

[0042] In a second aspect, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the fingerprint recognition method disclosed in the embodiments of this application.

[0043] A third aspect of the present invention provides a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implements the fingerprint recognition method disclosed in the embodiments of this application.

[0044] A fourth aspect of the present invention provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the fingerprint recognition method disclosed in the embodiments of this application.

[0045] The embodiments of the present invention have the following advantages:

[0046] In this embodiment, when the fingerprint module emits light in the fingerprint acquisition area, it acquires a fingerprint image of the object to be identified above the fingerprint acquisition area, resulting in a fingerprint image containing both bright and dark areas. Based on these bright and dark areas, the object's identification result can be obtained. The refractive index, reflectivity, and dispersion characteristics of the materials used to make a prosthetic finger differ from those of a real finger. Therefore, the bright and dark areas of a prosthetic finger differ from those of a real finger. Thus, by analyzing the bright and dark areas of the fingerprint image, the authenticity of the finger can be determined, leading to an accurate identification result. Attached Figure Description

[0047] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of the steps of a fingerprint recognition method according to an embodiment of this application;

[0049] Figure 2 This is a schematic diagram of fingerprint image acquisition of a prosthetic finger in an embodiment of this application;

[0050] Figure 3 This is a schematic diagram of the acquisition of a fingerprint image of a real finger in an embodiment of this application;

[0051] Figure 4 This is a schematic diagram of various fingerprint collection areas in the embodiments of this application;

[0052] Figure 5 This is a schematic diagram illustrating two relative positional relationships between dark area images and bright area images in embodiments of this application;

[0053] Figure 6 These are fingerprint images of a real finger before and after image processing in the embodiments of this application;

[0054] Figure 7 These are fingerprint images of a fake finger before and after image processing in the embodiments of this application;

[0055] Figure 8 This is a schematic diagram of the structure of a fingerprint recognition device according to an embodiment of this application;

[0056] Figure 9 This is a schematic diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0057] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0058] Biometric technology has been widely applied to various terminal devices and electronic devices. Biometric identification technologies include, but are not limited to, fingerprint recognition, palmprint recognition, vein recognition, iris recognition, face recognition, liveness detection, and anti-counterfeiting technologies. Fingerprint recognition typically includes optical fingerprint recognition, capacitive fingerprint recognition, and ultrasonic fingerprint recognition. With the rise of full-screen technology, fingerprint recognition modules can be placed in a partial or complete area under the display screen, forming under-display optical fingerprint recognition; alternatively, the optical fingerprint recognition module can be partially or completely integrated into the display screen of the electronic device, forming in-display optical fingerprint recognition. The display screen can be an organic light-emitting diode (OLED) display or a liquid crystal display (LCD), etc. Fingerprint recognition methods typically include fingerprint image acquisition, preprocessing, feature extraction, and feature matching. Some or all of the above steps can be implemented using traditional computer vision (CV) algorithms or deep learning algorithms based on artificial intelligence (AI). Fingerprint recognition technology can be applied to portable or mobile terminals such as smartphones, tablets, and gaming devices, as well as other electronic devices such as smart door locks, cars, and bank ATMs, for fingerprint unlocking, fingerprint payment, fingerprint attendance, and identity authentication.

[0059] With the expansion of fingerprint payment and security functions, preventing fake fingerprint attacks has become an urgent problem to solve. Currently, most fingerprint protection methods rely on neural network convolutional algorithms. However, this method suffers from poor generalization and cannot address attacks using 2.5D fake fingerprints (e.g., fingerprints created by etching circuit boards) or 3D fake fingerprints. Therefore, a combination of hardware and algorithms is needed to improve the performance of fake fingerprint protection and ensure user information security.

[0060] This invention provides a fingerprint recognition method, referring to... Figure 1 As shown, a flowchart illustrating the steps of a fingerprint recognition method according to an embodiment of this application is illustrated. Figure 1 As shown, this fingerprint recognition method is applied to a terminal device, which has a display screen and a fingerprint module located below the display screen. The terminal device can be a smartphone, tablet, gaming device, or other portable or mobile terminal, as well as a smart lock, car, bank ATM, or other electronic devices. The display screen includes a fingerprint acquisition area with bright and dark areas. The fingerprint recognition method includes the following steps:

[0061] Step S11: Obtain the fingerprint image to be identified captured by the fingerprint module for an object above the fingerprint acquisition area when the fingerprint acquisition area is partially illuminated. The bright area is the area where the light-emitting unit is in the illuminating state when the fingerprint acquisition area is partially illuminated, and the dark area is the area where the light-emitting unit is in the extinguished state when the fingerprint acquisition area is partially illuminated.

[0062] Step S12: Based on the bright area image and dark area image contained in the fingerprint image to be identified, obtain the identification result of the object. The bright area image is the image captured by the fingerprint module for the object above the bright area, and the dark area image is the image captured by the fingerprint module for the object above the dark area.

[0063] The terminal device's display screen contains light-emitting units. By applying different driving voltages to each light-emitting unit, it can be determined whether the unit emits light. The display screen also includes a fingerprint sensing area, which partially illuminates during fingerprint sensing. During fingerprint sensing, the areas containing the illuminated units are called bright areas, while the areas containing the off-state light-emitting units are called dark areas. The terminal device also includes a fingerprint module, located below the display screen, typically below the fingerprint sensing area.

[0064] During fingerprint acquisition, the fingerprint acquisition area is partially illuminated. The object (real or artificial finger) is placed above this area, and the fingerprint is identified through the principles of light refraction and reflection. Light shines from the luminescent unit in the fingerprint acquisition area onto the finger. The angle of refraction and the brightness of the reflected light vary depending on the uneven texture of the fingerprint surface. By collecting this information of varying brightness levels, the fingerprint image is acquired.

[0065] Because the fingerprint acquisition area contains both bright and dark areas, the acquired fingerprint image includes both bright and dark area images. The bright area image is the image captured by the fingerprint module for objects above the bright area, and the dark area image is the image captured by the fingerprint module for objects above the dark area.

[0066] Because fake fingers are usually opaque, and the dark area image of a fake finger is below a dark area, the fingerprint pattern of the fake finger cannot obtain light signals. As a result, the fingerprint image of the fake finger captured by the fingerprint module above the dark area has very low brightness and almost no fingerprint texture. Figure 2 The diagram illustrates the acquisition of a fingerprint image from a prosthetic finger. The arrows represent the propagation of light signals. Because the prosthetic finger is opaque, the fingerprint module located below the dark area cannot receive the light signal. Therefore, the fingerprint image of the prosthetic finger above the dark area has very low brightness and almost no fingerprint texture.

[0067] Because real fingers are translucent, even if the dark area beneath a real finger's image is also dark, the light from the bright area is transmitted within the finger, illuminating the dark area. Therefore, the brightness of the fingerprint image captured above the dark area of ​​a real finger will be higher than that of the dark area image of a fake finger, and it will still show the fingerprint texture. The dark area image of a real finger will be slightly less bright than the bright area image. Figure 3 The diagram illustrates the acquisition of a fingerprint image of a real finger. The arrows represent the propagation of light signals. Because a real finger is translucent, the light signal emitted from the bright area illuminates the dark area of ​​the finger. Therefore, the fingerprint module located below the dark area can also receive the light signal. Thus, the fingerprint image of the real finger acquired above the dark area has fingerprint texture.

[0068] Based on the bright and dark areas of the fingerprint image to be identified, it can be determined whether the object is a genuine finger. Furthermore, the fingerprint texture contained in the bright and dark areas can be used to determine whether the object's fingerprint matches that of the target finger. Thus, based on whether the object is a genuine finger and whether its fingerprint matches that of the target finger, the identification result can be obtained. Furthermore, based on the identification result, the next step can be determined, such as whether to unlock, whether to pass verification, or whether to proceed with payment.

[0069] In practical applications, terminal devices can perform fingerprint unlocking, fingerprint payment, fingerprint attendance (i.e., determining that the user of the target finger has arrived at the location where the terminal device is deployed), and identity authentication (i.e., determining that the object is the user of the target finger) when they determine that the object is a real finger and that the fingerprint of the object matches the fingerprint of the target finger.

[0070] Using the technical solution of this application embodiment, when the fingerprint module emits light in the fingerprint acquisition area, it acquires a fingerprint image to be identified for the object above the fingerprint acquisition area, obtaining a fingerprint image to be identified that includes bright area images and dark area images. Therefore, the object identification result can be obtained based on the bright area images and dark area images. The refractive index, reflectivity, and dispersion characteristics of the materials used to make fake fingers differ from those of real fingers. Therefore, the bright area images and dark area images of fake fingers are different from those of real fingers. Thus, by using the bright area images and dark area images contained in the fingerprint image to be identified, the authenticity of the finger can be determined, especially with high accuracy in identifying 2.5D and 3D fake fingers, thereby obtaining accurate identification results.

[0071] Alternatively, the bright areas in the fingerprint acquisition area can surround the dark areas so that objects located above the dark areas can receive light signals from the surrounding bright areas.

[0072] Alternatively, the fingerprint collection area may be a dark area surrounding a bright area, or the dark area may be located on one side of the bright area.

[0073] Optionally, the dark area can be located in the center of the bright area, so that the light signal from the bright area can be transmitted more concentratedly to the object located above the dark area. Optionally, the dark area may not be located in the center of the bright area.

[0074] Optionally, depending on actual needs, the dark area can be a single region or multiple disconnected sub-dark areas. The dark area can be circular or other shapes. The fingerprint collection area can be circular or other shapes.

[0075] Figure 4 The diagram shows various fingerprint acquisition areas. 4A, 4B, 4C, 4D, 4E, and 4F in the diagram are each a fingerprint acquisition area. The black areas in the fingerprint acquisition areas are dark areas, and the areas outside the black areas are bright areas.

[0076] Optionally, depending on different needs, the bright area image can be all image regions in the fingerprint image to be identified, excluding the dark area image, or it can be the middle image region among the remaining image regions in the fingerprint image to be identified, excluding the dark area image. The shape of the middle image region can be circular, rectangular, or other shapes. Figure 5 The diagram illustrates two relative positional relationships between dark and bright area images. In the left image, the bright area image represents all image regions in the fingerprint image to be identified, excluding the dark area image. In the right image, the bright area image represents the central circular image region among the remaining image regions in the fingerprint image to be identified, excluding the dark area image.

[0077] If the bright area image comprises all image regions in the fingerprint image excluding the dark areas, data is not wasted. Because the data at the edges of the fingerprint image is darker and has less effective fingerprint data, if the bright area image comprises the middle image region of the remaining image region excluding the dark areas, computational resources can be saved, and the recognition result of the obtained object can be more accurate.

[0078] Optionally, the size of the dark area should meet the following condition: the dark area of ​​the fingerprint image captured by the fingerprint module for a genuine finger must have fingerprint texture. Because light signals gradually attenuate as they travel through a genuine finger, if the dark area is set too large, even if it is a genuine finger, some parts of the dark area of ​​the genuine finger image may not have fingerprint texture. If the dark area is set too small, a fake finger is more likely to be recognized as a genuine finger. Therefore, the size of the dark area should ensure that each image region in the dark area of ​​the genuine finger image captured by the fingerprint module has fingerprint texture.

[0079] Optionally, the diameter of the dark area can be 5-15 light-emitting units, or 0.3-6 mm.

[0080] Optionally, based on the above technical solution, after obtaining the fingerprint image to be identified, the bright area image and dark area image contained in the fingerprint image to be identified can be determined according to the following steps: obtaining the code value of each pixel in the fingerprint image to be identified; obtaining the boundary line between the bright area image and the dark area image based on the code value of each pixel and the code values ​​of its neighboring pixels; obtaining the bright area image and the dark area image based on the boundary line between the bright area image and the dark area image.

[0081] The code value of a pixel can be obtained by multiplying the light intensity sensed by that pixel by the photoelectric conversion coefficient. The neighborhood of a pixel refers to the region within a certain distance centered on that pixel, such as a rectangular or circular region. Neighboring pixels of a pixel are other pixels located within the neighborhood of that pixel.

[0082] Because dark areas have lower brightness, the boundary between bright and dark areas can be determined by comparing the code value of each pixel in the fingerprint image with the code values ​​of its neighboring pixels. For example, the boundary can be determined by calculating the difference or gradient of the code values ​​of pixels. If the difference or gradient between a pixel's code value and its neighboring pixels is large, that pixel is likely the boundary between the bright and dark areas. Alternatively, the fingerprint image can be input into an image segmentation model, which directly outputs the bright and dark areas using a neural network segmentation algorithm. The training method for the image segmentation model can refer to relevant technologies, and this invention does not limit its scope.

[0083] Compared to determining the boundary between bright and dark areas of an image based on the code value of each pixel and the code values ​​of its neighboring pixels, determining the boundary between bright and dark areas based on the code value of each pixel and the code values ​​of its neighboring pixels can avoid errors caused by noise.

[0084] Optionally, since the bright area image is the image captured by the fingerprint module for the object above the bright area, and the dark area image is the image captured by the fingerprint module for the object above the dark area, the bright and dark areas in the fingerprint acquisition area can be mapped onto the fingerprint image to be identified, thereby determining which part of the fingerprint image to be identified is the bright area image and which part is the dark area image.

[0085] Optionally, based on the above technical solution, the object recognition result obtained from the bright area image and dark area image contained in the fingerprint image to be identified may include a genuine recognition result indicating whether the object is a real finger, or a matching recognition result indicating whether the fingerprint of the object matches the fingerprint of the target finger.

[0086] The determination of whether an object is genuine or fake is based on the relative relationship between the bright and dark areas of the image. The fingerprint image to be identified can be input into a neural network model, which can directly determine the authenticity of the object based on the relative relationship between the bright and dark areas.

[0087] While the brightness of the dark areas in a real finger's image is slightly lower than that of the bright areas, it is still higher than that of the dark areas in a fake finger's image. Therefore, the relative brightness relationship between the bright and dark areas of a real finger's image differs from that of a fake finger's image. Consequently, the real / fake identification result can be obtained based on the relative brightness relationship between the bright and dark areas of the object's image.

[0088] The matching and recognition result of an object can be obtained by matching the fingerprint image to be identified with the fingerprint image of the target finger. The fingerprint of the target finger can be a pre-recorded fingerprint that can successfully pass fingerprint recognition and proceed to the next step. The fingerprint of the target finger can be a clear and distinct fingerprint, or it can be a fingerprint of the target finger acquired when the entire fingerprint acquisition area is illuminated. There can be one or more fingerprints of the target finger. If there are multiple fingerprints of the target finger, the matching and recognition result is considered successful as long as the fingerprint image to be identified successfully matches any of the fingerprints of the target finger.

[0089] Because the dark areas of the fingerprint image to be identified have low brightness, directly using the fingerprint image to obtain the matching result of the object is very likely to fail. Therefore, in order to accurately obtain the matching result of the object, the fingerprint image to be identified can be processed to obtain a fingerprint image with uniform brightness, that is, a fingerprint image to be identified that eliminates dark spots in the dark areas.

[0090] Figure 6 The image shows fingerprint images of a real finger before and after image processing. The left side shows the image before image processing, and the right side shows the image after image processing. Figure 7The image shows fingerprint images of a fake finger before and after image processing. The left image is before processing, and the right image is after processing. Because the dark areas of a real finger actually contain fingerprint texture, the fingerprint texture is clearly visible in the uniformly bright image obtained after image processing of the real finger's fingerprint image. Conversely, because the dark areas of a fake finger do not actually contain fingerprint texture, the uniformly bright image obtained after image processing of the fake finger's fingerprint image not only lacks fingerprint texture in the dark areas, but also has its original fingerprint texture in the bright areas blurred.

[0091] After obtaining a uniformly bright fingerprint image to be identified, the matching and identification result of the object is obtained using the uniformly bright fingerprint image to be identified. Optionally, image feature points of the uniformly bright fingerprint image to be identified and image feature points of the fingerprint image of the target finger can be obtained; it is determined whether the image feature points of the uniformly bright fingerprint image to be identified match the image feature points of the fingerprint image of the target finger; if the image feature points of the uniformly bright fingerprint image to be identified match the image feature points of the fingerprint image of the target finger, the matching of the image to be identified and the fingerprint image of the target finger is determined to be successful; if the image feature points of the uniformly bright fingerprint image to be identified and the fingerprint image of the target finger do not match, the matching of the image to be identified and the fingerprint image of the target finger is determined to be unsuccessful. Optionally, the two images (the uniformly bright fingerprint image to be identified and the fingerprint image of the target finger) can also be directly compared to obtain the matching and identification result of the object.

[0092] Thus, the fingerprint texture in the uniformly bright fingerprint image obtained after image processing is clearer, and therefore, obtaining the matching and recognition results of the object based on the uniformly bright fingerprint image has the advantage of being more accurate.

[0093] Optionally, depending on different needs, when obtaining the recognition result of an object based on the fingerprint image to be recognized, one can first obtain the true or false recognition result of the object, and then obtain the matching recognition result of the object; or one can first obtain the matching recognition result of the object, and then obtain the true or false recognition result of the object; or one can only obtain the true or false recognition result of the object, or only obtain the matching recognition result of the object.

[0094] To improve the security and accuracy of fingerprint recognition, if the true / false recognition result of the object is obtained first, and then the matching recognition result of the object is obtained, then if the true / false recognition result of the object indicates that the object is a fake finger, then it is not necessary to obtain the matching recognition result of the object. It is only meaningful to obtain the matching recognition result of the object if the true / false recognition result of the object indicates that the object is a real finger.

[0095] Similarly, if the matching and identification results of the object are obtained first, and then the true and false identification results of the object are obtained, if the matching and identification results of the object indicate that the fingerprint of the object does not match the fingerprint of the target finger, then it is not necessary to obtain the true and false identification results of the object. It is only meaningful to obtain the true and false identification results of the object if the matching and identification results of the object indicate that the fingerprint of the object matches the fingerprint of the target finger.

[0096] Optionally, the relative relationship between the bright and dark areas can be determined based on the brightness ratio between the bright and dark areas, or it can be determined based on the brightness difference between the bright and dark areas. The brightness of the bright area image can be determined by the average brightness of each pixel in the bright area image, and the brightness of the dark area image can be determined by the average brightness of each pixel in the bright area image.

[0097] Optionally, the brightness of a bright area image can be determined by the code values ​​of all or some of the pixels in the bright area image, and the brightness of a dark area image can be determined by the code values ​​of all or some of the pixels in the dark area image. The code value of a pixel can be obtained by multiplying the light intensity sensed by that pixel by the photoelectric conversion coefficient.

[0098] Optionally, the average code value of the bright region image is obtained based on the code value of each pixel in the bright region image; the average code value of the dark region image is obtained based on the code value of each pixel in the dark region image; and the brightness ratio of the bright region image to the dark region image is obtained based on the average code value of the bright region image and the average code value of the dark region image.

[0099] Optionally, the average code value of the bright area image is obtained based on the code values ​​of some pixels in the bright area image; the average code value of the dark area image is obtained based on the code values ​​of some pixels in the dark area image; and the brightness ratio of the bright area image to the dark area image is obtained based on the average code values ​​of the bright area image and the average code value of the dark area image.

[0100] Optionally, if the brightness ratio of the bright area image to the dark area image is within a brightness ratio threshold range, the object is determined to be a genuine finger. If the brightness ratio of the bright area image to the dark area image is not within the brightness ratio threshold range, the object is determined to be a fake finger. The brightness ratio threshold range is determined based on the brightness ratio of the dark area and bright area of ​​the genuine finger image captured by the fingerprint module for a genuine finger. The brightness ratio threshold range can be pre-acquired and stored in a database.

[0101] In this way, the brightness ratio between the bright and dark areas of the image can be used to determine whether the object is a real finger, thereby effectively improving the security of fingerprint recognition and preventing fake finger attacks.

[0102] Optionally, if the brightness difference between the bright and dark areas of the image is within a brightness difference threshold range, the object is determined to be a genuine finger. If the brightness difference is outside the brightness difference threshold range, the object is determined to be a fake finger. The brightness difference threshold range is determined based on the brightness difference between the dark and bright areas of the genuine finger image captured by the fingerprint module. The brightness difference threshold range can be pre-acquired and stored in a database.

[0103] In this way, the difference in brightness between the bright and dark areas of the image can be used to determine whether the object is a real finger, thereby effectively improving the security of fingerprint recognition and preventing fake finger attacks.

[0104] Optionally, based on the above technical solutions, neural network convolutional AI algorithms and the relative relationship between bright and dark area images can be combined to obtain the result of object authenticity recognition.

[0105] The fingerprint image to be identified can be input into a fingerprint recognition model to detect whether the object is real or fake, and obtain the first result of the object's real or fake identification. The fingerprint recognition model can be trained using fingerprint image samples from real fingers and fingerprint image samples from fake fingers, and this application does not limit the training method.

[0106] A second result for determining whether an object is real or fake can be obtained based on the relative relationship between the bright and dark areas of the image. The method for obtaining this second result can refer to the method described above.

[0107] By combining the first and second true / false identification results, the true / false identification result of the object can be obtained. Optionally, the first and second true / false identification results can be weighted, and the true / false identification result of the object can be obtained based on the weighted first and second true / false identification results.

[0108] Thus, by combining the true / false identification model with the relative relationship between bright and dark area images, the obtained object authenticity identification results are more accurate, which is beneficial to improving the security of fingerprint recognition. Compared with using only the true / false identification model to detect the authenticity of objects, this greatly improves the model's generalization and applicability, reduces model resource investment, and shortens the product development cycle.

[0109] Optionally, based on the above technical solution, when the fingerprint module emits light in the fingerprint acquisition area, it can acquire a single-frame image of the object above the fingerprint acquisition area for fingerprint recognition. This single-frame image can be directly used as the fingerprint image to be recognized. Alternatively, multiple frames can be acquired. In the case of acquiring multiple frames, the multiple frames can be fused to obtain the fingerprint image to be recognized, and then fingerprint recognition can be performed using this fingerprint image.

[0110] In this way, the fingerprint image obtained by fusing multiple frames will contain clearer textures, making it more accurate for subsequent fingerprint recognition.

[0111] Optionally, when multiple frames of images are acquired, each frame can be used as a fingerprint image to be identified, and the identification result of each fingerprint image can be obtained. Then, a weighted average can be performed based on the identification results of each fingerprint image to obtain the identification result of the object.

[0112] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of the present invention are not limited to the described order of actions, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions involved are not necessarily essential to the embodiments of the present invention.

[0113] Figure 8 This is a schematic diagram of the structure of a fingerprint recognition device according to an embodiment of this application. The fingerprint recognition device is applied to a terminal device, which has a display screen and a fingerprint module located below the display screen. The display screen includes a fingerprint acquisition area with bright and dark areas, such as... Figure 8 As shown, the fingerprint recognition device includes a fingerprint image acquisition module and a recognition result acquisition module, wherein:

[0114] A fingerprint image acquisition module is used to acquire a fingerprint image to be identified for an object above the fingerprint acquisition area when the fingerprint module emits light in the fingerprint acquisition area. The bright area is the area where the light-emitting unit is in the light-emitting state when the fingerprint acquisition area is partially illuminated, and the dark area is the area where the light-emitting unit is in the light-off state when the fingerprint acquisition area is partially illuminated.

[0115] The recognition result acquisition module is used to obtain the recognition result of the object based on the bright area image and dark area image contained in the fingerprint image to be recognized. The bright area image is the image captured by the fingerprint module for the object above the bright area, and the dark area image is the image captured by the fingerprint module for the object above the dark area.

[0116] Optionally, the recognition result acquisition module includes:

[0117] The real / fake identification result acquisition submodule is used to obtain the real / fake identification result of the object based on the relative relationship between the bright area image and the dark area image, wherein the real / fake identification result characterizes whether the object is a real finger; and / or

[0118] The matching recognition result acquisition submodule is used to obtain the matching recognition result of the object based on the fingerprint image to be identified. The matching recognition result indicates whether the fingerprint of the object matches the fingerprint of the target finger.

[0119] Optionally, the submodule for obtaining the true / false identification result includes:

[0120] A brightness ratio acquisition unit is used to determine the brightness ratio between the bright area image and the dark area image;

[0121] A genuine finger identification unit is used to determine that the object is a genuine finger when the brightness ratio is within a brightness ratio threshold range. The brightness ratio threshold range is determined based on the brightness ratio of the dark area genuine finger image and the bright area genuine finger image in the genuine finger fingerprint image collected by the fingerprint module for genuine fingers.

[0122] A fake finger determination unit is used to determine that the object is a fake finger when the brightness ratio is outside the brightness ratio threshold range.

[0123] Optionally, the brightness ratio acquisition unit includes:

[0124] The code value acquisition subunit is used to acquire the code value of each pixel in the bright area image and the code value of each pixel in the dark area image;

[0125] The bright region average code value acquisition subunit is used to obtain the average code value of the bright region image based on the code value of each pixel in the bright region image;

[0126] The dark region average code value acquisition subunit is used to obtain the average code value of the dark region image based on the code value of each pixel in the dark region image.

[0127] The brightness ratio acquisition subunit is used to obtain the brightness ratio of the bright area image and the dark area image based on the average code value of the bright area image and the average code value of the dark area image.

[0128] Optionally, the matching recognition result acquisition submodule includes:

[0129] An image processing unit is used to perform image processing on the fingerprint image to be identified to obtain a fingerprint image with uniform brightness.

[0130] The matching and recognition result acquisition unit is used to obtain the matching and recognition result of the object based on the uniformly bright fingerprint image to be identified.

[0131] Optionally, it also includes:

[0132] The first true / false identification result acquisition module is used to perform true / false detection on the object based on the fingerprint image to be identified and using a true / false identification model to obtain the first true / false identification result of the object.

[0133] The submodule for obtaining the true / false identification result includes:

[0134] The second true / false recognition result acquisition unit is used to obtain the second true / false recognition result of the object based on the relative relationship between the bright area image and the dark area image;

[0135] The module for obtaining the combined true / false identification results is used to obtain the true / false identification result of the object based on the first true / false identification result and the second true / false identification result.

[0136] Optionally, the fingerprint image acquisition module includes:

[0137] The multi-frame image acquisition submodule is used to acquire multiple frames of images of an object above the fingerprint acquisition area when the fingerprint module emits light in the fingerprint acquisition area.

[0138] The image fusion submodule is used to fuse the multiple frames of images to obtain the fingerprint image to be identified.

[0139] Optionally, the bright area image and dark area image included in the fingerprint image to be identified are obtained according to the following steps:

[0140] Obtain the code value of each pixel in the fingerprint image to be identified;

[0141] Based on the code value of each pixel and the code values ​​of its neighboring pixels, the boundary line between the bright area image and the dark area image is obtained;

[0142] The bright area image and the dark area image are obtained based on the boundary line between the bright area image and the dark area image.

[0143] Optionally, the bright area surrounds the dark area.

[0144] Optionally, the dark area is located in the central region of the bright area.

[0145] Optionally, the dark region includes multiple non-connected sub-dark regions.

[0146] Optionally, the bright area refers to all areas of the fingerprint acquisition area except for the dark area; or

[0147] The bright area is the middle area of ​​the remaining area in the fingerprint acquisition area, excluding the dark area.

[0148] Optionally, the size of the dark area satisfies the condition that the fingerprint module has fingerprint texture in the dark area of ​​the real finger fingerprint image collected from the real finger.

[0149] Optionally, the diameter of the dark area is 5-15 light-emitting units; or

[0150] The diameter of the dark area is 0.3-6 mm.

[0151] It should be noted that the device embodiments are similar to the method embodiments, so the description is relatively simple. For relevant details, please refer to the method embodiments.

[0152] This invention also provides an electronic device, with reference to... Figure 9 , Figure 9 This is a schematic diagram of the electronic device proposed in an embodiment of this application. Figure 9 As shown, the electronic device 100 includes a memory 110 and a processor 120. The memory 110 and the processor 120 are connected via a bus. The memory 110 stores a computer program that can run on the processor 120 to implement the steps in the fingerprint recognition method disclosed in the embodiments of this application.

[0153] This invention also provides a computer-readable storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the fingerprint recognition method disclosed in the embodiments of this application.

[0154] This invention also provides a computer program product, including a computer program / instructions that, when executed by a processor, implement the fingerprint recognition method disclosed in the embodiments of this application.

[0155] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0156] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, apparatus, or computer program products. Therefore, embodiments of the present invention can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, embodiments of the present invention can take the form of computer program products implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0157] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, apparatuses, electronic devices, and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0158] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0159] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal equipment, causing a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0160] Although preferred embodiments of the present invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the present invention.

[0161] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0162] The fingerprint recognition method, electronic device, storage medium, and program product provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method of fingerprint recognition, characterized by, The method is applied to a terminal device having a display screen and a fingerprint module located below the display screen, the display screen comprising a fingerprint collection area having a bright area and a dark area, and the method comprises: obtaining a to-be-identified fingerprint image collected by the fingerprint module for an object above the fingerprint collection area when the fingerprint collection area partially emits light, the bright area being an area where light-emitting units in the emitting state are located when the fingerprint collection area partially emits light, and the dark area being an area where light-emitting units in the extinguishing state are located when the fingerprint collection area partially emits light; obtaining an identification result of the object according to a bright area image and a dark area image contained in the to-be-identified fingerprint image, the bright area image being an image collected by the fingerprint module for the object above the bright area, and the dark area image being an image collected by the fingerprint module for the object above the dark area; obtaining an identification result of the object according to a bright area image and a dark area image contained in the to-be-identified fingerprint image, comprising: obtaining a true-false identification result of the object according to a relative relationship between the bright area image and the dark area image, the true-false identification result representing whether the object is a real finger; obtaining a matching identification result of the object according to the to-be-identified fingerprint image, the matching identification result representing whether a fingerprint of the object matches a fingerprint of a target finger; and the relative relationship comprising a brightness relative relationship between the bright area image and the dark area image of the object; obtaining a true-false identification result of the object according to a relative relationship between the bright area image and the dark area image, comprising: determining a brightness ratio of the bright area image to the dark area image; in a case where the brightness ratio is within a brightness ratio threshold range, determining that the object is a real finger, the brightness ratio threshold range being determined according to a brightness ratio of a dark area real finger image to a bright area real finger image in a real finger fingerprint image collected by the fingerprint module for a real finger; in a case where the brightness ratio is outside the brightness ratio threshold range, determining that the object is a fake finger.

2. The method of claim 1, wherein, determining a brightness ratio of the bright area image to the dark area image, comprising: obtaining code values of at least some pixel points in the bright area image and code values of at least some pixels in the dark area image; obtaining an average code value of the bright area image according to the code values of the at least some pixel points in the bright area image, and obtaining an average code value of the dark area image according to the code values of the at least some pixel points in the dark area image; obtaining the brightness ratio of the bright area image to the dark area image according to the average code value of the bright area image and the average code value of the dark area image.

3. The method of claim 1, wherein, obtaining a matching identification result of the object according to the to-be-identified fingerprint image, comprising: performing image processing on the to-be-identified fingerprint image to obtain a to-be-identified fingerprint image with uniform brightness; obtaining the matching identification result of the object according to the to-be-identified fingerprint image with uniform brightness.

4. The method of claim 1, wherein, Further comprising: performing true-false detection on the object by using a true-false identification model based on the to-be-identified fingerprint image, to obtain a first true-false identification result of the object; obtaining a true-false identification result of the object according to the relative relationship between the bright area image and the dark area image, comprising: obtaining a second true-false identification result of the object according to the relative relationship between the bright area image and the dark area image; obtaining a true-false identification result of the object according to the first true-false identification result and the second true-false identification result.

5. The method according to any of claims 1-4, characterized by, obtaining a to-be-identified fingerprint image of an object above the fingerprint collection area when the fingerprint module partially emits light in the fingerprint collection area, comprising: obtaining a to-be-identified fingerprint image of an object above the fingerprint collection area when the fingerprint module partially emits light in the fingerprint collection area, comprising: performing image fusion on the multiple frames of images to obtain the to-be-identified fingerprint image.

6. The method according to any of claims 1-5, characterized by, The bright area image and the dark area image contained in the to-be-identified fingerprint image are obtained according to the following steps: obtaining the code value of each pixel point in the to-be-identified fingerprint image; obtaining the boundary line of the bright area image and the dark area image according to the code value of each pixel point and the code value of the neighborhood pixel points thereof; obtaining the bright area image and the dark area image according to the boundary line of the bright area image and the dark area image.

7. The method according to any of claims 1-6, characterized by, The bright area surrounds the dark area.

8. The method according to any of claims 1-7, characterized by, The dark area is located in the central region of the bright area.

9. The method according to any of claims 1-8, characterized by, The dark area includes multiple unconnected sub-dark areas.

10. The method of any of claims 1-9, wherein, The bright area image is all image regions in the to-be-identified fingerprint image except the dark area image; or The bright area image is the middle image region of the remaining image region in the to-be-identified fingerprint image except the dark area image.

11. The method of any of claims 1-10, wherein, The size of the dark area satisfies the condition that a dark area true-finger image in a true-finger fingerprint image collected by the fingerprint module for a true finger has fingerprint texture.

12. The fingerprint identification method according to any one of claims 1-11, characterized in that, The diameter size of the dark area is 5-15 light-emitting units; or The diameter size of the dark area is 0.3-6 millimeters.

13. An electronic device comprising a memory, a processor, and a computer program stored on the memory, wherein the computer program comprises instructions that, when executed by the processor, cause the electronic device to perform the method of any one of claims 1-12. The processor executes the computer program to implement the fingerprint identification method according to any one of claims 1-12.

14. A computer readable storage medium having stored thereon computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the fingerprint identification method according to any one of claims 1-12.

15. A computer program product comprising computer programs / instructions, characterized in that, The computer program / instruction is executed by the processor to implement the fingerprint identification method according to any one of claims 1-12.

Images