Identity verification method and device, terminal, storage medium and program product

Abstract

The embodiment of the invention discloses an identity verification method and device, a terminal, a storage medium and a program product, and belongs to the technical field of identity recognition. The method comprises the steps of collecting a fingerprint image of a finger and a capacitance signal generated when the finger is in contact with a fingerprint verification area under the condition that a touch operation on the fingerprint verification area is received; and performing identity verification based on the collected fingerprint image and the capacitance signal to obtain an identity verification result. By adopting the scheme provided by the embodiment of the invention, identity verification can be carried out based on a method of combining the fingerprint image and the capacitance signal, so that the success rate of identity verification is improved.

Description

Technical Field

[0001] Embodiments of the present application relate to the field of identity recognition technology, and particularly to an identity verification method, device, terminal, storage medium and program product. Background Art

[0002] Nowadays, when a smart terminal performs identity verification, it usually provides a fingerprint verification function. For example, during the process of screen unlocking or payment verification, the fingerprint verification function is used.

[0003] In the related art, when performing fingerprint verification, a fingerprint image is collected by a fingerprint collector, and then image feature extraction is performed on the fingerprint image collected by the fingerprint collector to obtain useful morphological features. Finally, the feature information extracted from the fingerprint image is matched with the fingerprint features stored in the database to determine the identity.

[0004] However, since a user may be in a wet hand state when performing identity verification in daily life, in this case, the fingerprint feature points in the fingerprint image collected by the fingerprint collector are relatively blurred, so the success rate of fingerprint recognition is low, and the applicability of the solution provided by the related art is poor. Summary of the Invention

[0005] Embodiments of the present application provide an identity verification method, device, terminal, storage medium and program product. The technical solution is as follows:

[0006] On the one hand, embodiments of the present application provide an identity verification method, the method comprising:

[0007] When a touch operation on the fingerprint verification area is received, collecting a fingerprint image of a finger and a capacitance signal generated by the contact between the finger and the fingerprint verification area;

[0008] Performing identity verification based on the collected fingerprint image and the capacitance signal to obtain an identity verification result.

[0009] On the other hand, embodiments of the present application provide an identity verification device, the device comprising:

[0010] A collection module, configured to collect a fingerprint image of a finger and a capacitance signal generated by the contact between the finger and the fingerprint verification area when a touch operation on the fingerprint verification area is received;

[0011] A verification module, configured to perform identity verification based on the collected fingerprint image and the capacitance signal to obtain an identity verification result.

[0012] On the other hand, an embodiment of the present application provides a terminal, which includes a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the authentication method as described in the above aspect.

[0013] On the other hand, an embodiment of the present application provides a computer-readable storage medium, in which at least one program code is stored, and the program code is loaded and executed by a processor to implement the authentication method as described in the above aspect.

[0014] On the other hand, an embodiment of the present application provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the authentication method provided in various optional implementations of the above aspect.

[0015] In an embodiment of the present application, when a touch operation on a fingerprint verification area is received, a fingerprint image and a capacitance signal are collected, and then authentication is performed based on the fingerprint image and the capacitance signal. The capacitance signal is introduced into the authentication to enhance the success rate of biometric recognition unlocking. Thus, when the collected fingerprint image is incomplete or unclear, the capacitance signal is combined for authentication to ensure the success rate of authentication. For example, when a user touches the fingerprint verification area with wet hands, the collected fingerprint image may have blurred areas at this time. Combining the collected capacitance signal for authentication at this time can make up for the problem of missing fingerprint features in the blurred areas of the fingerprint image caused by wet hands, thereby improving the success rate of fingerprint recognition in the wet hand state. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 Shows a schematic diagram of a process for obtaining fingerprint feature data;

[0018] Figure 2 Shows a flowchart of an authentication method provided by an exemplary embodiment of the present application;

[0019] Figure 3 Shows a schematic diagram of the process for inputting a capacitance signal template and the process for matching capacitance signal features provided by an exemplary embodiment of the present application;

[0020] Figure 4 Shows a schematic diagram of the collected capacitance signal provided by an exemplary embodiment of the present application;

[0021] Figure 5 Shows a flowchart of obtaining the first matching score provided by an exemplary embodiment of the present application;

[0022] Figure 6 Shows a flowchart of the process of performing image feature matching provided by an exemplary embodiment of the present application;

[0023] Figure 7 Shows a schematic diagram of the segmentation of the user fingerprint image area provided by an exemplary embodiment of the present application;

[0024] Figure 8 Shows a flowchart of image feature matching provided by an exemplary embodiment of the present application;

[0025] Figure 9 Shows a flowchart of the authentication process provided by an exemplary embodiment of the present application;

[0026] Figure 10 Shows a flowchart of the authentication process provided by another exemplary embodiment of the present application;

[0027] Figure 11 Shows a flowchart of the authentication process provided by another exemplary embodiment of the present application;

[0028] Figure 12 Shows a flowchart of the authentication process provided by another exemplary embodiment of the present application;

[0029] Figure 13 Shows a block diagram of the authentication device provided by an embodiment of the present application;

[0030] Figure 14 Shows a block diagram of the structure of the terminal provided by an exemplary embodiment of the present application. Detailed implementation manners

[0031] To make the objectives, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0032] Nowadays, to ensure information security, it is usually necessary to authenticate users to confirm whether the user identity has certain permissions. Since the fingerprints of different users are different, fingerprint recognition can be used as a common method for identity authentication.

[0033] The fingerprint recognition process mainly includes three steps: fingerprint acquisition, feature extraction, and pattern matching. Fingerprint acquisition refers to placing the finger of the person to be identified on a fingerprint acquisition device, and collecting the fingerprint image through an optical or electronic sensor. The optical fingerprint acquisition device uses a camera to collect the fingerprint image, while the electronic sensor uses sensors such as capacitance and thermosensitivity to collect fingerprint information. The collected fingerprint image will be sent to the fingerprint recognition system for feature extraction and pattern matching.

[0034] After the fingerprint image is collected, feature extraction will be performed on the fingerprint image to extract useful morphological features from the fingerprint image for subsequent fingerprint matching. The morphological features of fingerprints mainly include three basic types: arch, loop, and arch-loop mixture. During the feature extraction process, preprocessing will be performed on the fingerprint image, such as noise removal and image enhancement, and then algorithms such as filtering, segmentation, and thinning will be used to extract the features in the fingerprint image. Common feature extraction algorithms include orientation image, octree, Gabor filter, etc.

[0035] After the fingerprint feature data is extracted, it needs to be compared with the fingerprint features stored in the database to determine the identity of the fingerprint. During the pattern matching process, it is necessary to first preprocess the collected fingerprint image, such as removing noise and enhancing the image, and then compare the preprocessed fingerprint image with the stored fingerprint features to find the corresponding fingerprint features from the stored fingerprint features and determine its identity.

[0036] Figure 1 A schematic diagram showing a process of obtaining fingerprint feature data is shown. After the fingerprint image is obtained, fingerprint feature points are found from the fingerprint image based on the morphological features of the fingerprint, and feature extraction is performed based on the determined fingerprint feature points to obtain fingerprint feature data.

[0037] However, in some cases, due to different fingerprint verification scenarios and different placement methods and positions of the finger during fingerprint verification, the fingerprint image collected by the fingerprint acquisition device may be incomplete or there may be a blurred area. For example, when the user places a wet finger on the fingerprint acquisition device, the collected fingerprint image may be blurred. In this case, the blurred fingerprint image will cause great difficulties in fingerprint recognition, resulting in a decrease in the success rate of fingerprint recognition.

[0038] Therefore, the embodiments of the present application provide an identity verification method, which combines the fingerprint image with the capacitance signal to ensure the success rate of identity verification when the fingerprint image is blurred, especially the success rate of identity verification with a wet finger.

[0039] In a possible implementation, the authentication method provided by the embodiments of the present application can be applied to computer network security scenarios, financial transaction scenarios, personnel management, permission management, etc. For example, in a computer network security scenario, the method provided by the embodiments of the present application is used on a computer for authentication in combination with traditional identity authentication to prevent security threats when website passwords or passwords are stolen. For another example, in a financial transaction scenario, when conducting identity authentication in institutions such as banks or during mobile payments, security verification is performed by acquiring the fingerprint image of the user's finger and the capacitance signal generated by the contact between the finger and the fingerprint acquisition area. For another example, in a personnel management scenario, the method provided by the embodiments of the present application is used to manage personnel, attendance, database access permissions, etc.

[0040] In a possible implementation, the authentication scheme adopted by the present application is applied to various authentication devices providing fingerprint verification functions, such as smart terminals, fingerprint verifiers, etc., and a fingerprint verification area is provided in the authentication device. A node capacitance array is provided in the fingerprint verification area to acquire capacitance signals. In the following embodiments, taking the application to a smart terminal as an example is intended to illustrate the scheme provided by the embodiments of the present application.

[0041] Figure 2 The flowchart of the authentication method provided by an exemplary embodiment of the present application is shown. The method includes:

[0042] Step 201, when a touch operation on the fingerprint verification area is received, acquire the fingerprint image of the finger and the capacitance signal generated by the contact between the finger and the fingerprint verification area.

[0043] There is a node capacitance at each intersection of two sets of electrodes that intersect vertically on a capacitive touch screen. The node capacitances at all intersections can form a node capacitance array. In this node array, the capacitance signal of each node capacitance is used to describe the capacitance magnitude of the node capacitance. When the finger contacts the fingerprint verification area, the capacitive sensor acquires the capacitance signal based on the characteristic that the capacitance voltages generated by the fingerprint ridges and valleys on the node array are different.

[0044] Optionally, through optical screen fingerprint recognition, when the finger presses the screen, the screen emits light to illuminate the finger area, and the reflected light that illuminates the fingerprint returns to the sensor closely attached under the screen through the gaps between the screen pixels, thereby obtaining the fingerprint image.

[0045] Step 202, perform identity authentication based on the acquired fingerprint image and capacitance signal to obtain an identity authentication result.

[0046] The process of performing identity verification based on the collected fingerprint image and capacitance signal is to match the fingerprint image with the previously recorded fingerprint image template and match the capacitance signal with the pre-recorded capacitance signal template to obtain different matching results, thereby obtaining the identity verification result.

[0047] In summary, in the embodiment of the present application, when a touch operation on the fingerprint verification area is received, a fingerprint image and a capacitance signal are collected, and then identity verification is performed based on the fingerprint image and the capacitance signal. The capacitance signal is introduced into the identity verification to enhance the success rate of biometric unlocking. Thus, when the collected fingerprint image is incomplete or unclear, the capacitance signal is combined for identity verification to ensure the success rate of identity verification. For example, when a user touches the fingerprint verification area with wet hands, the collected fingerprint image may have blurred areas. At this time, combining the collected capacitance signal for identity verification can make up for the lack of fingerprint features in the blurred areas of the fingerprint image caused by wet hands, thereby improving the success rate of fingerprint recognition in the wet hand state.

[0048] Before performing identity verification based on the fingerprint image and the capacitance signal, it is necessary to first record the fingerprint image template and the capacitance signal template that are allowed to pass the verification, and then verify the collected capacitance signal and fingerprint image to obtain the identity verification result.

[0049] Before performing identity verification, the fingerprint image template and the capacitance signal template corresponding to the user's finger are recorded. First, the fingerprint image template of the finger performing the touch operation on the fingerprint verification area and the capacitance signal template generated by the contact between the finger and the fingerprint verification area are collected. After the capacitance signal template and the fingerprint image template are collected, feature extraction is respectively performed on the fingerprint image template and the capacitance signal template to obtain the capacitance signal feature template and the fingerprint image feature template. Finally, the fingerprint image feature template and the capacitance signal feature template are saved for feature matching of the fingerprint image feature and the capacitance signal feature.

[0050] Figure 3 The figure shows a schematic diagram of the input process of the capacitance signal template and the matching process of the capacitance signal template provided by an exemplary embodiment of the present application. In the input process, the capacitance signal template generated by the contact between the finger and the fingerprint verification area is collected, and then the capacitance signal feature is generated according to the capacitance signal template, and finally the feature is saved as the capacitance signal feature template. In the matching process, first, the capacitance signal generated by the contact between the finger and the fingerprint verification area is collected, and then feature extraction is performed on the capacitance signal to obtain the capacitance signal feature. Then, the capacitance signal feature is matched with the capacitance signal feature template to obtain the matching score.

[0051] Specifically, the extraction of features from the capacitance signal template and the capacitance signal can be based on multiple frames of capacitance signals collected.

[0052] In a possible implementation, the fingerprint verification area is composed of a node capacitance array. The node capacitance array includes at least two node capacitances, and at least two frames of capacitance signals generated by the contact between the finger and the fingerprint verification area are collected. Each frame of capacitance signal includes capacitance signals corresponding to at least two node capacitances. Figure 4 The figure shows a schematic diagram of the collected capacitance signals provided by an exemplary embodiment of the present application, which includes multiple frames of capacitance signals. Different capacitance signals include capacitance signal data corresponding to different node capacitances. The capacitance signal data is used to characterize the strength of the capacitance signal, and the degree of contact between the fingerprint and the screen can be characterized by the magnitude of this value, that is, the degrees of contact between the fingerprint ridges and valleys and the screen are not the same. Therefore, when the node capacitances are set densely enough, each frame of the collected capacitance signal can characterize the user's fingerprint information. In each frame of capacitance signal, the capacitance signals collected by different node capacitances form a matrix, and the capacitance signal values corresponding to each node capacitance can be normalized to adapt to the capacitance signal deviation generated when the user presses the fingerprint verification area in different ways and at different granularities.

[0053] Optionally, when the fingerprint verification area is a specified area on the screen, the setting density of the capacitance nodes in the fingerprint verification area is higher than that of other screen touch areas.

[0054] Figure 5 The figure shows a flowchart of obtaining the first matching score provided by an exemplary embodiment of the present application. The process includes:

[0055] Step 501, determine the node capacitance signal features of the same node capacitance in at least two frames of collected capacitance signals.

[0056] Among them, the node capacitance signal feature refers to at least one of statistical features, time-domain features, frequency-domain features, and transform features. The statistical features, time-domain features, frequency-domain features, and transform features all refer to the node capacitance signal features of the same node capacitance in at least two frames of collected capacitance signals. For example, when the node capacitance signal feature is a statistical feature, assuming that 20 frames of capacitance signals are collected, for the first node capacitance, it also corresponds to 20 frames of node capacitance signals. Therefore, the statistical features corresponding to the 20 frames of node capacitance signals of the first node capacitance can be determined, such as mean, maximum value, minimum value, etc.

[0057] Step 502, determine the capacitance signal feature based on the arrangement order of the node capacitances in the node capacitance array and the node capacitance signal features corresponding to at least two node capacitances.

[0058] After obtaining the node capacitance signal features corresponding to different node capacitances, the terminal arranges the node capacitance signal features corresponding to different node capacitances into a node capacitance signal feature matrix according to the arrangement order of different node capacitances in the capacitance array, that is, the capacitance signal features are obtained.

[0059] For example, if the node capacitance array includes the first node capacitance to the I-th node capacitance, after determining the first node capacitance signal feature to the I-th node capacitance signal feature corresponding to the first node capacitance to the I-th node capacitance respectively, the node capacitance signal features are arranged into a node capacitance signal feature matrix according to the arrangement order of the first node capacitance to the I-th node capacitance, that is, the capacitance signal features are obtained.

[0060] Step 503, determine the n-th candidate matching score between the n-th capacitance signal feature and the n-th capacitance signal feature template when the node capacitance signal feature is a statistical feature.

[0061] When the node capacitance signal feature is a statistical feature, the capacitance signal corresponds to capacitance signal features of N different statistical feature dimensions, where N is a positive integer. For example, when the node capacitance signal feature is a statistical feature, the capacitance signal may correspond to a mean feature dimension, a maximum value feature dimension, a minimum value feature dimension, and so on.

[0062] The n-th capacitance signal feature template is a capacitance signal feature that allows authentication and corresponds to the n-th capacitance signal feature, where n is greater than 0 and n is less than or equal to N.

[0063] In the case where there are capacitance signal features of different statistical feature dimensions, the terminal also stores capacitance signal feature templates corresponding to capacitance signal features of different statistical feature dimensions. After determining the N capacitance signal features corresponding to the N feature dimensions, the N capacitance signal features are respectively matched with the corresponding N capacitance signal feature templates to obtain N candidate matching scores.

[0064] Step 504, determine the first matching score based on the first candidate matching score to the N-th candidate matching score.

[0065] Optionally, determine the average value of the first candidate matching score to the N-th candidate matching score, and determine this average value as the first matching score.

[0066] Optionally, determine the weighted candidate scores of the first candidate matching score to the N-th candidate matching score, where different candidate matching scores correspond to different weights, and thus determine this weighted candidate score as the first matching score.

[0067] In the embodiments of the present application, feature extraction is performed based on multiple frames of capacitance signals to determine capacitance signal features, so that the obtained capacitance signal features can better represent the features of the capacitance signals generated by the contact between the finger and the fingerprint verification area, and can better represent the fingerprint situation of the current user. Moreover, after determining the capacitance features of multiple statistical dimensions, the first matching score is determined according to the matching scores corresponding to different statistical dimensions, and the determined matching score is more accurate.

[0068] In some embodiments of the present application, in addition to matching the capacitance signals, the fingerprint image features are also matched with the fingerprint image feature template to obtain a matching score. During the process of feature extraction from the fingerprint image, the terminal extracts useful morphological features from the fingerprint image template for feature matching. Similarly, after the fingerprint image is collected, feature extraction is also performed on the fingerprint image to obtain fingerprint image features, and then they are matched with the fingerprint image feature template.

[0069] Figure 6 The flowchart showing the process of image feature matching provided by an exemplary embodiment of the present application is shown.

[0070] Step 601, in the case where there is a blurred area in the fingerprint image, based on the image gradient of the fingerprint image, the fingerprint image is divided into a valid area and a blurred area.

[0071] Optionally, the image gradient (derivative) is used to measure the change rate of the image gray level, so as to distinguish the blurred area and the valid area in the image. In the valid area, the fingerprint in the image is clearer, so the change of the image gradient in the valid pixel area is more obvious, that is, its image gradient is higher. While in the blurred area, the fingerprint is more blurred, so the change of its image gradient is not obvious and its image gradient is lower. Then, an image gradient threshold is set in the terminal. When the image gradient is greater than the image gradient threshold, the current area is determined as the valid area, and when the image gradient is less than the image gradient threshold, the current area is determined as the blurred area.

[0072] Figure 7 The schematic diagram of fingerprint image area segmentation provided by an exemplary embodiment of the present application is shown. It includes a clear fingerprint image and a fingerprint image with a blurred area. Among them, based on the image gradient, the first area 701 can be determined as the valid area, and the second area 702 as the blurred area. In the first area 701, the fingerprint is relatively clear, while in the second area 702, the fingerprint is blurred.

[0073] Step 602, in the case where the proportion of the valid area in the fingerprint image does not reach the proportion threshold, it is determined that the identity verification fails.

[0074] After determining the effective area, the terminal only extracts the fingerprint image features within the effective area, thereby eliminating the impact of the fuzzy area on identity authentication. In some embodiments, the effective area in the fingerprint image is small. In this case, even if the matching score between the effective area and the fingerprint image feature template is high, the matching score of the smaller area cannot be used as the matching score of the entire fingerprint image, and the verification result is not accurate enough.

[0075] Therefore, a ratio threshold is set in the terminal. Only when the effective area accounts for a certain proportion of the ratio threshold can the matching score of the effective area be used to represent the matching score of the entire fingerprint image. For example, the ratio threshold can be 45%. If the proportion of the effective area in the fingerprint image does not reach the ratio threshold, the identity authentication is directly determined to have failed.

[0076] Step 603: When the proportion of the effective area in the fingerprint image reaches a proportion threshold, feature extraction is performed on the fingerprint feature points in the effective area to obtain fingerprint image features.

[0077] When the effective area accounts for a large proportion, the matching score of the entire fingerprint image can be represented according to the matching score of the effective area.

[0078] The feature points in the fingerprint image provide unique confirmation information of the fingerprint, which can be divided into overall features and local features. Overall features include core points, triangulation points and grain numbers. Local features refer to the detailed features of the fingerprint, such as the direction, curvature and node position of the feature points.

[0079] Only extracting features from fingerprint feature points within the effective area helps to ignore the impact of inaccurate image features in the fuzzy area on the matching score.

[0080] Figure 8 The flowchart of image feature matching provided by an exemplary embodiment of the present application is shown. First, the fingerprint image is segmented based on the image gradient to separate the effective fingerprint area. When extracting features, the effective area is feature extracted to obtain the fingerprint features of the effective area, and the features of the fuzzy area are removed. Finally, the fingerprint image features in the effective area are feature matched with the fingerprint image feature template in the effective area of ​​the fingerprint image feature template to obtain a second matching score.

[0081] In a possible implementation, since there are also feature points with strong fingerprint characteristics in the fuzzy area, such feature points are relatively stable and not easily affected by wet hands, such as extreme points, such feature points can also be included in the range of valid feature points.

[0082] Specifically, based on the image gradient of the fingerprint image, the extreme points in the blurred area are determined as valid feature points. Feature extraction is performed on the fingerprint feature points in the valid area and the valid feature points in the blurred area of the fingerprint image to obtain the fingerprint image features.

[0083] In the embodiment of the present application, through the image gradient of the fingerprint image, the valid area and the blurred area are determined, and only the fingerprint image features in the valid area are used for matching during the fingerprint image feature matching process, which can eliminate the influence of the blurred area on fingerprint matching, thereby increasing the probability of unlocking based on the fingerprint image.

[0084] In fact, the process of identity verification is a process of matching the collected capacitance signal features and fingerprint image features with the stored fingerprint image feature template and capacitance signal feature template. When the fingerprint image and capacitance signal are collected, the terminal performs feature extraction on the fingerprint image to obtain the fingerprint image features, and performs feature extraction on the capacitance signal to obtain the capacitance signal features, and then performs identity verification based on the fingerprint image features and capacitance signal features to obtain the identity verification result. By comparing the fingerprint image features and capacitance signal features, the success rate of identity verification is ensured.

[0085] Figure 9 The flowchart of the identity verification process provided by an exemplary embodiment of the present application is shown. After the finger presses the fingerprint verification area on the screen, 20 consecutive frames of capacitance signals are collected by the capacitance signal sensor, and then feature extraction is performed on the capacitance signals to obtain the capacitance signal features. Finally, the matching score between the capacitance signal features and the capacitance signal feature template is determined. At the same time, one frame is collected by the fingerprint sensor, feature extraction is performed on the fingerprint image to obtain the fingerprint image features, and the matching score between the fingerprint image features and the fingerprint image feature template is determined. After obtaining the matching score between the capacitance signal features and the capacitance signal feature template and the matching score between the fingerprint image features and the fingerprint image feature template, the fingerprint verification result is determined based on the identity verification determination rule.

[0086] The identity verification determination rule will be described below. When performing identity verification based on the fingerprint image features and capacitance signal features, there are the following possible implementation manners, and the following will separately describe several possible implementation manners:

[0087] 1. Perform identity verification based on the capacitance signal features and fingerprint image features, and the capacitance signal feature verification is prior.

[0088] First, it is necessary to perform identity verification based on the capacitance signal characteristics. The first score threshold and the second score threshold are stored in the terminal. The first score threshold is a strong threshold, and the second score threshold is a weak threshold. After obtaining the capacitance signal characteristics, determine the first matching score between the capacitance signal characteristics and the capacitance signal characteristic template.

[0089] Among them, the capacitance signal characteristic template is the capacitance signal characteristic of the capacitance signal template that has been entered and allows identity verification. The first matching score is used to characterize the matching degree between the capacitance signal characteristics and the capacitance signal characteristic template. The first matching score has a positive correlation with the matching degree. The higher the first matching score, the stronger the matching degree between the capacitance signal characteristics and the capacitance signal characteristic template. Then, the first matching score may have the following three situations:

[0090] 1. When the first matching score is higher than the first score threshold, it is determined that the identity verification is successful.

[0091] The first score threshold is the score threshold set for identity verification only through capacitance signals. Then, in some cases, the first matching score is lower than the first score threshold. In order to further determine whether identity verification can be passed and improve the success rate of identity verification, the terminal sets the second score threshold. When the first matching score is higher than the second score threshold, it indicates that the fingerprint image needs to be combined to further determine the identity verification result.

[0092] 2. When the first matching score is lower than the first score threshold and higher than the second score threshold, perform identity verification based on the fingerprint image characteristics to obtain the identity verification result.

[0093] When performing identity verification based on the fingerprint image characteristics, it is necessary to determine the second matching score between the fingerprint image characteristics and the fingerprint image characteristic template.

[0094] Among them, the fingerprint image characteristic template is the fingerprint image characteristic of the fingerprint image template that has been entered and allows identity verification. The second matching score is used to characterize the matching degree between the fingerprint image characteristics and the fingerprint image characteristic template. The second matching score has a positive correlation with the matching degree. The higher the second matching score, the stronger the matching degree between the fingerprint image characteristics and the fingerprint image characteristic template.

[0095] Moreover, a third score threshold is stored in the terminal in advance. The third score threshold is used to limit whether the fingerprint image characteristics can pass the identity verification. The higher the third score threshold, the stronger the matching degree between the fingerprint image characteristics and the fingerprint image characteristic template is required to pass the identity verification, indicating that it is more difficult to pass the identity verification and the security level is higher. In addition, since there is capacitance signal characteristic as auxiliary identity verification information, the third score threshold should be lower than the score threshold for identity verification only based on fingerprint images.

[0096] If the second matching score is higher than the third score threshold, it is determined that the authentication is successful. The third score threshold is lower than the score threshold for authentication based only on fingerprint images.

[0097] If the second matching score is lower than the third score threshold, it is determined that the authentication fails.

[0098] In a possible implementation, the terminal stores fingerprint image feature templates corresponding to multiple pre-recorded fingerprint image templates, and capacitance signal feature templates corresponding to multiple pre-recorded capacitance signal templates. When performing feature matching, the collected fingerprint image features should be respectively matched with the multiple fingerprint image feature templates to obtain multiple candidate matching scores, and the highest candidate matching score is selected as the second matching score. Similarly, the collected capacitance signal features are respectively matched with the multiple capacitance signal feature templates to obtain multiple candidate matching scores, and the highest candidate matching score is selected as the first matching score.

[0099] 3. If the first matching score is lower than the second score threshold, it is determined that the authentication fails. The second score threshold is used to define whether the capacitance signal directly fails the authentication. The lower the second score threshold, the easier it is to enter the fingerprint image matching process. The higher the second score threshold, the higher the matching degree between the capacitance signal feature and the capacitance signal feature template is required to further perform fingerprint image matching. Therefore, the higher the second score threshold, the higher the requirement for the matching degree of the capacitance signal feature, the more difficult it is to pass the authentication, and the higher the security level.

[0100] Of course, the first score threshold, the second score threshold, and the third score threshold are not set to be safer with higher values. When the score threshold is set to be large, it is not easy to pass the authentication, which may affect the normal use of the user.

[0101] Figure 10 The flowchart of the authentication process provided by another exemplary embodiment of the present application is shown. First, after obtaining the first matching score corresponding to the capacitance signal feature, it is determined whether the first matching score is greater than the first score threshold. If it is greater than the first score threshold, it is directly determined that the authentication is successful. If it is not greater than the first score threshold, it is determined whether the first matching score is greater than the second score threshold. If it is not greater than the second score threshold, it is determined that the authentication fails. If it is greater than the second score threshold, the second matching score between the fingerprint image feature and the fingerprint image feature template is obtained, and it is determined whether the second matching score is greater than the third score threshold. If it is greater than the third score threshold, it is determined that the authentication is successful. If it is less than the third score threshold, it is determined that the authentication fails.

[0102] Second, identity verification is performed based on fingerprint image features and capacitance signal features, with fingerprint image feature verification being prior.

[0103] First, it is necessary to perform identity verification based on fingerprint image features. A fifth score threshold and a third score threshold are set in the terminal. The fifth score threshold is a strong threshold, and the third score threshold is a weak threshold. Among them, the fifth score threshold is the score threshold for performing identity verification based only on fingerprint images. After obtaining the fingerprint image features, determine the second matching score between the fingerprint image features and the fingerprint image feature template.

[0104] Among them, the fingerprint image feature template is the fingerprint image features of the fingerprint image template that has been entered and allowed to pass identity verification. The second matching score is used to characterize the matching degree between the fingerprint image features and the fingerprint image feature template. The second matching score may have the following three situations:

[0105] 1. When the second matching score is higher than the fifth score threshold, determine that the identity verification is successful.

[0106] 2. When the second matching score is lower than the fifth score threshold and higher than the third score threshold, perform identity verification based on the capacitance signal features to obtain the identity verification result.

[0107] When performing identity verification based on the capacitance signal features, it is necessary to determine the first matching score between the capacitance signal features and the capacitance signal feature template.

[0108] Among them, the capacitance signal feature template is the capacitance signal features of the capacitance signal that has been entered and allowed to pass identity verification. The first matching score is used to characterize the matching degree between the capacitance signal features and the capacitance signal feature template. The second matching score has a positive correlation with the matching degree. The higher the second matching score, the stronger the matching degree between the fingerprint image features and the fingerprint image feature template.

[0109] Moreover, a sixth score threshold set in advance is stored in the terminal. The sixth score threshold is used to determine whether the capacitance signal features can pass the identity verification. The higher the sixth score threshold, the stronger the matching degree required between the capacitance signal features and the capacitance signal feature template to pass the identity verification, indicating that it is more difficult to pass the identity verification and the security level is higher.

[0110] Then, when the first matching score is higher than the sixth score threshold, determine that the identity verification is successful; when the first matching score is lower than the sixth score threshold, determine that the identity verification fails.

[0111] Among them, since a combination of fingerprint image matching and capacitance signal matching is adopted, the sixth score threshold is lower than the first score threshold.

[0112] 3. In the case where the second matching score is lower than the fifth score threshold, it is determined that the authentication fails. The fifth score threshold is used to define whether the fingerprint image directly fails the authentication. The lower the fifth score threshold, the easier it is to enter the capacitance signal feature matching link. The higher the fifth score threshold, the higher the matching degree between the fingerprint image feature and the fingerprint image feature template is required to further perform capacitance signal matching. Therefore, the higher the fifth score threshold, the higher the requirement for the matching degree of the fingerprint image feature, the more difficult it is to pass the authentication, and the higher the security level.

[0113] Of course, the higher the fifth score threshold, the third score threshold, and the sixth score threshold are not, the stronger the security level is. When the score threshold is set relatively large, it is not easy to pass the authentication, which may affect the normal use of users.

[0114] Figure 11 The flowchart of the authentication process provided by another exemplary embodiment of the present application is shown. First, after obtaining the second matching score corresponding to the fingerprint image feature, it is determined whether the second matching score is greater than the fifth score threshold. In the case where it is greater than the fifth score threshold, it is directly determined that the authentication is successful. In the case where it is not greater than the fifth score threshold, it is determined whether the second matching score is greater than the third score threshold. In the case where it is not greater than the third score threshold, it is determined that the authentication fails. In the case where it is greater than the third score threshold, the first matching score between the capacitance signal feature and the capacitance signal feature template is obtained, and it is determined whether the first matching score is greater than the sixth score threshold. In the case where it is greater than the sixth score threshold, it is determined that the authentication is successful. In the case where it is less than the sixth score threshold, it is determined that the authentication fails.

[0115] Third, first perform authentication based on the fingerprint image feature, and combine the capacitance signal for feature verification in the wet state.

[0116] In the embodiment of the present application, the fingerprint verification area is composed of a node capacitance array, and the node capacitance array includes at least two node capacitances. When performing authentication, the terminal collects the fingerprint image and the capacitance signal, and only performs authentication through the fingerprint image feature corresponding to the fingerprint image to obtain a preliminary authentication result. If the current state is a wet hand state, it may cause the authentication result obtained through the fingerprint image feature to be inaccurate, resulting in the authentication result being determined as authentication failure.

[0117] Since a capacitive touch screen can detect minute current changes, identify and determine the touch position based on the change in the coupling capacitance on the capacitive touch screen, and report touch events, when other conductors, such as water stains, come into contact with the capacitive touch screen and absorb a small amount of current, the coupling capacitance on the capacitive touch screen will also change, that is, ghost points are generated. As a result, the terminal can determine whether it is in a water state based on the collected capacitance signals. The water state and the non-water state are two different screen states. The water state refers to the state entered when there are water stains on the fingerprint verification area, and the non-water state refers to the state entered when it is recognized that there are no water stains on the touch screen.

[0118] When it is determined that the current is in the water state, it is determined that the finger in contact with the fingerprint verification area is in a wet hand state. Since the influence of the wet hand state on the fingerprint image is greater than that on the capacitance signal, therefore, a method combining fingerprint image features and capacitance signal features can be used for identity verification to obtain an identity verification result.

[0119] Specifically, first, identity verification is performed based on fingerprint image features to obtain a preliminary identity verification result.

[0120] Subsequently, when the preliminary identity verification result indicates a failed identity verification, the current screen state is determined based on the node mutual capacitance signal of each node capacitance and the self-capacitance signal of the corresponding rows and columns of the node capacitance.

[0121] On a capacitive touch screen, the self-capacitance includes the capacitance formed by the horizontal electrodes (or called row electrodes) to the ground, and the capacitance formed by the vertical electrodes (or called column electrodes) to the ground; the mutual capacitance is the capacitance formed by the intersecting horizontal and vertical electrodes. The node capacitance in each of the following embodiments is the capacitance at the intersection point. Correspondingly, the node mutual capacitance signal is used to characterize the capacitance value between the row electrode and the column electrode at this intersection point, and the self-capacitance signal is used to characterize the capacitance value between the corresponding row electrode of this intersection point and the ground, and the capacitance value between the corresponding column electrode of this intersection point and the ground.

[0122] Optionally, since there are inconsistent conclusions on whether there is a touch operation object on the capacitive touch screen when there is water on the capacitive touch screen, in a possible implementation, when the capacitive touch device determines that there is a suspected touch point based on the mutual capacitance signal and determines that there is no suspected touch point based on the self-capacitance signal, it determines that the capacitive touch screen is in a water state; when it determines that there is no suspected touch point based on the mutual capacitance signal and determines that there is a suspected touch point based on the self-capacitance signal, it determines that the capacitive touch screen is in a water state; when it determines that there is a suspected touch point based on the mutual capacitance signal and determines that there is a suspected touch point based on the self-capacitance signal, it determines that the capacitive touch screen is in a non-water state; when it determines that there is no suspected touch point based on the mutual capacitance signal and determines that there is no suspected touch point based on the self-capacitance signal, it determines that the capacitive touch screen is in a non-water state.

[0123] When it is determined that the current screen state is the water state, perform identity verification based on the fingerprint image feature and the capacitance signal feature to obtain an identity verification result.

[0124] The process of performing identity verification based on the fingerprint image feature and the capacitance signal feature can refer to the above two identity verification processes, and this embodiment will not be elaborated here.

[0125] Figure 12 The flowchart of the identity verification process provided by another exemplary embodiment of the present application is shown. First, determine whether the identity verification based only on the fingerprint image feature is successful. In the case of identity verification failure, based on the node mutual capacitance signal of each node capacitance and the self-capacitance signal of the corresponding row and column of the node capacitance, determine whether the current screen state is the water state. In the case where the current screen state is the non-water state, determine that the identity verification fails. In the case where the current screen state is the water state, determine whether the identity verification based on the fingerprint image feature and the capacitance signal feature is successful.

[0126] IV. After fusing the fingerprint image and the capacitance signal, perform identity verification based on the fusion feature.

[0127] After collecting the fingerprint image and the capacitance signal, in addition to performing identity verification based on the fingerprint signal feature and the capacitance signal feature respectively, the fingerprint image and the capacitance signal can also be fused.

[0128] Specifically, weight the fingerprint image based on the signal value corresponding to the node capacitance in the capacitance signal to obtain a fused image.

[0129] The capacitance signal is essentially a matrix composed of capacitance signal values collected by node capacitances. Since a large number of node capacitances need to be set in practical applications to obtain capacitance signals with sufficient details, the matrix composed of the capacitance signal values has the same size as the fingerprint image. Therefore, the corresponding pixels in the fingerprint image can be weighted by the capacitance signal values to obtain a fused image.

[0130] Secondly, feature extraction is performed on the fused image to obtain fused image features.

[0131] The process of performing feature extraction on the fused image can refer to the implementation manner of performing feature extraction on the fingerprint image in the above embodiment, and this embodiment will not elaborate on this.

[0132] Subsequently, a third matching score between the fused image features and the fused image feature template is determined. The fused image feature template is obtained by fusing the capacitance signal feature template and the fingerprint image feature template. The capacitance signal template is the capacitance signal feature of the capacitance signal that has been entered and allows authentication, and the fingerprint image feature template is the fingerprint image feature of the fingerprint image that has been entered and allows authentication.

[0133] A fourth score threshold is set in the terminal. The fourth score threshold is used to control whether the fused image features obtained by combining the capacitance signal and the fingerprint image can pass authentication. The higher the fourth score threshold, the higher the point matching score required to pass authentication, and the higher the security level.

[0134] Then, when the third matching score is greater than the fourth score threshold, it is determined that the fingerprint authentication is successful; when the third matching score is less than the fourth score threshold, it is determined that the fingerprint authentication fails.

[0135] In the embodiments of the present application, different authentication schemes are provided. In different authentication schemes, the conditions for the capacitance signal features and the fingerprint image features to pass authentication are different. Combining the capacitance signal features with the fingerprint image features for authentication can effectively improve the success rate of authentication. Especially in the wet hand state, using the capacitance signal as auxiliary information for fingerprint image authentication ensures the success rate of authentication.

[0136] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the present application.

[0137] Please refer to Figure 13 , which shows a structural block diagram of an authentication device provided by an embodiment of the present application. The device may include:

[0138] The acquisition module 1301 is configured to acquire a fingerprint image of a finger and a capacitance signal generated by the contact between the finger and the fingerprint verification area when a touch operation on the fingerprint verification area is received;

[0139] The verification module 1302 is configured to perform identity verification based on the acquired fingerprint image and the capacitance signal to obtain an identity verification result.

[0140] Optionally, the verification module 1302 is configured to:

[0141] Extract features from the fingerprint image to obtain fingerprint image features;

[0142] Extract features from the capacitance signal to obtain capacitance signal features;

[0143] Perform identity verification based on the fingerprint image features and the capacitance signal features to obtain the identity verification result.

[0144] Optionally, the verification module 1302 is configured to:

[0145] Determine a first matching score between the capacitance signal features and a capacitance signal feature template, where the capacitance signal feature template is the capacitance signal feature of a capacitance signal template of an enrolled capacitance signal that allows identity verification to pass, and the first matching score is used to characterize the matching degree between the capacitance signal features and the capacitance signal feature template;

[0146] When the first matching score is higher than a first score threshold, determine that the identity verification is successful;

[0147] When the first matching score is lower than the first score threshold and higher than a second score threshold, perform identity verification based on the fingerprint image features to obtain the identity verification result;

[0148] When the first matching score is lower than the second score threshold, determine that the identity verification fails.

[0149] Optionally, the verification module 1302 is configured to:

[0150] Determine a second matching score between the fingerprint image features and a fingerprint image feature template, where the fingerprint image feature template is the fingerprint image feature of a fingerprint image template of an enrolled fingerprint image that allows identity verification to pass, and the second matching score is used to characterize the matching degree between the fingerprint image features and the fingerprint image feature template;

[0151] When the second matching score is higher than a third score threshold, determine that the identity verification is successful, and the third score threshold is lower than the score threshold for performing identity verification based only on the fingerprint image;

[0152] In the case where the second matching score is lower than the third score threshold, it is determined that the authentication fails.

[0153] Optionally, the device further includes:

[0154] An input module, configured to collect the fingerprint image template of the finger that touches the fingerprint verification area and the capacitance signal template generated by the contact between the finger and the fingerprint verification area;

[0155] The input module is further configured to perform feature extraction on the fingerprint image template to obtain the fingerprint image feature template;

[0156] The input module is further configured to perform feature extraction on the capacitance signal template to obtain the capacitance signal feature template;

[0157] The input module is further configured to save the fingerprint image feature template and the capacitance signal feature template for feature matching of the fingerprint image feature and the capacitance signal feature.

[0158] Optionally, the fingerprint verification area is composed of a node capacitance array, the node capacitance array includes at least two node capacitances, and at least two frames of the capacitance signals generated by the contact between the finger and the fingerprint verification area are collected, and each frame of the capacitance signal includes capacitance signals corresponding to at least two of the node capacitances;

[0159] The verification module 1302 is configured to:

[0160] Determine the node capacitance signal feature of the same node capacitance in at least two frames of the collected capacitance signals, where the node capacitance signal feature refers to at least one of a statistical feature, a time domain feature, a frequency domain feature, and a transform feature;

[0161] Based on the arrangement order of the node capacitances in the node capacitance array and the node capacitance signal features corresponding to at least two of the node capacitances, determine the capacitance signal feature.

[0162] Optionally, in the case where the node capacitance signal feature is the statistical feature, the capacitance signal corresponds to capacitance signal features of N different statistical feature dimensions, where N is a positive integer;

[0163] The verification module 1302 is configured to:

[0164] The determining the first matching score between the capacitance signal feature and the capacitance signal feature template includes:

[0165] Determine the nth candidate matching score between the nth capacitance signal feature and the nth capacitance signal feature template, where the nth capacitance signal feature template is a capacitance signal feature that allows authentication and corresponds to the nth capacitance signal feature, n is greater than 0 and less than or equal to N;

[0166] Based on the first candidate matching score to the Nth candidate matching score, determine the first matching score.

[0167] Optionally, the apparatus further includes:

[0168] A region division module, configured to divide the fingerprint image into a valid region and the blurred region based on the image gradient of the fingerprint image when the fingerprint image has a blurred region;

[0169] The verification module 1302 is configured to extract features of fingerprint feature points in the valid region of the fingerprint image to obtain the fingerprint image features.

[0170] Optionally, the apparatus further includes:

[0171] A determination module, configured to determine the extreme points in the blurred region as valid feature points based on the image gradient of the fingerprint image;

[0172] The verification module 1302 is configured to extract features of the fingerprint feature points in the valid region and the valid feature points in the blurred region of the fingerprint image to obtain the fingerprint image features.

[0173] Optionally, the verification module 1302 is further configured to:

[0174] Determine that the identity verification fails when the proportion of the valid region in the fingerprint image does not reach the proportion threshold;

[0175] When the proportion of the valid region in the fingerprint image reaches the proportion threshold, extract features of the fingerprint feature points in the valid region to obtain the fingerprint image features.

[0176] Optionally, the verification module 1302 is configured to:

[0177] Determine a second matching score between the fingerprint image features and a fingerprint image feature template, where the fingerprint image feature template is the fingerprint image feature of a fingerprint image template that has been entered and allows authentication, and the second matching score is used to characterize the matching degree between the fingerprint image features and the fingerprint image feature template;

[0178] When the second matching score is higher than the fifth score threshold, it is determined that the authentication is successful, and the fifth score threshold is the score threshold for authentication based only on the fingerprint image;

[0179] When the second matching score is lower than the fifth score threshold and the second matching score is higher than the third score threshold, authenticate based on the capacitance signal feature to obtain the authentication result;

[0180] When the second matching score is lower than the fifth score threshold, it is determined that the authentication fails.

[0181] Optionally, the verification module 1302 is configured to:

[0182] Determine a first matching score between the capacitance signal feature and a capacitance signal feature template, where the capacitance signal feature template is the capacitance signal feature of the capacitance signal that has been entered and allowed to pass authentication, and the first matching score is used to characterize the matching degree between the capacitance signal feature and the capacitance signal feature template;

[0183] When the first matching score is higher than the sixth score threshold, it is determined that the authentication is successful;

[0184] When the first matching score is lower than the sixth score threshold, it is determined that the authentication fails.

[0185] Optionally, the fingerprint verification area is composed of a node capacitance array, and the node capacitance array includes at least two node capacitances;

[0186] The verification module 1302 is further configured to:

[0187] Authenticate based on the fingerprint image feature to obtain a preliminary authentication result;

[0188] When the preliminary authentication result indicates that the authentication fails, determine the current screen state based on the node mutual capacitance signal of each node capacitance and the self-capacitance signal of the row and column corresponding to the node capacitance. The current screen state includes a water state and a non-water state. The water state refers to the state entered when there is a water trace on the fingerprint verification area;

[0189] When the current screen state is the water state, authenticate based on the fingerprint image feature and the capacitance signal feature to obtain the authentication result.

[0190] Optionally, the verification module 1302 is configured to:

[0191] Weight the fingerprint image based on the signal value corresponding to the node capacitance in the capacitance signal to obtain a fused image;

[0192] Extract features from the fused image to obtain fused image features;

[0193] Determine a third matching score between the fused image features and a fused image feature template, where the fused image feature template is obtained by fusing a capacitance signal feature template and a fingerprint image feature template. The capacitance signal template is the capacitance signal feature of the capacitance signal that has been entered and allows authentication, and the fingerprint image feature template is the fingerprint image feature of the fingerprint image that has been entered and allows authentication;

[0194] When the third matching score is greater than a fourth score threshold, determine that fingerprint verification is successful;

[0195] When the third matching score is less than the fourth score threshold, determine that fingerprint verification fails.

[0196] In summary, in the embodiments of the present application, when a touch operation on the fingerprint verification area is received, a fingerprint image and a capacitance signal are collected, and then identity verification is performed based on the fingerprint image and the capacitance signal. The capacitance signal is introduced into the identity verification to enhance the success rate of biometric recognition unlocking. Thus, when the collected fingerprint image is incomplete or unclear, identity verification is performed in combination with the capacitance signal to ensure the success rate of identity verification. For example, when a user touches the fingerprint verification area with wet hands, the collected fingerprint image may have blurred areas at this time. At this time, performing identity verification in combination with the collected capacitance signal can make up for the lack of fingerprint features in the blurred areas of the fingerprint image caused by wet hands, thereby improving the success rate of fingerprint recognition in the wet hand state.

[0197] Please refer to Figure 14 , which shows a block diagram of the structure of a terminal provided by an exemplary embodiment of the present application. The terminal 1400 can be implemented as the terminal in each of the above embodiments. The terminal 1400 may include one or more of the following components: a processor 1410, a memory 1420, a fingerprint image sensor 1430, and a capacitive sensor 1440.

[0198] The processor 1410 may include one or more processing cores. The processor 1410 connects various parts within the entire terminal 1400 through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 1420, and by invoking data stored in the memory 1420, it performs various functions of the terminal 1400 and processes data. Optionally, the processor 1410 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 1410 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), a neural-network processing unit (NPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for the rendering and drawing of the content to be displayed on the touch display screen; the NPU is used to implement artificial intelligence (AI) functions; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1410 and may be implemented separately by a single chip.

[0199] The memory 1420 may include random access memory (RAM) and may also include read-only memory (ROM). Optionally, the memory 1420 includes a non-transitory computer-readable storage medium. The memory 1420 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1420 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch control function, sound playback function, image playback function, etc.), instructions for implementing the following various method embodiments, etc.; the data storage area may store data created according to the use of the terminal 1400 (such as audio data, phone book, etc.).

[0200] The fingerprint image sensor 1430 is configured to collect a fingerprint image of a finger when a touch operation on the fingerprint verification area is received. Alternatively, a fingerprint image template of the finger is collected when a touch operation on the fingerprint verification area is received.

[0201] The capacitive sensor 1440 is configured to collect a capacitance signal generated by the contact between the finger and the fingerprint verification area when a touch operation on the fingerprint verification area is received. Alternatively, a capacitance signal template generated by the contact between the finger and the fingerprint verification area is collected when a touch operation on the fingerprint verification area is received.

[0202] In addition, those skilled in the art can understand that the structure of the terminal 1400 shown in the above drawings does not limit the terminal. The terminal may include more or fewer components than those shown in the drawings, or combine certain components, or have different component arrangements. For example, the terminal 1400 further includes components such as a display screen, a camera assembly, a microphone, a speaker, a radio frequency circuit, an input unit, sensors (such as an acceleration sensor, an angular velocity sensor, a light sensor, etc.), an audio circuit, a WiFi module, a power supply, a Bluetooth module, etc., which will not be elaborated here.

[0203] The embodiment of the present application also provides a computer-readable storage medium, which stores at least one piece of program code, and the program code is loaded and executed by a processor to implement the authentication method described in each of the above embodiments.

[0204] The embodiment of the present application provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the authentication method provided in various alternative implementations of the above aspects.

[0205] It should be understood that "a plurality of" mentioned herein refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. In addition, the step numbers described herein only exemplarily show a possible execution sequence between steps. In some other embodiments, the above steps may not be executed in the order of the numbers. For example, two steps with different numbers are executed simultaneously, or two steps with different numbers are executed in the reverse order of the illustration. The embodiments of the present application do not limit this.

[0206] It should be noted that, before collecting the fingerprint image of the user and the capacitance signal generated by the contact between the finger and the fingerprint verification area, as well as during the process of collecting the fingerprint image and the capacitance signal, a prompt interface, a pop-up window or a voice prompt message can be displayed. The prompt interface, the pop-up window or the voice prompt message is used to prompt the user that their relevant data is being collected currently, so that this application only starts to execute the relevant steps of obtaining the user's relevant data after obtaining the confirmation operation issued by the user for the prompt interface or the pop-up window. Otherwise (that is, when the confirmation operation issued by the user for the prompt interface or the pop-up window is not obtained), the relevant steps of obtaining the user's relevant data are ended, that is, the relevant data of the user is not obtained. In other words, all user data collected by this application is collected with the consent and authorization of the user, and the collection, use and processing of the relevant user data need to comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0207] The above are only optional embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. An authentication method, characterized in that, The method includes: When a touch operation on the fingerprint verification area is received, collecting a fingerprint image of a finger and a capacitance signal generated by the contact between the finger and the fingerprint verification area; Performing identity verification based on the collected fingerprint image and the capacitance signal to obtain an identity verification result.

2. The method according to claim 1, characterized in that, The performing identity verification based on the collected fingerprint image and the capacitance signal to obtain an identity verification result includes: Extracting features from the fingerprint image to obtain fingerprint image features; Extracting features from the capacitance signal to obtain capacitance signal features; Performing identity verification based on the fingerprint image features and the capacitance signal features to obtain the identity verification result.

3. The method according to claim 2, characterized in that, The performing identity verification based on the fingerprint image features and the capacitance signal features to obtain the identity verification result includes: Determining a first matching score between the capacitance signal features and a capacitance signal feature template, where the capacitance signal feature template is the capacitance signal feature of a capacitance signal template that has been entered and allows identity verification to pass, and the first matching score is used to characterize the matching degree between the capacitance signal features and the capacitance signal feature template; When the first matching score is higher than a first score threshold, determining that the identity verification is successful; When the first matching score is lower than the first score threshold and the first matching score is higher than a second score threshold, performing identity verification based on the fingerprint image features to obtain the identity verification result; When the first matching score is lower than the second score threshold, determining that the identity verification fails.

4. The method according to claim 3, characterized in that, The performing identity verification based on the fingerprint image features to obtain the identity verification result includes: Determining a second matching score between the fingerprint image features and a fingerprint image feature template, where the fingerprint image feature template is the fingerprint image feature of a fingerprint image template that has been entered and allows identity verification to pass, and the second matching score is used to characterize the matching degree between the fingerprint image features and the fingerprint image feature template; When the second matching score is higher than a third score threshold, determining that the identity verification is successful, and the third score threshold is lower than the score threshold for performing identity verification based only on the fingerprint image; When the second matching score is lower than the third score threshold, determining that the identity verification fails.

5. The method according to claim 4, characterized in that, The method further includes: Collecting the fingerprint image template of the finger that performs a touch operation on the fingerprint verification area and the capacitance signal template generated by the contact between the finger and the fingerprint verification area; Extracting features from the fingerprint image template to obtain the fingerprint image feature template; Extracting features from the capacitance signal template to obtain the capacitance signal feature template; Saving the fingerprint image feature template and the capacitance signal feature template for feature matching of the fingerprint image features and the capacitance signal features.

6. The method according to claim 2, characterized in that, The fingerprint verification area is composed of a node capacitance array. The node capacitance array includes at least two node capacitances, and at least two frames of the capacitance signals generated by the contact between the finger and the fingerprint verification area are collected. Each frame of the capacitance signal includes capacitance signals corresponding to at least two of the node capacitances; The extracting features from the capacitance signals to obtain capacitance signal features includes: Determining the node capacitance signal features of the same node capacitance in at least two frames of the collected capacitance signals. The node capacitance signal features refer to at least one of statistical features, time-domain features, frequency-domain features, and transform features; Based on the arrangement order of the node capacitances in the node capacitance array and the node capacitance signal features corresponding to at least two of the node capacitances, determining the capacitance signal features.

7. The method according to claim 6, characterized in that, When the node capacitance signal features are the statistical features, the capacitance signal corresponds to capacitance signal features of N different statistical feature dimensions, where N is a positive integer; The determining a first matching score between the capacitance signal features and a capacitance signal feature template includes: Determining an nth candidate matching score between the nth capacitance signal feature and the nth capacitance signal feature template. The nth capacitance signal feature template is a capacitance signal feature that allows authentication and corresponds to the nth capacitance signal feature, where n is greater than 0 and n is less than or equal to N; Based on the first candidate matching score to the Nth candidate matching score, determining the first matching score.

8. The method according to claim 2, characterized in that, The method further includes: When there is a blurred area in the fingerprint image, based on the image gradient of the fingerprint image, dividing the fingerprint image into a valid area and the blurred area; The extracting features from the fingerprint image to obtain fingerprint image features includes: Extracting features from fingerprint feature points in the valid area of the fingerprint image to obtain the fingerprint image features.

9. The method according to claim 8, wherein, The method further includes: Based on the image gradient of the fingerprint image, determining the extreme points in the blurred area as valid feature points; The extracting features from the fingerprint image to obtain fingerprint image features includes: Extracting features from the fingerprint feature points in the valid area of the fingerprint image and the valid feature points in the blurred area of the fingerprint image to obtain the fingerprint image features.

10. The method according to claim 8, wherein, The method further includes: When the proportion of the valid area in the fingerprint image does not reach the proportion threshold, determining that the authentication fails; The extracting features from the fingerprint feature points in the valid area of the fingerprint image to obtain the fingerprint image features includes: When the proportion of the valid area in the fingerprint image reaches the proportion threshold, extracting features from the fingerprint feature points in the valid area to obtain the fingerprint image features.

11. The method according to claim 2, wherein, The performing authentication based on the fingerprint image features and the capacitance signal features to obtain the authentication result includes: Determine a second matching score between the fingerprint image features and the fingerprint image feature template, where the fingerprint image feature template is the fingerprint image features of the fingerprint image template that has been entered and allows authentication, and the second matching score is used to characterize the matching degree between the fingerprint image features and the fingerprint image feature template; In the case where the second matching score is higher than the fifth score threshold, determine that the authentication is successful, and the fifth score threshold is the score threshold for authentication based only on the fingerprint image; In the case where the second matching score is lower than the fifth score threshold and the second matching score is higher than the third score threshold, perform authentication based on the capacitance signal features to obtain the authentication result; In the case where the second matching score is lower than the fifth score threshold, determine that the authentication fails.

12. The method according to claim 11, wherein, The performing authentication based on the capacitance signal features to obtain the authentication result includes: Determine a first matching score between the capacitance signal features and the capacitance signal feature template, where the capacitance signal feature template is the capacitance signal features of the capacitance signal that has been entered and allows authentication, and the first matching score is used to characterize the matching degree between the capacitance signal features and the capacitance signal feature template; In the case where the first matching score is higher than the sixth score threshold, determine that the authentication is successful; In the case where the first matching score is lower than the sixth score threshold, determine that the authentication fails.

13. The method according to claim 2, wherein, The fingerprint verification area is composed of a node capacitance array, and the node capacitance array includes at least two node capacitances; Before performing authentication based on the fingerprint image features and the capacitance signal features, the method further includes: Perform authentication based on the fingerprint image features to obtain a preliminary authentication result; In the case where the preliminary authentication result indicates that the authentication fails, determine the current screen state based on the node mutual capacitance signal of each node capacitance and the self-capacitance signal of the row and column corresponding to the node capacitance. The current screen state includes a water state and a non-water state, and the water state refers to the state entered when there is a water trace on the fingerprint verification area; The performing authentication based on the fingerprint image features and the capacitance signal features to obtain the authentication result includes: In the case where the current screen state is the water state, perform authentication based on the fingerprint image features and the capacitance signal features to obtain the authentication result.

14. The method according to claim 1, wherein, The performing authentication based on the collected fingerprint image and the capacitance signal to obtain the authentication result includes: Weight the fingerprint image based on the signal value corresponding to the node capacitance in the capacitance signal to obtain a fused image; Extract features from the fused image to obtain fused image features; Determine a third matching score between the fused image feature and a fused image feature template, where the fused image feature template is obtained by fusing a capacitance signal feature template and a fingerprint image feature template, the capacitance signal template is the capacitance signal feature of the capacitance signal that has been entered and allows authentication, and the fingerprint image feature template is the fingerprint image feature of the fingerprint image that has been entered and allows authentication; When the third matching score is greater than a fourth score threshold, determine that the fingerprint authentication is successful; When the third matching score is less than the fourth score threshold, determine that the fingerprint authentication fails.

15. An authentication device, wherein, The device includes: An acquisition module, configured to acquire a fingerprint image of a finger and a capacitance signal generated by the contact between the finger and the fingerprint authentication area when a touch operation on the fingerprint authentication area is received; A verification module, configured to perform identity verification based on the acquired fingerprint image and the capacitance signal to obtain an identity verification result.

16. A terminal, characterized in that The terminal includes a processor and a memory; the memory stores at least one instruction, and the at least one instruction is used to be executed by the processor to implement the authentication method according to any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that At least one program code is stored in the computer-readable storage medium, and the program code is loaded and executed by a processor to implement the authentication method according to any one of claims 1 to 14.

18. A computer program product, characterized in that The computer program product includes computer instructions, and the computer instructions are stored in a computer-readable storage medium; a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the authentication method according to any one of claims 1 to 14.

Images