Fingerprint image verification method and device, computer equipment and storage medium

Abstract

The invention relates to the technical field of intelligent locks, and discloses a fingerprint image verification method and device, computer equipment and a storage medium, and the method comprises the steps: detecting a pressing operation of a user for a curved surface covering coating; when the pressing operation is detected, fingerprint images collected by a plurality of fingerprint sensors on the curved surface covering coating are obtained; matching a first fingerprint image acquired by a first sensor in the fingerprint sensors with a first fingerprint template associated with the first sensor to obtain a first matching number; and triggering a hierarchical verification mechanism according to the first matching number, and verifying the remaining fingerprint images to obtain a verification result. According to the invention, the problems of tedious registration and easy failure of identification caused by poor fitting degree and small sensor area of a planar fingerprint module are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart locks, and in particular to a fingerprint image verification method, device, computer equipment and storage medium. Background Art

[0002] In the field of smart locks, fingerprint recognition technology is widely used in various smart devices as an important authentication method. However, the current fingerprint recognition module is usually a flat design, and the size of its fingerprint sensor is much smaller than the overall size of the module, and is located in the center of the collection surface. This design results in only a fingerprint area equivalent to the size of the sensor being collected each time the finger is pressed, while other areas of the collection surface cannot effectively collect fingerprint information. Therefore, during the fingerprint registration stage, the user needs to move his finger multiple times to collect multiple fingerprint images, which increases the complexity and time cost of the registration process. Moreover, during the fingerprint recognition stage, due to the limited recognition area, not enough fingerprints can be collected for recognition. The user needs to move his finger multiple times to meet the inspection requirements, resulting in low recognition efficiency, which further affects the convenience of users using the fingerprint recognition function, making the entire fingerprint recognition process have major deficiencies in practical applications.

[0003] Existing fingerprint modules have problems such as poor fit, small sensor area and single sensor. The design of the flat acquisition surface fails to fully consider the natural curvature of the finger, which makes it easy to press lightly, heavily or off-center during the acquisition process, affecting the accuracy of fingerprint acquisition and user experience. At the same time, the design of a single sensor limits the area and feature information of fingerprint acquisition, which not only increases the number of entries during registration, but also reduces the success rate and efficiency of recognition. These problems have seriously restricted the development and application of fingerprint recognition technology. Summary of the invention

[0004] In view of this, the embodiments of the present invention provide a fingerprint image verification method, apparatus, computer device and storage medium to solve the problem that the poor fit of the planar fingerprint module and the small sensor area lead to cumbersome registration and easy recognition failure.

[0005] In a first aspect, an embodiment of the present invention provides a fingerprint image verification method, the method comprising:

[0006] Detecting a user's pressing operation on the curved surface covering coating;

[0007] When a pressing operation is detected, acquiring fingerprint images collected by multiple fingerprint sensors on the curved surface covering coating;

[0008] Matching a first fingerprint image captured by a first sensor of the fingerprint sensor with a first fingerprint template associated with the first sensor to obtain a first matching number;

[0009] A hierarchical verification mechanism is triggered according to the first matching number, and the remaining fingerprint images are verified to obtain a verification result.

[0010] Furthermore, before detecting a user's pressing operation on the curved surface covering coating, the method further includes:

[0011] Acquire original fingerprint images collected by multiple fingerprint sensors on the curved surface covering coating;

[0012] Filter the original fingerprint image according to a preset entry standard to obtain a plurality of standard fingerprint images;

[0013] A plurality of preset feature points of the standard fingerprint image are extracted, and a fingerprint template is constructed using the preset feature points, and the fingerprint template is associated with the corresponding fingerprint sensor and stored in a template storage space.

[0014] Furthermore, matching a first fingerprint image collected by a first sensor in the fingerprint sensor with a first fingerprint template associated with the first sensor to obtain a first matching number includes:

[0015] Traversing the preset numbers corresponding to the fingerprint sensors;

[0016] Determine a first sensor with a first priority according to the preset number;

[0017] Acquire a first fingerprint image captured by the first sensor and a corresponding first fingerprint template;

[0018] A plurality of first feature points are extracted from the first fingerprint image, and the first feature points are matched with preset feature points in the first fingerprint template to obtain a first matching number.

[0019] Furthermore, triggering a hierarchical verification mechanism according to the first number of matches to verify the remaining fingerprint images and obtain a verification result includes:

[0020] comparing the first matching number with a preset matching number;

[0021] If the first matching number does not reach the preset matching number, the hierarchical verification mechanism is triggered to verify the remaining fingerprint images to obtain a verification result;

[0022] Alternatively, if the first matching number reaches a preset matching number, the verification result is determined to be a successful fingerprint verification.

[0023] Further, the triggering of the hierarchical verification mechanism to verify the remaining fingerprint images to obtain a verification result includes:

[0024] Obtaining the distribution status of the remaining sensors in the fingerprint sensor;

[0025] If the distribution state is a plurality of small array sensors, performing a verification operation of the remaining fingerprint image based on a first strategy to obtain a first verification result;

[0026] If the distribution state is a ring sensor, a verification operation of the remaining fingerprint image is performed based on a second strategy to obtain a second verification result.

[0027] Further, performing the verification operation of the remaining fingerprint image based on the first strategy to obtain a first verification result includes:

[0028] Determine a second sensor of next priority according to a preset number corresponding to the fingerprint sensor;

[0029] Acquire a second fingerprint image collected by the second sensor and a corresponding second fingerprint template;

[0030] Extracting a plurality of second feature points in the second fingerprint image, and matching the second feature points with preset feature points in the second fingerprint template to obtain a second matching number;

[0031] Calculating a sum of the first matching number and the second matching number, and determining whether the sum reaches a first verification threshold;

[0032] If the first verification threshold is reached, the first verification result is determined to be a successful fingerprint verification and the matching operation is terminated; or, if the first verification threshold is not reached, the matching operation is repeated until all fingerprint sensors are matched and the first verification threshold is not reached, and the first verification result is determined to be a failed fingerprint verification.

[0033] Further, performing the verification operation of the remaining fingerprint image based on the second strategy to obtain a second verification result includes:

[0034] Acquire a third fingerprint image collected by the annular sensor and a corresponding third fingerprint template;

[0035] Extracting a plurality of third feature points from the third fingerprint image, and classifying the third feature points according to preset areas to obtain a set of feature points corresponding to each area;

[0036] Matching the feature point set corresponding to each area with the third preset feature point in the third fingerprint template to obtain multiple matching areas;

[0037] Determining whether the number of regions of the matching regions reaches a third verification threshold;

[0038] If the third verification threshold is reached, the second verification result is determined to be a successful fingerprint verification, or, if the third verification threshold is not reached, the second verification result is determined to be a failed fingerprint verification.

[0039] In a second aspect, an embodiment of the present invention provides a fingerprint image verification device, the device comprising:

[0040] A detection module, used to detect a user's pressing operation on the curved surface covering coating;

[0041] An acquisition module, configured to acquire fingerprint images collected by multiple fingerprint sensors on the curved surface covering coating when a pressing operation is detected;

[0042] a matching module, configured to match a first fingerprint image acquired by a first sensor of the fingerprint sensor with a first fingerprint template associated with the first sensor to obtain a first matching number;

[0043] A trigger module is used to trigger a hierarchical verification mechanism according to the first matching number, verify the remaining fingerprint images, and obtain a verification result.

[0044] In a third aspect, an embodiment of the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the method of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0045] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the method of the first aspect or any corresponding embodiment thereof.

[0046] The method provided in the embodiment of the present application has the following beneficial effects:

[0047] The method provided in the embodiment of the present application detects the pressing operation of the curved surface covering coating, adapts to the natural curvature of the finger, improves the user's operating comfort and accuracy, and reduces the situation of biased pressing. In order to solve the problem of small sensor area, multiple fingerprint sensors can collect more fingerprint information, enrich fingerprint features, and improve recognition accuracy and success rate. The number of matches obtained by matching the fingerprint image with the template provides a basis for hierarchical verification, improves verification efficiency, and reduces unnecessary steps. When the number of matches does not reach the preset value, the hierarchical verification mechanism is triggered, and the advantages of multiple sensors are utilized to adopt different verification strategies for different types of sensors, improve the accuracy and reliability of fingerprint verification, reduce the misjudgment rate, and solve the problem of easy failure of flat fingerprint module recognition. The original fingerprint image is screened by preset entry standards to ensure the quality of the template and reduce interference. The fingerprint template is stored in association with the sensor for quick call and improved registration and verification efficiency.

[0048] The method provided in the embodiment of the present application adopts the first strategy to determine the priority sensors for matching in sequence for the distribution state of multiple small array sensors, and increases the number of matches to improve the verification accuracy, which can reduce the verification failure caused by the inaccuracy of a single sensor and more comprehensively analyze the fingerprint features. For the distribution state of the annular sensor, the second strategy is adopted to classify and match the feature points according to the preset area to improve the verification accuracy. The specific verification strategies for different sensor types can better adapt to various fingerprint collection situations and improve the success rate and reliability of fingerprint recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 is a flow chart of a fingerprint image verification method according to an embodiment of the present invention;

[0051] Figure 2 is a schematic structural diagram of an existing fingerprint recognition module according to an embodiment of the present invention;

[0052] Figure 3 is a schematic structural diagram of a small area array sensor layout according to an embodiment of the present invention;

[0053] Figure 4 is a schematic structural diagram of a ring sensor layout according to an embodiment of the present invention;

[0054] Figure 5 is a schematic diagram of a process flow of a hierarchical verification strategy for a small-area array sensor according to an embodiment of the present invention;

[0055] Figure 6 is a schematic diagram of a flow chart of a ring sensor hierarchical verification strategy according to an embodiment of the present invention;

[0056] Figure 7 is a structural block diagram of a fingerprint image verification device according to an embodiment of the present invention;

[0057] Figure 8 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0059] According to an embodiment of the present invention, a fingerprint image verification method, apparatus, computer device and storage medium are provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0060] In this embodiment, a fingerprint image verification method is provided. Figure 1 FIG. 1 is a flow chart of a fingerprint image verification method according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0061] Step S11, detecting a user's pressing operation on the curved surface covering coating.

[0062] In the embodiment of the present application, the curved surface covering coating refers to a protective layer with a curved shape covering the top of the fingerprint sensor. On the one hand, it protects the fingerprint sensor and prevents the sensor from being damaged by the external environment, such as dust, moisture, scratches, etc. On the other hand, the curved surface design of the curved surface covering coating can better adapt to the natural curvature of the finger, so that when the user presses, the contact between the finger and the coating is more closely fitted, thereby improving the comfort and accuracy of the user's operation and reducing the occurrence of light, heavy or offset pressing. At the same time, the curved surface covering coating has a special material or processing technology to ensure that the fingerprint sensor can accurately collect fingerprint information and will not have a negative impact on the quality of the fingerprint image.

[0063] In the embodiment of the present application, before detecting the user's pressing operation on the curved surface covering coating, the method further includes the following steps A1-A3:

[0064] Step A1, obtaining original fingerprint images collected by multiple fingerprint sensors on the curved surface coating.

[0065] Specifically, in the early stage of fingerprint recognition, multiple fingerprint sensors are activated on the curved surface covering coating, including the central main sensor and small array or ring-shaped partial sensors. The curved surface multi-sensor can collect fingerprints from different angles. When the user puts his finger on it, each sensor works simultaneously to obtain rich fingerprint feature information, providing a basis for subsequent processing.

[0066] Step A2, screening the original fingerprint image according to the preset entry standard to obtain a plurality of standard fingerprint images.

[0067] Specifically, after obtaining the original fingerprint image, it is screened according to standards such as image clarity, completeness, and contrast. For example, the minimum resolution is set, the texture is ensured to be complete, and a large difference between the texture and the background is required. Poor images are removed and a standard fingerprint image is obtained for constructing a template to improve recognition accuracy and reliability.

[0068] Step A3: extract multiple preset feature points of the standard fingerprint image, construct a fingerprint template using the preset feature points, and associate the fingerprint template with the corresponding fingerprint sensor and store it in the template storage space.

[0069] Specifically, the standard fingerprint image is extracted for detailed features such as endpoints and bifurcation points, and global features such as the direction of the grain lines, and converted into representative data. The fingerprint template is constructed using these feature points and encoded into a feature vector. The template is associated with the corresponding sensor and stored in an independent space, which facilitates the rapid finding of the corresponding template during fingerprint recognition, improves the comparison efficiency, avoids template confusion, and ensures accuracy.

[0070] Step S12, when a pressing operation is detected, acquiring fingerprint images collected by multiple fingerprint sensors on the curved surface covering coating.

[0071] It should be noted that if Figure 2 As shown, existing fingerprint recognition modules are commonly square and circular, and the size of the fingerprint sensor is usually much smaller than the size of the curved surface covering coating. It is generally located in the center of the fingerprint collection surface. Each time the finger is pressed, the fingerprint is collected through the sensor, and the collected fingerprint area is less than or equal to the size of the sensor chip. Fingerprints cannot be collected in other areas of the collection surface.

[0072] In the embodiments of the present application, Figure 3 As shown in the figure, when the small array sensors are laid out, the central main sensor is numbered first, and the others are numbered in sequence. When the user presses, the small array sensors work simultaneously, and can collect multiple images of different parts of the finger, increase the richness of fingerprint features, and provide detailed information for subsequent identification. Figure 4 As shown in the figure, in the ring sensor configuration, the central large sensor is numbered first and the ring sensor is numbered second. Users can capture multiple images with one press of the dual sensors. The ring sensor can capture images all around the finger, improving the quality and integrity of the fingerprint image.

[0073] Step S13: Matching a first fingerprint image collected by a first sensor in the fingerprint sensor with a first fingerprint template associated with the first sensor to obtain a first matching number.

[0074] In the embodiment of the present application, step S13 includes the following steps B1-B4:

[0075] Step B1, traverse the preset numbers corresponding to the fingerprint sensors.

[0076] Specifically, in the process of fingerprint image matching, it is first necessary to traverse the preset numbers corresponding to the fingerprint sensors. Since multiple fingerprint sensors are placed in the curved coating and are numbered in a certain order, each sensor can be processed and analyzed in turn by traversing these numbers. For example, for the layout of small array sensors, the main sensor in the central area is numbered as the first sensor, and the other small array sensors are numbered in sequence. For the configuration of annular sensors, the large sensor in the central area is numbered first, and the annular sensor is numbered second. The process of traversing the numbers ensures that the system does not miss any sensor, thereby comprehensively processing the fingerprint image.

[0077] Step B2: determining a first sensor of a first priority according to a preset number.

[0078] Specifically, after traversing the numbers, the first sensor with the first priority is determined according to the preset numbering rules. The main sensor in the central area is usually given a higher priority because it plays a leading role in the fingerprint collection process. The sensor with the first priority is used as the starting point for matching the fingerprint image. For example, in the small array sensor layout, the central main sensor is the first priority sensor, and the fingerprint image collected by it contains more key features.

[0079] Step B3: Acquire a first fingerprint image collected by the first sensor and a corresponding first fingerprint template.

[0080] Specifically, after determining the sensor of the first priority, the first fingerprint image collected by the sensor and the corresponding first fingerprint template are obtained. The first fingerprint image is the fingerprint image collected by the first sensor in real time when the user presses the fingerprint module. The first fingerprint template is constructed by extracting feature points from the original fingerprint image collected by the sensor according to preset standards during the fingerprint entry stage, and is associated with the sensor and stored in the template storage space. The two data are obtained for subsequent feature point matching to determine the similarity between the first fingerprint image and the first fingerprint template.

[0081] Step B4: extract multiple first feature points in the first fingerprint image, and match the first feature points with preset feature points in the first fingerprint template to obtain a first matching number.

[0082] Specifically, after acquiring the first fingerprint image and the first fingerprint template, extract multiple first feature points in the first fingerprint image. Feature points can be detailed features of the fingerprint, such as endpoints, bifurcation points, etc., or global features, such as the direction and frequency of the lines. Then, match these first feature points with the preset feature points in the first fingerprint template. By comparing the feature points in the two sets, determine the degree of similarity between them, and obtain the first matching number, that is, the number of feature points in the first fingerprint image that match the feature points in the first fingerprint template. This number will serve as one of the bases for subsequent judgment of whether the fingerprint verification is successful.

[0083] Step S14, triggering a hierarchical verification mechanism according to the first matching number, verifying the remaining fingerprint images to obtain a verification result.

[0084] In the embodiment of the present application, step S14 includes the following steps C1-C3:

[0085] Step C1, comparing the first matching number with the preset matching number.

[0086] Specifically, the first matching number is compared with the preset matching number. The first matching number is the number of feature point matches obtained by matching the first fingerprint image collected by the first sensor with the first fingerprint template. The preset matching number is a threshold value pre-set according to design requirements and performance indicators. By comparing these two numbers, the progress of fingerprint verification can be preliminarily judged. If the first matching number reaches or exceeds the preset matching number, it means that the fingerprint verification has a high probability of success in the first stage; if the first matching number does not reach the preset matching number, it is necessary to further perform a hierarchical verification mechanism to more comprehensively evaluate the authenticity of the fingerprint.

[0087] Step C2: If the first matching number does not reach the preset matching number, the hierarchical verification mechanism is triggered to verify the remaining fingerprint images to obtain a verification result.

[0088] It should be noted that the hierarchical verification mechanism is activated when the first matching number does not reach the preset value. Different strategies are adopted according to the remaining sensor types. The small array sensor determines the next priority sensor according to the first strategy, and the matching feature point judgment threshold determines the result; the ring sensor determines the result according to the second strategy classification feature point matching judgment threshold. This mechanism uses the advantages of different sensors to verify fingerprints from multiple angles to improve accuracy and reliability.

[0089] Specifically, triggering the hierarchical verification mechanism to verify the remaining fingerprint images and obtaining the verification result includes the following steps D1-D3:

[0090] Step D1, obtaining the distribution status of the remaining sensors in the fingerprint sensor.

[0091] Specifically, the remaining sensors refer to sensors other than the first sensor that have not participated in the matching after the fingerprint image matching of the first sensor is completed. The distribution status includes but is not limited to the distribution of multiple small array sensors and the distribution of annular sensors. If there are multiple small array sensors, they are scattered in different positions of the curved coating to collect fingerprint images from different angles; if there are annular sensors, they are distributed around the large sensor in the central area to form an annular structure, which can collect fingerprint information of fingers in all directions.

[0092] Step D2: if the distribution state is a plurality of small array sensors, then the verification operation of the remaining fingerprint images is performed based on the first strategy to obtain a first verification result.

[0093] As an example, Figure 5 As shown, the first strategy includes: when the finger presses the fingerprint module, the recognition process is started. Multiple sensors collect fingerprint images of fingers at the same time, and then perform image processing to extract key information. Then they are compared in sequence, with large array sensors as priority, and feature points are compared from the first sensor template. If the threshold is not reached, the next sensor template feature point is combined to continue the comparison, and so on, until the feature point reaches the threshold and enters the next process or all sensor template feature points still do not reach the threshold after comparison. Finally, if the feature point reaches the threshold during the comparison process, the recognition is passed, otherwise the recognition fails.

[0094] Specifically, step D2 includes the following steps D21-D25:

[0095] Step D21, determining the second sensor of the next priority according to the preset number corresponding to the fingerprint sensor.

[0096] Specifically, when performing hierarchical verification on multiple small array sensors, the next priority sensor must be determined first. Since each sensor has a corresponding preset number, the order and priority of the sensors can be clarified by the number. After the matching of the first sensor has been completed, if the number of first matches does not reach the preset number of matches, the second sensor of the next priority must be determined in the order of numbers. For example, the main sensor in the central area is the first sensor, and the small array sensors around it are numbered in sequence according to a rule. When the second sensor is determined, the next sensor that should be matched is found according to this numbering order.

[0097] Step D22, obtaining a second fingerprint image collected by a second sensor and a corresponding second fingerprint template.

[0098] Specifically, after determining the second sensor, obtain the second fingerprint image collected by the sensor. This image is the fingerprint information collected by the second sensor in real time when the user presses the fingerprint module. At the same time, it is also necessary to obtain the corresponding second fingerprint template. The second fingerprint template is constructed by extracting feature points from the original fingerprint image collected by the second sensor according to preset standards during the fingerprint entry stage, and is associated with the second sensor and stored in the template storage space. The two data are obtained for subsequent feature point matching.

[0099] Step D23, extracting a plurality of second feature points in the second fingerprint image, and matching the second feature points with preset feature points in the second fingerprint template to obtain a second matching number.

[0100] Specifically, after acquiring the second fingerprint image and the second fingerprint template, extract a plurality of second feature points in the second fingerprint image. These feature points may include detailed features and global features of the fingerprint. Match the second feature points with preset feature points in the second fingerprint template. By comparing the feature points in the two sets, determine the degree of similarity between them, and thereby obtain a second matching number, that is, the number of feature points in the second fingerprint image that match the feature points in the second fingerprint template.

[0101] Step D24, calculating the sum of the first matching number and the second matching number, and determining whether the sum reaches a first verification threshold.

[0102] Specifically, after obtaining the second matching number, sum it with the first matching number. The sum represents the comprehensive matching degree of the two sensors currently involved in the matching. Then, determine whether the sum reaches the first verification threshold. The first verification threshold determines whether the fingerprint verification is successful. If the sum reaches the first verification threshold, it means that the fingerprint has a high matching degree and is likely to be a real fingerprint.

[0103] Step D25, if the first verification threshold is reached, the first verification result is determined to be a successful fingerprint verification, and the matching operation is terminated; or, if the first verification threshold is not reached, the matching operation is repeated until all fingerprint sensors are matched and the first verification threshold is not reached, and the first verification result is determined to be a failed fingerprint verification.

[0104] Specifically, if the sum reaches the first verification threshold, the first verification result is determined to be a successful fingerprint verification, and the matching operation is terminated. This is because the verification requirements have been met and no other sensors need to be matched. If the sum does not reach the first verification threshold, the matching operation is repeated, the next priority sensor is determined in numerical order, steps D21-D23 are repeated, the sum is calculated again, and it is determined whether the first verification threshold is reached. This process continues until all fingerprint sensors have been matched and the first verification threshold has not been reached, at which time the first verification result is determined to be a failed fingerprint verification.

[0105] Step D3: If the distribution state is a ring sensor, a verification operation of the remaining fingerprint images is performed based on the second strategy to obtain a second verification result.

[0106] As an example, Figure 6 As shown, the second strategy includes: when the finger presses the fingerprint module, the fingerprint recognition process is started. Multiple sensors work simultaneously to collect fingerprint images, with large array sensors taking priority and other sensors such as ring sensors assisting. Image processing is then performed to extract key feature points. Then the comparison starts from the first sensor template feature point of the large array sensor. If the threshold is not reached, the comparison is continued in combination with the ring sensor template feature point until the feature point reaches the threshold and enters the next step or all sensor template feature points still do not reach the threshold after comparison. Finally, if the feature point reaches the threshold in the comparison, the recognition passes, otherwise it fails.

[0107] Specifically, step D3 includes the following steps D31-D35:

[0108] Step D31, obtaining a third fingerprint image collected by the annular sensor and a corresponding third fingerprint template.

[0109] Specifically, when the distribution state of the remaining sensors is a ring sensor, the third fingerprint image collected by the ring sensor is first obtained. This image is the fingerprint information collected by the ring sensor in real time when the user presses the fingerprint module. At the same time, the corresponding third fingerprint template is obtained. The third fingerprint template is constructed by extracting feature points from the original fingerprint image collected by the ring sensor according to preset standards during the fingerprint entry stage, and is associated with the ring sensor and stored in the template storage space.

[0110] Step D32: extract multiple third feature points from the third fingerprint image, and classify the third feature points according to preset areas to obtain a feature point set corresponding to each area.

[0111] Specifically, after acquiring the third fingerprint image, a plurality of third feature points are extracted. These feature points may also include detailed features and global features of the fingerprint. Then, these third feature points are classified according to the preset area. The preset area can be divided according to the structural characteristics of the annular sensor and the distribution law of the fingerprint. For example, the annular sensor can be divided into a plurality of sector areas or annular areas. Through the classification operation, a set of feature points corresponding to each area is obtained.

[0112] Step D33, matching the feature point set corresponding to each area with the third preset feature point in the third fingerprint template to obtain multiple matching areas.

[0113] Specifically, the feature point sets corresponding to each region are matched with the third preset feature points in the third fingerprint template. The third preset feature points are feature points extracted when constructing the third fingerprint template, and correspond to feature points in the third fingerprint image. Through the matching operation, it can be determined which regions' feature points match the feature points in the template, thereby obtaining multiple matching regions.

[0114] Step D34, determining whether the number of matching areas reaches a third verification threshold.

[0115] Specifically, statistics are collected on the obtained multiple matching areas to determine whether the number of matching areas reaches a third verification threshold. The third verification threshold is used to determine whether the fingerprint verification of the ring sensor is successful.

[0116] Step D35, if the third verification threshold is reached, the second verification result is determined to be a successful fingerprint verification, or, if the third verification threshold is not reached, the second verification result is determined to be a failed fingerprint verification.

[0117] Specifically, if the number of matching areas reaches the third verification threshold, it means that the fingerprint collected by the annular sensor and the template have a high degree of matching, and the second verification result is determined to be a successful fingerprint verification. If the third verification threshold is not reached, it means that the matching degree is insufficient, and the second verification result is determined to be a failed fingerprint verification.

[0118] In an embodiment of the present application, the method also includes: monitoring the working state of the annular sensor; if the working state is a fault state, detecting the fault area of ​​the annular sensor, and adjusting the comparison area of ​​the second matching strategy to a non-fault area; if the number of hits in the non-fault area reaches a second verification threshold, determining that the verification is successful, or, if the second verification threshold is not reached, determining that the verification has failed.

[0119] Step C3: if the first matching number reaches the preset matching number, the verification result is determined to be successful fingerprint verification.

[0120] Specifically, if the first matching number reaches the preset matching number, it means that the first fingerprint image collected by the first sensor has a high matching degree with the first fingerprint template, and the authenticity of the fingerprint can be determined in the first stage. At this time, there is no need to perform a hierarchical verification mechanism, and the verification result is directly determined to be a successful fingerprint verification.

[0121] In this embodiment, a method for adjusting a curved surface coating based on a mechanical structure is provided, and the process includes the following steps:

[0122] Step S21, detecting first pressure data of the curved surface covering coating;

[0123] Step S22, calculating the adjustment height of each micro-retractable support in the mechanical structure below the curved surface covering coating according to the first pressure data;

[0124] Step S23, controlling the curved surface covering coating to perform a moving operation based on the adjusted height of each micro-retractable support;

[0125] Step S24, detecting the second pressure data of the curved surface covering coating after adjustment, and judging whether the current curved surface covering coating is subjected to uniform force according to the second pressure data;

[0126] Step S25, if the current curved surface coating is uniformly stressed, the current state parameters of each micro-retractable support are stored in a preset information library.

[0127] In the embodiment of the present application, the mechanical structure under the curved surface covering coating is composed of a plurality of micro-retractable pillars and a pressure sensing module, which is installed between the curved surface covering coating and the fingerprint sensor. When the user presses the finger on the curved surface covering coating, the pressure sensing module will quickly detect the pressure distribution of the finger and activate the micro-retractable pillars to make corresponding adjustments according to the pressure data.

[0128] It should be noted that the micro-retractable struts are made of high-strength but lightweight alloy materials with good durability and stability. The diameter of each strut is about a few millimeters, and the height can be adjusted within a certain range. A precision coil spring and micro-motor drive system are used inside the struts. When receiving the signal from the pressure sensing module, the micro-motor rotates according to the command and adjusts the height of the strut by compressing or stretching the coil spring. Multiple micro-retractable struts are evenly distributed under the curved surface covering coating to form a support grid, ensuring that the coating can be flexibly adjusted in all directions.

[0129] Specifically, when the user places the finger on the curved surface coating for fingerprint recognition, the pressure sensing module will immediately detect the pressure data of the finger and transmit it to the central control system. The central control system calculates the adjustment height of the micro-retractable support based on the pressure distribution, and then sends a control instruction to the micro-motor drive system. After receiving the instruction, the micro-motor drive system quickly adjusts the height of the support so that the curved surface coating can fit the shape of the finger, allowing the fingerprint sensor to more accurately capture the fingerprint image. For example, when the finger is thicker, the pressure sensing module will detect a larger pressure distribution range. At this time, the central control system will adjust the support height accordingly so that the coating bulges outward to adapt to the shape of the finger; when the finger is thinner, the central control system will adjust the support height to make the coating shrink inward to ensure a close fit to the finger. This mechanical structure design enables the curved surface coating to be automatically adjusted, providing users with a more comfortable and accurate fingerprint recognition experience.

[0130] In the embodiment of the present application, in addition to the above-mentioned curved surface coating adjustment method based on mechanical structure and related design, a small array sensor with dynamically adjustable position or sensitivity is also used to optimize the collection efficiency, especially in the traditional difficult collection areas such as the edge and fingertip of the finger. Through dynamic adjustment, the small array sensor can better adapt to the characteristics of different finger parts and obtain richer and more accurate fingerprint information.

[0131] In addition, a near-infrared light source can be integrated under the curved coating to achieve dual collection and recognition of fingerprints and finger veins. Because vein recognition is based on biological internal features and is difficult to copy, this dual recognition method provides a more reliable guarantee for user identity authentication. Throughout the fingerprint recognition process, various parts work together, from pressure detection to coating adjustment, to sensor optimization collection and application of dual recognition technology, to jointly create an efficient, accurate and secure fingerprint recognition experience for users.

[0132] In this embodiment, a fingerprint image verification device is also provided, which is used to implement the above embodiments and preferred implementations, and the descriptions that have been made will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0133] This embodiment provides a fingerprint image verification device, such as Figure 7 As shown, including:

[0134] A detection module 71, used to detect a user's pressing operation on the curved surface covering coating;

[0135] An acquisition module 72, configured to acquire fingerprint images collected by multiple fingerprint sensors on the curved surface coating when a pressing operation is detected;

[0136] A matching module 73, configured to match a first fingerprint image collected by a first sensor in the fingerprint sensor with a first fingerprint template associated with the first sensor to obtain a first matching number;

[0137] The trigger module 74 is used to trigger the hierarchical verification mechanism according to the first matching number, verify the remaining fingerprint images, and obtain a verification result.

[0138] In an optional embodiment of the present application, the device also includes: a storage module, which is used to obtain original fingerprint images collected by multiple fingerprint sensors on the curved surface covering coating; filter the original fingerprint images according to preset entry standards to obtain multiple standard fingerprint images; extract multiple preset feature points of the standard fingerprint image, and use the preset feature points to construct a fingerprint template, and associate the fingerprint template with the corresponding fingerprint sensor and store it in the template storage space.

[0139] In an optional embodiment of the present application, the matching module 73 is used to traverse the preset numbers corresponding to the fingerprint sensors; determine the first sensor of the first priority according to the preset numbers; obtain the first fingerprint image collected by the first sensor and the corresponding first fingerprint template; extract multiple first feature points in the first fingerprint image, and match the first feature points with the preset feature points in the first fingerprint template to obtain a first matching number.

[0140] In an optional embodiment of the present application, the trigger module 74 is used to compare the first matching number with the preset matching number; if the first matching number does not reach the preset matching number, the hierarchical verification mechanism is triggered to verify the remaining fingerprint images to obtain a verification result; or, if the first matching number reaches the preset matching number, the verification result is determined to be a successful fingerprint verification.

[0141] In an optional embodiment of the present application, the trigger module 74 is used to obtain the distribution status of the remaining sensors in the fingerprint sensor; if the distribution status is multiple small array sensors, the verification operation of the remaining fingerprint images is performed based on the first strategy to obtain a first verification result; if the distribution status is a ring sensor, the verification operation of the remaining fingerprint images is performed based on the second strategy to obtain a second verification result.

[0142] In an optional embodiment of the present application, the trigger module 74 is used to determine the second sensor of the next priority according to the preset number corresponding to the fingerprint sensor; obtain the second fingerprint image collected by the second sensor and the corresponding second fingerprint template; extract multiple second feature points in the second fingerprint image, and match the second feature points with the preset feature points in the second fingerprint template to obtain a second matching number; calculate the sum of the first matching number and the second matching number, and determine whether the sum reaches the first verification threshold; if the first verification threshold is reached, determine that the first verification result is a successful fingerprint verification, and terminate the matching operation, or, if the first verification threshold is not reached, repeat the matching operation until all fingerprint sensors are compared and the first verification threshold is not reached, and determine that the first verification result is a failed fingerprint verification.

[0143] In an optional embodiment of the present application, the trigger module 74 is used to obtain a third fingerprint image collected by the annular sensor and a corresponding third fingerprint template; extract multiple third feature points in the third fingerprint image, and classify the third feature points according to preset areas to obtain a feature point set corresponding to each area; match the feature point set corresponding to each area with the third preset feature point in the third fingerprint template to obtain multiple matching areas; determine whether the number of matching areas reaches a third verification threshold; if the third verification threshold is reached, determine that the second verification result is a successful fingerprint verification, or, if the third verification threshold is not reached, determine that the second verification result is a failed fingerprint verification.

[0144] See also Figure 8 , Figure 8 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 8 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system).

[0145] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0146] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0147] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of a computer device based on the presentation of a small program landing page, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0148] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0149] The computer device further comprises a communication interface 30 for the computer device to communicate with other devices or a communication network.

[0150] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0151] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A fingerprint image verification method, characterized in that: The method comprises: Detecting a user's pressing operation on the curved surface covering coating; When a pressing operation is detected, acquiring fingerprint images collected by multiple fingerprint sensors on the curved surface covering coating; Matching a first fingerprint image captured by a first sensor of the fingerprint sensor with a first fingerprint template associated with the first sensor to obtain a first matching number; A hierarchical verification mechanism is triggered according to the first matching number, and the remaining fingerprint images are verified to obtain a verification result.

2. The method according to claim 1, characterized in that Before detecting a user's pressing operation on the curved surface covering coating, the method further includes: Acquire original fingerprint images collected by multiple fingerprint sensors on the curved surface covering coating; Filter the original fingerprint image according to a preset entry standard to obtain a plurality of standard fingerprint images; A plurality of preset feature points of the standard fingerprint image are extracted, and a fingerprint template is constructed using the preset feature points, and the fingerprint template is associated with the corresponding fingerprint sensor and stored in a template storage space.

3. The method according to claim 1, characterized in that The step of matching a first fingerprint image acquired by a first sensor in the fingerprint sensor with a first fingerprint template associated with the first sensor to obtain a first matching number includes: Traversing the preset numbers corresponding to the fingerprint sensors; Determine a first sensor with a first priority according to the preset number; Acquire a first fingerprint image captured by the first sensor and a corresponding first fingerprint template; A plurality of first feature points are extracted from the first fingerprint image, and the first feature points are matched with preset feature points in the first fingerprint template to obtain a first matching number.

4. The method according to claim 1, characterized in that: The triggering of the hierarchical verification mechanism according to the first number of matches to verify the remaining fingerprint images and obtain the verification result includes: comparing the first matching number with a preset matching number; If the first matching number does not reach the preset matching number, the hierarchical verification mechanism is triggered to verify the remaining fingerprint images to obtain a verification result; Alternatively, if the first matching number reaches a preset matching number, the verification result is determined to be a successful fingerprint verification.

5. The method according to claim 4, characterized in that The triggering of the hierarchical verification mechanism to verify the remaining fingerprint images to obtain a verification result includes: Obtaining the distribution status of the remaining sensors in the fingerprint sensor; If the distribution state is a plurality of small array sensors, performing a verification operation of the remaining fingerprint image based on a first strategy to obtain a first verification result; If the distribution state is a ring sensor, a verification operation of the remaining fingerprint image is performed based on a second strategy to obtain a second verification result.

6. The method according to claim 5, characterized in that The performing the verification operation of the remaining fingerprint image based on the first strategy to obtain a first verification result includes: Determine a second sensor of next priority according to a preset number corresponding to the fingerprint sensor; Acquire a second fingerprint image collected by the second sensor and a corresponding second fingerprint template; Extracting a plurality of second feature points in the second fingerprint image, and matching the second feature points with preset feature points in the second fingerprint template to obtain a second matching number; Calculating a sum of the first matching number and the second matching number, and determining whether the sum reaches a first verification threshold; If the first verification threshold is reached, the first verification result is determined to be a successful fingerprint verification and the matching operation is terminated; or, if the first verification threshold is not reached, the matching operation is repeated until all fingerprint sensors are matched and the first verification threshold is not reached, and the first verification result is determined to be a failed fingerprint verification.

7. The method according to claim 5, characterized in that The performing the verification operation of the remaining fingerprint image based on the second strategy to obtain a second verification result includes: Acquire a third fingerprint image collected by the annular sensor and a corresponding third fingerprint template; Extracting a plurality of third feature points from the third fingerprint image, and classifying the third feature points according to preset areas to obtain a set of feature points corresponding to each area; Matching the feature point set corresponding to each area with the third preset feature point in the third fingerprint template to obtain multiple matching areas; Determining whether the number of regions of the matching regions reaches a third verification threshold; If the third verification threshold is reached, the second verification result is determined to be a successful fingerprint verification, or, if the third verification threshold is not reached, the second verification result is determined to be a failed fingerprint verification.

8. A fingerprint image verification device, characterized in that: The device comprises: A detection module, used to detect a user's pressing operation on the curved surface covering coating; An acquisition module, configured to acquire fingerprint images collected by multiple fingerprint sensors on the curved surface covering coating when a pressing operation is detected; a matching module, configured to match a first fingerprint image acquired by a first sensor of the fingerprint sensor with a first fingerprint template associated with the first sensor to obtain a first matching number; A trigger module is used to trigger a hierarchical verification mechanism according to the first matching number, verify the remaining fingerprint images, and obtain a verification result.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the method according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 7.

Images