TWI631512B - Fingerprint verification method and electronic device - Google Patents

Abstract

The invention provides a fingerprint verification method and an electronic device. The fingerprint verification method includes the following steps. Perform a fingerprint sensing operation to obtain a fingerprint image. And analyzing the fingerprint image to obtain the first feature information and the second feature information, wherein the first feature information is a plurality of fingerprint features of the fingerprint image, and the second feature information is multiple of the fingerprint image Pore characteristics. Combining the first feature information and the second feature information to obtain third feature information and fourth feature information. And verifying whether at least one of the third feature information and the fourth feature information of the fingerprint image matches the registered fingerprint image to identify the fingerprint image as a real fingerprint image.

Description

Fingerprint verification method and electronic device

The present invention relates to a verification method, and in particular to a fingerprint verification method and an electronic device to which the fingerprint verification method is applied.

The types of biometrics include face, sound, iris, retina, vein, fingerprint, and palmprint recognition. Since each person's fingerprint is unique and the fingerprint is not easy to change with age or physical health, the fingerprint identification device has become the most popular biometric identification device. However, in the technical field of fingerprint recognition, since the fingerprint identification is difficult to distinguish the difference between the authentic finger, if the fake finger mimics the fingerprint of the human finger, the verification of the conventional fingerprint identification may result in a safety problem. Accordingly, how to provide accurate and safe fingerprint verification technology is an important issue at present.

The invention provides a fingerprint verification method and an electronic device, which can provide an accurate and safe fingerprint verification function.

The fingerprint verification method of the present invention includes the following steps. Perform a fingerprint sensing operation to obtain a fingerprint image. And analyzing the fingerprint image to obtain the first feature information and the second feature information, wherein the first feature information is a plurality of fingerprint features of the fingerprint image, and the second feature information is multiple of the fingerprint image Pore characteristics. Combining the first feature information and the second feature information to obtain third feature information and fourth feature information, wherein the third feature information is that each of the plurality of fingerprint features is within a preset range a geometric relationship between the corresponding plurality of pore features, wherein the fourth feature information is at least one of the plurality of corresponding pore features of each of the plurality of fingerprint features respectively within a preset range A geometric relationship with at least one of the corresponding plurality of pore features. Verifying that at least one of the third feature information and the fourth feature information of the fingerprint image matches the registered fingerprint image to identify the fingerprint image as a real fingerprint image.

In an embodiment of the invention, the step of obtaining the plurality of fingerprint features of the fingerprint image comprises: verifying whether the first feature information of the fingerprint image matches the registered fingerprint image to determine a re Performing the fingerprint sensing operation.

In an embodiment of the present invention, the step of obtaining the third feature information and the fourth feature information includes: recording, corresponding to a feature point of each of the plurality of fingerprint features in the preset range The number of the plurality of pore features is described as the third feature information.

In an embodiment of the invention, the step of obtaining the third feature information and the fourth feature information includes recording the feature points of each of the plurality of fingerprint features within the preset range a distance of each of the plurality of pore features to serve as the third feature information.

In an embodiment of the invention, the step of obtaining the third feature information and the fourth feature information includes recording the feature points of each of the plurality of fingerprint features within the preset range The direction of the connection of each of the plurality of pore features is used as the third feature information.

In an embodiment of the invention, the step of acquiring the third feature information and the fourth feature information includes: recording, by the feature point of each of the plurality of fingerprint features, within the preset range The distance between at least one of the plurality of pore features and at least one of the corresponding one of the plurality of pore features as the fourth feature information.

In an embodiment of the invention, each of the plurality of fingerprint features has at least two pore features within the predetermined range.

In an embodiment of the present invention, the fingerprint verification method further includes: after identifying the fingerprint image as the real fingerprint image, verifying the fourth feature information of the fingerprint image and the registered fingerprint again. Whether the images match to determine that the fingerprint image passes verification.

The electronic device of the present invention includes an image analysis module and a fingerprint verification module. The image analysis module is configured to analyze the fingerprint image to obtain the first feature information and the second feature information. The first feature information is a plurality of fingerprint features of the fingerprint image, the second feature information is a plurality of pore features of the fingerprint image, and the image analysis module is further configured to combine the first feature The information and the second feature information are used to obtain the third feature information and the fourth feature information. The third feature information is a geometric relationship between each of the plurality of fingerprint features and a corresponding plurality of pore features in a preset range, and the fourth feature information is the plurality of fingerprint features Each of the geometric relationships between at least one of the corresponding plurality of pore features within a predetermined range and at least one of the corresponding one of the plurality of pore features. The fingerprint verification module is configured to verify whether the registered fingerprint image matches at least one of the third feature information and the fourth feature information of the fingerprint image to identify the fingerprint image as a real fingerprint image.

In an embodiment of the invention, after the fingerprint verification module recognizes the fingerprint image as the real fingerprint image, the fingerprint verification module verifies the fingerprint image again by using the registered fingerprint image. Whether the fourth feature information matches the registered fingerprint image to determine that the fingerprint image passes verification.

Based on the above, the fingerprint verification method and the electronic device of the present invention can provide an accurate and highly secure fingerprint verification function by analyzing the geometric relationship between the fingerprint feature and the pore feature.

The above described features and advantages of the invention will be apparent from the following description.

1 is a block diagram of an electronic device in accordance with an embodiment of the present invention. Referring to FIG. 1, in the embodiment, the electronic device 100 is, for example, a smart phone, a tablet, a desktop computer or a notebook computer or other similar electronic device having a fingerprint sensor. The electronic device 100 includes a fingerprint sensor 110, a processor 120, and a storage device 130.

In this embodiment, the fingerprint sensor 110 can be an optical, resistive, capacitive or other kind of sensing component for sensing a user's operation (eg, touching or approaching) to capture a fingerprint image. However, the invention is not limited thereto. Those skilled in the art can select the fingerprint sensor 110 that captures the fingerprint image in different ways according to actual needs.

In this embodiment, the processor 120 is, for example, a central processing unit (CPU) or other programmable general purpose or special purpose microprocessor (Microprocessor), digital signal processor (Digital Signal Processor, DSP). ), programmable controller, Application Specific Integrated Circuits (ASIC), Programmable Logic Device (PLD) or other similar devices or a combination of these devices. The processor 120 is coupled to the fingerprint sensor 110 and the storage device 130. The processor 120 loads the image analysis module 131 and the fingerprint verification module 132 from the storage device 130, thereby executing the embodiments of the present invention. Fingerprint verification method. That is, the image analysis module 131 and the fingerprint verification module 132 of the embodiment are implemented by software, and the image analysis module 131 and the fingerprint verification module 132 may further include multiple sub-image processing modules. In order to implement the fingerprint verification method of various embodiments of the present invention.

In this embodiment, the storage device 130 can be any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory. A flash memory or similar element or a combination of the above elements. In the embodiment, the storage device 130 is used to record the image analysis module 131 and the fingerprint verification module 132. The modules are, for example, programs stored in the storage device 130. Moreover, in an embodiment, the storage device 130 can also be used to store fingerprint images captured by the fingerprint sensor 110.

2 is a flow chart of a fingerprint verification method in accordance with an embodiment of the present invention. Referring to FIG. 1 and FIG. 2, the fingerprint verification method of the present embodiment is applied to the electronic device 100 of FIG. 1, and the detailed steps of the fingerprint verification method of the present invention are described below with the components in the electronic device 100.

First, in step S210, the electronic device 100 can perform a fingerprint sensing operation by the fingerprint sensor 110 to capture a fingerprint image. The fingerprint sensing operation means that when the user's finger is pressed against the fingerprint sensor 110, the fingerprint sensor 110 can capture the user's finger image, and further obtain the user's fingerprint by image analysis. Then, in step S220, the processor 120 may analyze the fingerprint image by executing the image analysis module 131 to obtain the first feature information and the second feature information. The first feature information is a plurality of fingerprint features in the fingerprint image, and the second feature information is a plurality of pore features in the fingerprint image. Then, the processor 120 can further obtain the third feature information and the fourth feature information by combining the first feature information and the second feature information by executing the image analysis module 131. For example, a plurality of fingerprint features and positions, coordinates or images of the plurality of pore features are overlapped to obtain a relative geometric relationship between the plurality of fingerprint features and the plurality of pore features. Therefore, in this embodiment, the third feature information is a geometric relationship between each of the plurality of fingerprint features and the corresponding plurality of pore features in a preset range. The fourth feature information is a geometric relationship between at least one of the plurality of corresponding pore features in each of the plurality of fingerprint features and at least one of the corresponding plurality of pore features. Finally, the processor 120 can perform the fingerprint verification module 132 to verify whether at least one of the third feature information and the fourth feature information of the fingerprint image matches the registered fingerprint image to identify the fingerprint image as a real fingerprint image.

That is to say, even if the fake finger mimics the fingerprint texture and the fingerprint feature, it even mimics a part of the pore feature. However, the fake finger cannot imitate all the pore features like the living body, and the relative position of each pore feature cannot be the same as the real finger of the living body. Therefore, the electronic device 100 of the present embodiment can further verify whether the fingerprint image acquired by the fingerprint sensor 110 is taken from the real finger of the living body by analyzing the fingerprint features of the fingerprint image and the geometric relationship between the plurality of pore features. In this way, the false finger can be excluded from passing verification.

FIG. 3 is a schematic diagram of a fingerprint image according to an embodiment of the present invention. Referring to FIG. 1 and FIG. 3, the fingerprint image captured by the fingerprint sensor 110 of the embodiments of the present invention may be, for example, the fingerprint shown in FIG. 3. Image FI_1. In the embodiment, the fingerprint image FI_1 may be an image of all or part of the finger, and the present invention is not limited thereto. Moreover, in the present embodiment, the fingerprint image FI_1 has the characteristics of fingerprint lines and pores.

4A is a schematic diagram of first feature information in accordance with an embodiment of the present invention. 4B is a schematic diagram of second feature information in accordance with an embodiment of the present invention. Referring to FIG. 1 and FIG. 4A, the first feature information described in the embodiments of the present invention may be, for example, the fingerprint image FI_2 shown in FIG. 4A. In this embodiment, the processor 120 can analyze the fingerprint image FI_2 by executing the image analysis module 131, and further obtain the positions of the plurality of fingerprint features 401-406, wherein the fingerprint feature can be, for example, the end of the fingerprint line of the finger. Points, bifurcation points or short lines, etc., the invention is not limited. Referring to FIG. 1 and FIG. 4B, the second feature information in the embodiments of the present invention may be the fingerprint image FI_3 shown in FIG. 4B. In this embodiment, the processor 120 can analyze the fingerprint image FI_3 by executing the image analysis module 131 to further obtain the positions of the plurality of pore features 500.

Specifically, in this embodiment, the processor 120 may perform image analysis and processing on the fingerprint image captured by the fingerprint sensor 110, for example, analyzing the grayscale degree or change of the fingerprint image. For example, the processor 120 may define a texture whose grayscale value is higher than a preset threshold as a fingerprint, and determine a position of an end point, a bifurcation point or a short pattern of the fingerprint texture as a fingerprint feature. As another example, processor 120 may define the location of each individual point where the grayscale changes are large as a pore feature. However, in an embodiment, the fingerprint image may be determined according to different types of fingerprint sensors 110, and the analysis of the fingerprint image may also perform color change analysis using, for example, a color fingerprint image, and the present invention is not limited thereto.

FIG. 5A is a schematic diagram of third feature information according to an embodiment of the invention. FIG. 5B is a schematic diagram of fourth feature information according to an embodiment of the invention. Referring to FIG. 1 and FIG. 5A, the third feature information described in the embodiments of the present invention may be, for example, the fingerprint image FI_4 shown in FIG. 5A. In this embodiment, the processor 120 can perform the image analysis module 131 to combine the first feature information and the second feature information of the fingerprint image to further obtain the third feature information.

Specifically, in the embodiment, the image analysis module 131 can combine the position information of the fingerprint feature and the position information of the pore feature, and in particular, determine the corresponding pore feature within the preset range of each fingerprint feature. As shown in FIG. 5A, the fingerprint feature 601 can have 14 pore features 701-714 within a predetermined range 601S of the radius R. The image analysis module 131 can record the geometric relationship between the fingerprint feature 601 and the pore features 701-714 as the third feature information. In the present embodiment, the radius R may be preset such that each of the fingerprint features has at least two pore features within a predetermined range 601S. In an embodiment, the size of the radius R can be set according to different judgment requirements, and the invention is not limited.

In this embodiment, the third feature information may be a geometric relationship between the fingerprint feature 601 and the pore features 701-714. In an implementation scenario, the image analysis module 131 can record, for example, the number of corresponding pore features 701-714 in the preset range 601S of the feature features of the fingerprint feature 601 as the third feature information. Alternatively, in another implementation scenario, the image analysis module 131 may, for example, record the distance between the feature points of the fingerprint feature 601 and each of the pore features 701-714 within the preset range 610S. Three feature information. For example, the distance a1 between the fingerprint feature 601 and the pore feature 701. Alternatively, in another implementation scenario, the image analysis module 131 may, for example, record the connection direction or vector of the feature points of the fingerprint feature 601 in each of the preset features 601S and the pore features 701-714 as Third feature information. For example, the fingerprint feature 601 and the connection feature direction d1 of the pore feature 701. It should be noted that the third feature information of each embodiment of the present invention may include at least the number of pore features, the distance between the fingerprint feature and the pore feature, and the connection direction between the fingerprint feature and the pore feature. At least one of them.

Referring to FIG. 1 and FIG. 5B, the fourth feature information described in the embodiments of the present invention may be, for example, the fingerprint image FI_5 shown in FIG. 5B. In this embodiment, the processor 120 can perform the image analysis module 131 to combine the first feature information and the second feature information of the fingerprint image to further obtain the fourth feature information.

Specifically, in the embodiment, the image analysis module 131 can combine the position information of the fingerprint feature and the position information of the pore feature, and in particular, determine the corresponding pore feature within the preset range of each fingerprint feature. As shown in FIG. 5B, the fingerprint feature 801 can have 14 pore features within a predetermined range 801S of the radius R. The image analysis module 131 can record the geometric relationship between the pore features in the preset range 801S of the fingerprint feature 801 as the fourth feature information.

In this embodiment, the image analysis module 131 may, for example, record at least one of the corresponding pore features of the feature point of the fingerprint feature 801 in the preset range 801S and at least one of the corresponding pore features. The distance between the two is used as the fourth feature information. For example, the distance b1 between the pore feature 901 and the pore feature 902. In this embodiment, the image analysis module 131 can record the distance between all or part of the pore features. That is, the radius R of the embodiment may be preset to include at least two pore features, so that the image analysis module 131 can obtain the geometric relationship between the two pore features, but the invention is not limited thereto.

FIG. 6 is a flowchart of a fingerprint registration method according to an embodiment of the present invention. Please refer to FIG. 1 and FIG. 6. In this embodiment, the electronic device 100 may pre-store the registered fingerprint image for verification. Moreover, the fingerprint registration method of the present embodiment is applied to the electronic device 100 of FIG. 1, and the detailed steps of the fingerprint registration method of the present invention are described below in conjunction with the components in the electronic device 100.

First, in step S1010, the electronic device 100 can perform a fingerprint sensing operation by the fingerprint sensor 110 to capture a fingerprint image. Next, in step S1020 and step S1040, the image analysis module 131 can analyze the fingerprint image to obtain a plurality of fingerprint features and obtain a plurality of pore features. Then, in step S1030 and step S1050, the image analysis module 131 can respectively locate a plurality of fingerprint features and a plurality of pore features (such as the first feature information and the second feature information) among the fingerprint images. In addition, in step S1060, the image analysis module 131 may be further configured to calculate a geometric relationship between each of the plurality of fingerprint features and a corresponding plurality of pore features in a preset range, and calculate the plurality of fingerprint features. The geometric relationship between the plurality of pore features corresponding to each of the preset ranges (like the third feature information and the fourth feature information). Finally, in step S1070, the image analysis module 131 can record the fingerprint image and the analysis result in the storage device as the registered fingerprint image.

7 is a flow chart of a fingerprint verification method in accordance with another embodiment of the present invention. 1 and 7 are referred to. The fingerprint registration method of the present embodiment is applicable to the electronic device 100 of FIG. 1, and the detailed steps of the fingerprint verification method of the present invention are described below with the components in the electronic device 100.

First, in step S1110, the electronic device 100 can perform a fingerprint sensing operation by the fingerprint sensor 110 to capture a fingerprint image. Next, in steps S1120 and S1040, the image analysis module 131 may analyze the fingerprint image to obtain a plurality of fingerprint features and obtain a plurality of pore features. Then, in step S1130 and step S1150, the image analysis module 131 can respectively locate the plurality of fingerprint features and the positions of the plurality of pore features in the fingerprint image as the first feature information and the second feature information, respectively. Then, in step S1160, the image analysis module 131 may first verify whether the first feature information matches the registered fingerprint image to determine whether to retrieve the fingerprint image. That is to say, the fingerprint registration method in this embodiment may first determine whether the fingerprint feature in the fingerprint image is identical to the fingerprint feature of the fingerprint image registered by the user to determine whether to continue execution. In this regard, unnecessary analysis and verification of fingerprint images that do not match the fingerprint feature and the registered fingerprint image can be avoided.

Then, in step S1170, when the image analysis module 131 determines that the fingerprint feature of the fingerprint image matches the registered fingerprint image, the image analysis module 131 may further combine the first feature information and the second feature information to obtain the third Feature information and fourth feature information. Finally, in step S1180, the processor 120 may execute the fingerprint verification module 132 to verify whether at least one of the third feature information and the fourth feature information of the fingerprint image matches the registered fingerprint image. That is, if the fingerprint image and the registered fingerprint image have at least one of the third feature information and the fourth feature information, the fingerprint verification module 132 determines that the verification is performed, so that the electronic device 100 can enter, for example, The present invention is not limited in its one-step work phase or execution of an application. On the other hand, if the fingerprint image does not have the same third feature information and the fourth feature information, the processor 120 determines that the fingerprint image is a non-authentic fingerprint image, and performs a fingerprint sensing operation again, so that the fingerprint image is re-executed. Re-acquire the fingerprint image. Incidentally, in step S1180, the processor 120 may determine the third feature information or the fourth feature information of the fingerprint image separately according to different verification requirements, or use the third feature information of the fingerprint image and the first Four feature information is used for verification, and the present invention is not limited thereto.

In summary, the fingerprint verification method and the electronic device of the present invention can acquire a plurality of fingerprint features and a plurality of pore features by executing an image analysis module, and combine the two to further record a plurality of fingerprint features and a plurality of The relative relationship between pore characteristics. That is, the fingerprint verification method and the electronic device of the present invention can accurately perform fingerprinting by verifying the fingerprint features between the captured fingerprint image and the registered fingerprint image and the geometric relationship between the pore features. Verification, and can effectively avoid the fingerprint of the non-living pseudo finger to pass the verification, further providing a high security fingerprint recognition function.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention, and any one of ordinary skill in the art can make some changes and refinements without departing from the spirit and scope of the present invention. The scope of the invention is defined by the scope of the appended claims.

100: electronic device 110: fingerprint sensor 120: processor 130: storage device 131: image analysis module 132: fingerprint verification module S210, S220, S230, S240, S1010, S1020, S1030, S1040, S1050, S1060, S1070, S1110, S1120, S1130, S1140, S1150, S1160, S1170, S1180: steps FI_1, FI_2, FI_3, FI_4, FI_5: fingerprint images 401, 402, 403, 404, 405, 406, 601, 801: fingerprint feature 500 , 701, 702, 703, 704, 705, 706, 707, 708, 709, 710, 711, 712, 713, 714, 901, 902: pore features 601S, 801S: preset range R: radius a1, b1: distance D1: direction

1 is a block diagram of an electronic device in accordance with an embodiment of the present invention. 2 is a flow chart of a fingerprint verification method in accordance with an embodiment of the present invention. 3 is a schematic diagram of a fingerprint image in accordance with an embodiment of the present invention. 4A is a schematic diagram of first feature information in accordance with an embodiment of the present invention. 4B is a schematic diagram of second feature information in accordance with an embodiment of the present invention. FIG. 5A is a schematic diagram of third feature information according to an embodiment of the invention. FIG. 5B is a schematic diagram of fourth feature information according to an embodiment of the invention. 6 is a flow chart of a fingerprint registration method in accordance with an embodiment of the present invention. 7 is a flow chart of a fingerprint verification method in accordance with another embodiment of the present invention.

Claims (8)

A fingerprint verification method includes: performing a fingerprint sensing operation to obtain a fingerprint image; analyzing the fingerprint image to obtain a first feature information and a second feature information, wherein the first feature information is the a plurality of fingerprint features of the fingerprint image, the second feature information is a plurality of pore features of the fingerprint image; combining the first feature information and the second feature information to obtain a third feature information and a first feature Four feature information, wherein the third feature information is that each of the plurality of fingerprint features is within a predetermined range and at least a quantity, a distance, and a connection direction between the corresponding plurality of pore features In one aspect, the fourth feature information is that at least one of the corresponding plurality of pore features and each of the plurality of pore features in each of the plurality of fingerprint features are respectively within the preset range a distance between at least one of the other; verifying at least one of the third feature information of the fingerprint image and the fourth feature information with a registered Whether the fingerprint image matches to identify the fingerprint image as a real fingerprint image; and after identifying the fingerprint image as the real fingerprint image, verifying the fourth feature information of the fingerprint image and the registered fingerprint again Whether the images match to determine that the fingerprint image passes verification. The fingerprint verification method of claim 1, wherein the step of obtaining the plurality of fingerprint features of the fingerprint image comprises: verifying the first feature information of the fingerprint image and the registered fingerprint image Like if it matches, to decide to re-execute the fingerprint sensing operation. The fingerprint verification method of claim 1, wherein the obtaining the third feature information and the fourth feature information comprises: recording feature points of each of the plurality of fingerprint features in the pre- The number of the plurality of pore features corresponding to the range is set as the third feature information. The fingerprint verification method of claim 1, wherein the obtaining the third feature information and the fourth feature information comprises: recording feature points of each of the plurality of fingerprint features in the pre- A distance within the range from each of the plurality of pore features is set as the third feature information. The fingerprint verification method of claim 1, wherein the obtaining the third feature information and the fourth feature information comprises: recording feature points of each of the plurality of fingerprint features in the pre- A direction of connection between each of the plurality of pore features in the range is set as the third feature information. The fingerprint verification method of claim 1, wherein the obtaining the third feature information and the fourth feature information comprises: recording feature points of each of the plurality of fingerprint features in the pre- And providing a distance between at least one of the plurality of pore features corresponding to the plurality of pore features and at least one of the corresponding plurality of pore features as the fourth feature information. The fingerprint verification method of claim 1, wherein each of the plurality of fingerprint features has at least two pore features within the predetermined range. An electronic device includes: an image analysis module for analyzing a fingerprint image to obtain a first feature information and a second feature information, wherein the first feature information is a plurality of fingerprint features of the fingerprint image The second feature information is a plurality of pore features of the fingerprint image, and the image analysis module is further configured to combine the first feature information and the second feature information to obtain a third feature information. And a fourth feature information, wherein the third feature information is a quantity, a distance, and a connection direction between each of the plurality of fingerprint features and a corresponding plurality of pore features in a predetermined range At least one of the fourth feature information is that at least one of the corresponding plurality of pore features and each of the plurality of fingerprint features are respectively within the preset range a distance between at least one of the other pore features; and a fingerprint verification module for verifying a registered fingerprint image and the third feature information of the fingerprint image Whether at least one of the fourth feature information matches to identify the fingerprint image as a real fingerprint image, wherein the fingerprint verification module identifies the fingerprint image as the real fingerprint image, and the fingerprint verification The module re-verifies whether the fourth feature information of the fingerprint image matches the registered fingerprint image by using the registered fingerprint image to determine that the fingerprint image passes verification.