CN112001233A - Biological characteristic identification system and identification method - Google Patents

Abstract

The invention discloses a biological characteristic identification system and a biological characteristic identification method, wherein the biological characteristic identification system comprises a sensor, a first sensor, a second sensor and a third sensor, wherein the sensor is used for sensing a first biological characteristic to generate an image; a first feature extraction unit, coupled to the sensor, for generating a first information according to the image, the first information describing a uniqueness of the first biological feature; a second feature extraction unit, coupled to the sensor, for generating a second information according to the image, where the second information describes a true or false characteristic of the first biological feature; and an identification unit coupled to the first feature extraction unit and the second feature extraction unit for generating an identification result according to the first information and/or the second information.

Description

Biometric identification system and identification method

technical field

The present invention relates to a biometric identification system and identification method.

Background technique

More and more electronic devices or systems use biometrics to identify users. Common biometric identifications include fingerprint identification, face identification, iris identification, voiceprint identification and palmprint identification. However, the current biometric identification still has shortcomings. For example, fingerprint identification cannot effectively distinguish the authenticity of a finger. Therefore, there are still concerns that biometric identification systems may be deceived.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide a biometric identification system and identification method thereof, which can avoid false biometric identification through identity identification.

According to the present invention, a biological feature identification system includes a sensor, a first feature extraction unit, a second feature extraction unit and an identification unit. The sensor senses a first biometric feature to generate an image. The first feature extraction unit is coupled to the sensor, and generates first information according to the image, wherein the first information describes the true and false characteristics of the first biological feature. The second feature extraction unit is coupled to the sensor, and generates a second information according to the image, wherein the second information describes the true and false characteristics of the first biological feature. The identification unit is coupled to the first feature extraction unit and the second feature extraction unit, and generates an identification result according to the second information or the first information and the second information.

According to the present invention, a method for identifying a biometric feature includes: sensing a first biometric feature to generate an image; generating a first information according to the image, wherein the first information describes the uniqueness of the first biometric feature; Obtaining a second information from the image, wherein the second information describes the true and false characteristics of the first biological feature; and generating an identification result according to the second information or the first information and the second information.

The identification system and method of the present invention can effectively improve the security of the biometric identification system and prevent false biometrics from passing identity authentication.

Description of drawings

FIG. 1 is a block diagram of an embodiment of a biometric identification system of the present invention.

FIG. 2 shows a flow chart of the biometric identification method of the present invention.

Figure 3 shows a block diagram of an embodiment of a CNN and a classifier.

Description of reference numerals: 10-recognition system; 11-sensor; 12-first feature extraction unit; 13-second feature extraction unit; 131-convolutional neural network; 1311-feature extraction part; 1312-classification part; 14 - memory; 15 - recognition unit; 151 - classifier.

Detailed ways

1 shows an embodiment of the biometric identification system of the present invention. The identification system 10 includes a sensor 11 , a first feature extraction unit 12 , a second feature extraction unit 13 , a memory 14 , and an identification unit 15 . The sensor 11 may be an image sensor for sensing the first biometric feature to generate an image A. The first biometric feature may be, for example, a fingerprint, a face, a palm print, or an iris. The first feature extraction unit 12, the second feature extraction unit 13 and the identification unit 15 may be implemented by software or hardware. The first feature extraction unit 12 is coupled to the sensor 11, and generates a first information according to the image A provided by the sensor 11, and the first information describes the uniqueness of the first biological feature. The first information includes sets of feature vectors. In one embodiment, the first feature extraction unit 12 may use a computer vision method to extract features of the image A to generate the first information. The computer vision method can be, for example, Features From Accelerated Segment Test (FAST), Adaptive and generic corner detection based on the accelerated segment test (AGAST), Scale-invariant feature transformation (Scale- Algorithms such as invariant feature transform, SIFT), Speeded Up Robust Features (SURF), KAZE or AKAZE, etc. In another embodiment, the first feature extraction unit 12 is a trained deep learning model, which may be implemented with, for example, a model architecture based on a Convolutional Neural Network (CNN) 131 . The method used by the first feature extraction unit 12 may be, but not limited to, Local Binary Patterns (LBP), Local Phase Quantization (LPQ) or Histogram of Oriented Gradient (HOG), etc. etc. algorithm.

The second feature extraction unit 13 is coupled to the sensor 11, and generates a second information according to the image A, and the second information describes the true and false characteristics of the first biological feature. In one embodiment, the second feature extraction unit 13 may use a computer vision method to extract features of the image A to generate the second information. The computer vision method may be to use, for example, Features From Accelerated Segment Test (FAST), Adaptive and generic corner detection based on the accelerated segment test (AGAST), scale-invariant feature transformation ( Scale-invariant feature transform, SIFT), speeded up robust features (Speeded Up Robust Features, SURF), KAZE or AKAZE and so on. In another embodiment, the second feature extraction unit 13 is a pre-trained deep learning model, which may be implemented, for example, based on a convolutional neural network (Convolutional Neural Network, CNN) 131 or its improved model architecture, or It can also be a deep network model such as AlexNet, MobileNet, etc. The method used by the second feature extraction unit 13 may be, but not limited to, Local Binary Patterns (LBP), Local Phase Quantization (LPQ) or Histogram of Oriented Gradient (HOG), etc. etc. algorithm. In one embodiment, the second information includes an embedding feature of the image, and the embedded feature is vector data generated when the CNN 131 performs data conversion according to the image A, and is used to describe the authenticity of the first biological feature. A property that is not just a number representing true (1) or false (0).

Although the first feature extraction unit 12 and the second feature extraction unit 13 are both used for feature extraction. But the purpose of the two is not the same, and the coefficients used to extract the features are not the same. The first feature extraction unit 12 and the second feature extraction unit 13 can be understood as viewing the image A from different angles. The first feature extraction unit 12 is used to describe the uniqueness of the first biological feature shown in the image A, such as the distribution relationship of some specific feature points. This uniqueness can be used to distinguish different individuals. The second feature extraction unit 13 is used to describe the true and false characteristics of the first biological feature shown in the image A, and is usually used to judge whether the first biological feature is from a living body.

The memory 14 is respectively coupled to the first feature extraction unit 12 , the second feature extraction unit 13 and the identification unit 15 for storing a first template information and a second template information. The first template information and the second template information are generated by the first feature extraction unit 12 and the second feature extraction unit 13 respectively in the user's enrollment process. In the registration process, the sensor 11 senses a second biometric feature of a user to be registered to generate an image B (not shown in the figure), wherein the first biometric feature and the second biometric feature are the same type of biometric feature . The first feature extraction unit 12 generates first template information according to the image B, and the first template information describes the uniqueness of the second biological feature. The second feature extraction unit 13 generates the second template information according to the image B, and the second template information describes the true and false characteristics of the second biological feature.

The identification unit 15 is coupled to the first feature extraction unit 12 , the second feature extraction unit 13 and the memory 14 . The identification unit 15 generates an identification result according to the first information, the second information or the first information and the second information, and the identification result represents pass or fail the identity authentication. In one embodiment, the identification unit 15 includes a classifier 151 . The classifier 151 is based on a model trained by machine learning (Machine Learning), which may be implemented by a support vector machine (Support Vector Machine, SVM) or a neural network (Neural Network, NN). The classifier 151 may be a software or hardware circuit.

The following takes fingerprint identification as an example to illustrate the operation of the identification system 10 of the present invention, but the present invention is not limited to fingerprint identification, and the present invention can also be applied to other biometric identifications, such as face identification, iris identification, palmprint identification, etc. . When the identification system 10 performs the registration process, the registrant puts his finger on the sensor 11. In this embodiment, the sensor 11 is a fingerprint sensor, which may be an optical fingerprint sensor or a capacitive fingerprint sensor. The sensor 11 senses the fingerprint of the finger (equivalent to the aforementioned second biometric feature) to generate a fingerprint image Fi1. The first feature extraction unit 12 generates the first template information En1 according to the fingerprint image Fi1, and the first template information En1 can be understood as describing the fingerprint characteristics of the fingerprint image Fi1. The pattern of each person's fingerprint is unique and different from others. The first template information En1 is describing the uniqueness of the fingerprint. The second feature extraction unit 13 generates second template information En2 according to the fingerprint image Fil. The second template information En2 describes the true and false characteristics of the fingerprint image Fi1. After the first template information En1 and the second template information En2 are stored in the memory 14, the registration process is completed.

When the identification system 10 performs the verification process, after the verifier puts the finger on the sensor 11, the sensor 11 will sense the fingerprint of the finger (equivalent to the aforementioned first biometric feature) to generate a fingerprint image Fi2, as shown in the figure Step S10 of 2. The first feature extraction unit 12 generates the first information Ve1 according to the fingerprint image Fi1, as shown in step S12 in FIG. 2 . The second feature extraction unit 13 generates the second information Ve2 according to the fingerprint image Fi2, as shown in step S14 in FIG. 2 . The second information Ve2 describes the true and false characteristics of the fingerprint image Fi2. Finally, the identification unit 15 generates an identification result Vre according to the first information Ve1, the second information Ve2 or the first information Ve1 and the second information Ve2 to indicate whether the authentication succeeds or fails, as shown in step S16 in FIG. 2 .

In one embodiment, the identification unit 15 generates the identification result Vre according to the difference D1 between the first information Ve1 and the first template information En1 and the difference D2 between the second information Ve2 and the second template information En2. The identification unit 15 can use, but is not limited to, one of Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, normalized Euclidean distance, Mahalanobis distance, and Hamming distance to determine the difference between the first information Ve1 and the first information Ve1. The difference D1 of the template information En1 and the difference D2 of the second information Ve2 and the second template information En2 are judged, and then the difference D1 and D2 are multiplied by the weights W1 and W2, respectively, and then added together to generate a sum, wherein the weights W1 and W2 are not A value of 0. If the sum is less than a preset value TH1, the generated identification result Vre is a value of "1", indicating that the authentication is successful. On the contrary, if the sum is greater than the preset value TH1, the generated identification result Vre is a value of "0", indicating that the authentication is a failure.

In another embodiment, the identification unit 15 includes a classifier 151, which can be implemented by hardware or software, and uses a machine learning method for classification. The classifier 151 may perform a recognition step to generate the recognition result Vre. The identifying step includes, but is not limited to, judging the similarity between the combination of the first information Ve1 and the second information Ve2 and the combination of the first template information En1 and the second template information En2 to generate the identification result Vre. If the similarity is greater than a preset value TH2, the generated identification result Vre is a value of "1", indicating that the authentication is successful; otherwise, the generated identification result Vre is a value of "0", indicating that the authentication has failed.

In one embodiment, the identification unit 15 also includes a classifier 151. The identification unit 15 first uses but is not limited to Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, normalized Euclidean distance, Mahalanobis distance and Hamming distance. One of the distances is used to determine whether the first information Ve1 is similar to the first template information En1. If not, the identification unit 15 generates the identification result Vre as "0", indicating that the authentication fails. If so, the identifying unit 15 uses the classifier 151 to perform the aforementioned identifying steps to generate the identifying result Vre. The advantage of doing this is that it saves resources. If it is determined that the first information Ve1 is not similar to the first template information EN1, it is enough to determine that the person to be verified is different from the registered user. It is therefore unnecessary to continue the identification step.

In another embodiment, the identification unit 15 also includes a classifier 151. The identification unit 15 first uses but is not limited to Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, normalized Euclidean distance, Mahalanobis distance and Hanoi distance. One of the clear distances is used to determine whether the second information Ve2 is similar to the second template information En2. If not, the identification unit 15 generates the identification result Vre as "0", indicating that the authentication fails. If so, the identifying unit 15 uses the classifier 151 to perform the aforementioned identifying steps to generate the identifying result Vre.

If the first feature extraction unit 12 uses a trained deep learning model, pre-training is required to obtain the feature extraction capability. The following takes fingerprint recognition as an example. During the training process, fingerprint images of many different people are provided to a training program T1. The training program T1 has the same model architecture as the first feature extraction unit 12 . The training program T1 obtains a set of coefficients for extracting the features of the fingerprint images according to the fingerprint images of these different people and their corresponding owners. This process is actually to tell the training program T1 which fingerprint image represents who, and let the training program T1 learn how to classify. The first feature extraction unit 12 operates using the set of coefficients to extract the features of the fingerprint image to generate the first information. This first information describes the uniqueness of the fingerprint, and it can also be understood as describing what the fingerprint looks like in a mathematical way. If the first feature extraction unit 12 uses a computer vision method to extract features, it uses already defined features to describe what the biological feature looks like, that is, its uniqueness.

If the second feature extraction unit 13 uses a trained deep learning model, it also needs to be pre-trained to obtain the capability of feature extraction. The following takes fingerprint recognition as an example. During the training process, a large number of real fingerprint images and fake fingerprint images need to be prepared and provided to the training program T2, and the training program T2 has the same model architecture as the first feature extraction unit 13. The aforementioned large number of real fingerprint images are obtained by sensing the fingerprints of many different people, all of which are fingerprint images obtained from living bodies. These fingerprint images are formed on a material such as silica gel and then sensed to obtain the aforementioned large number of fake fingerprint images. By telling the training program T2 which are real fingerprint images and which are fake fingerprint images, the training program T2 can obtain a set of coefficients for identifying real fingerprints or fake fingerprints after learning. This process is actually letting the training program T2 learn how to identify real and fake fingerprints. The second feature extraction unit 13 uses the set of coefficients to extract the features of the fingerprint image to generate the second information. The second information can also be used to directly determine whether it is a real fingerprint or a fake fingerprint, but this is not the case in the present invention. The second feature extraction unit 13 of the present invention mainly obtains a set of feature values generated after the feature extraction and before determining the true and false fingerprints as the second information. Therefore, the second information describes the authenticity of the fingerprint, and it can also be understood to describe the authenticity of the fingerprint in a mathematical way. If the first feature extraction unit 12 uses a computer vision method to extract features, it uses already defined features to describe the true and false characteristics of the biological feature.

By providing a large number of images to the first feature extraction unit 12 and the second feature extraction unit 13 in advance, a large amount of first information and second information can be obtained for the machine learning model of the classifier 151 to learn and classify. The classifier 151 has the ability to judge the success or failure of authentication. Taking fingerprint recognition as an example, it is necessary to prepare a training program T3 which has the same model structure as the classifier 151 . Next, it is necessary to provide a large number of combinations of the first information and the second information to the training program T3, and tell the training program T3 which combinations are successful in verification and which combinations are failed in verification. For example, the training program T3 is told to use the first information and the second information generated by the real fingerprint image to represent the verification success (pass), and the first information generated from the real fingerprint image and the second information generated by the fake fingerprint to represent the verification failure (fail). From this process, the training program T3 can learn how to judge that the combination of the first information and the second information represents the verification success or failure.

It can be understood from the above description of training and identification that the present invention uses the first information generated by the first feature extraction unit 11 to determine whether the fingerprint currently sensed is similar to the registered fingerprint and the second feature extraction unit 12 The generated second information is used to judge whether the true and false characteristics of the currently sensed fingerprint are close to the true and false characteristics of the registered fingerprint, so as to determine whether the identity verification is passed.

FIG. 2 provides an embodiment to illustrate the structure of the CNN 131 , which mainly includes a feature extraction part 1311 and a classification part 1312 . The image A is processed by the feature extraction part 1311 and the classification part 1312, and the classifier 1312 generates embedded feature information, the embedded feature information represents the true and false characteristics of the biometric feature (eg fingerprint) shown in the image A. The embedded feature information may be a set of values, such as "1101000". Please note that the second feature extraction unit 13 does not use the classification part 1312 for classification to generate a true or false identification result, but obtains the embedded feature information generated by the classifier 1312 . If a feature extraction unit is used to directly determine whether a biometric feature to be verified is true or false, there may be problems with accuracy. Taking fingerprint recognition as an example, if fake fingerprints of 10 materials are provided to train the feature extraction unit, the feature extraction unit cannot accurately determine whether it is true or false for false fingerprints other than these 10 materials. However, the second feature extraction unit 13 of the present invention does not directly determine whether the biological feature is true or false, but obtains embedded feature information describing the true and false characteristics of the biological feature, which is used for comparison with the registered second template information in the memory. Comparison. Therefore, for the new material that the second extraction feature unit 13 has not learned, the impact on the accuracy of the identity verification of the present invention is relatively low.

The above description of the preferred embodiments of the present invention is for illustrative purposes, and is not intended to limit the present invention to the exact form disclosed. Modifications or changes are possible based on the above teachings or learning from the embodiments of the present invention. , the embodiment is to illustrate the principle of the present invention and to allow those skilled in the art to select and describe the present invention in practical application with various embodiments, and the technical idea of the present invention is intended to be determined by the scope of claims and their equivalents.

Claims (28)

1. A biometric identification system, characterized in that, comprising: a sensor for sensing a first biometric feature to generate an image; a first feature extraction unit, coupled to the sensor, to generate first information according to the image, the first information describing the uniqueness of the first biological feature; a second feature extraction unit, coupled to the sensor, the second feature extraction unit generates a second information according to the image, the second information describes the true and false characteristics of the first biological feature; and An identification unit, coupled to the first feature extraction unit and the second feature extraction unit, generates an identification result according to the second information or the first information and the second information. 2 . The identification system of claim 1 , wherein the identification result represents pass or fail the identity authentication. 3 . 3 . The identification system of claim 1 , wherein the sensor is a fingerprint sensor, and the first biometric feature is a fingerprint. 4 . 4. The identification system of claim 1, further comprising a memory for storing a first template information and a second template information. 5. The identification system of claim 4, wherein the identification unit generates the identification result according to the difference between the first information and the first template information and the difference between the second information and the second template information . 6. The identification system according to claim 5, wherein the identification unit uses Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, normalized Euclidean distance, Mahalanobis distance and Hamming distance. One is to determine the difference between the first information and the first template information and to determine the difference between the second information and the second template information. 7 . The identification system of claim 4 , wherein the identification unit comprises a classifier, and the classifier is used for performing an identification step to determine the combination of the first information and the second information and the first template. 8 . similarity between the combination of information and the second template information to generate the recognition result. 8. The identification system of claim 7, wherein the classifier comprises a support vector machine or a neural network. 9 . The identification system of claim 7 , wherein the identification unit further comprises first determining whether the first information is similar to the first template information, and if so, the identification unit uses the classifier to perform the identification step. 10 . 10 . The identification system of claim 7 , wherein the identification unit further comprises first judging whether the second information is similar to the second template information, and if so, the identification unit uses the classifier to perform the identification step. 11 . 11. The identification system according to claim 9 or 10, wherein the identification unit further comprises using Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, standardized Euclidean distance, Mahalanobis distance and Hanoi distance. One of the clear distances is used to determine whether the first information is similar to the first template information or to determine whether the second information is similar to the second template information. 12 . The identification system of claim 1 , wherein the first feature extraction unit or the second feature extraction unit comprises a deep learning model. 13 . 13. The identification system of claim 1, wherein the first feature extraction unit or the second feature extraction unit comprises a convolutional neural network. 14. The identification system of claim 1, wherein the first feature extraction unit or the second feature extraction unit uses accelerated segment test features, adaptive general accelerated segmentation detection, scale-invariant feature conversion, accelerated robustness Feature, KAZE, AKAZE, Local Binary Pattern, Local Phase Quantization or Orientation Gradient Histogram algorithm to obtain this first information. 15. A method for identifying biological features, comprising the following steps: A. Sensing a first biometric feature to generate an image; B. generating a first message according to the image, wherein the first message describes the uniqueness of the first biological feature; C. obtaining a second information from the image, wherein the second information describes the true and false characteristics of the first biometric; and D. Generate an identification result according to the second information or the first information and the second information. 16. The identification method of claim 15, further comprising judging whether to pass or fail the identity authentication according to the identification result. 17. The identification method of claim 15, wherein the first biometric feature is a fingerprint. 18. The identification method of claim 15, further comprising obtaining a first template information and a second template information from a memory. 19. The identification method of claim 18, wherein the step D comprises generating the identification according to the difference between the first information and the first template information and the difference between the second information and the second template information result. 20. The identification method of claim 19, wherein step D further comprises using Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, normalized Euclidean distance, Mahalanobis distance and Hamming distance One of judging the difference between the first information and the first template information and judging the difference between the second information and the second template information. 21 . The identification method of claim 18 , wherein the step D comprises performing an identification step using a classifier to determine the combination of the first information and the second information and the first template information and the first information. 22 . The similarity between the combination of the two template information to produce the recognition result. 22. The identification method of claim 21, further comprising implementing the classifier with a support vector machine or a neural network-like network. 23. The identification method of claim 21, wherein the step D further comprises: determining whether the first information is similar to the first template information; and If so, perform this identification step. 24. The identification method of claim 21 , wherein the step D further comprises: determining whether the second information is similar to the second template information; and If so, perform this identification step. 25. The identification method according to claim 23 or 24, wherein the step D further comprises using Euclidean distance, Manhattan distance, Chebyshev distance, Minkowski distance, standardized Euclidean distance, Mahalanobis distance and Hanoi distance. One of the clear distances is used to determine whether the first information is similar to the first template information or to determine whether the second information is similar to the second template information. 26. The identification method of claim 15, wherein step B comprises using accelerated segment test features, adaptive general accelerated segmentation detection, scale-invariant feature transformation, accelerated robust features, KAZE, AKAZE, local binary mode, local phase quantization or directional gradient histogram algorithm to obtain this first information. 27. The identification method of claim 15, wherein step B comprises using a deep learning model to obtain the first information or the second information. 28. The identification method of claim 15, wherein step B comprises using a convolutional neural network to obtain the first information or the second information.

Images