WO2012138086A2

WO2012138086A2 - Apparatus and method for hierarchically verifying fingerprints using similarity distribution

Info

Publication number: WO2012138086A2
Application number: PCT/KR2012/002446
Authority: WO
Inventors: 채승훈; 반성범
Original assignee: 조선대학교산학협력단
Priority date: 2011-04-06
Filing date: 2012-04-02
Publication date: 2012-10-11
Also published as: KR20120113989A; KR101237148B1; WO2012138086A3

Abstract

Provided are an apparatus and method for hierarchically verifying a fingerprint using similarity distribution. The fingerprint verifying apparatus comprises: a database unit for storing registered fingerprint images; a fingerprint image input unit for receiving a user's fingerprint image from a user; a distinct feature based fingerprint matching unit for extracting distinct features from the user's fingerprint image received through the fingerprint image input unit and the registered fingerprint images stored in the database unit, so as to match fingerprints based on the extracted distinct features; a similarity determination unit for determining whether the similarity between the user's fingerprint image and the registered fingerprint images is within a preset range; a binary image based fingerprint matching unit for matching fingerprints based on binary images; and a verification unit for verifying a fingerprint based on the binary images if the determined result by the similarity determination unit shows that the similarity is within the present range, and verifying a fingerprint based on the distinct features if the determined result by the similarity determination unit is that the similarity is not within the preset range.

Description

Hierarchical Fingerprint Authentication Device Using Similarity Distribution and Its Method

The present invention relates to a hierarchical fingerprint authentication device and method using similarity distribution. More specifically, by using the fingerprint feature point and the binary image information of the fingerprint, two times of fingerprint comparison process enables more accurate authentication, and also determines the similarity for the user fingerprint image and based on the binary image only based on the determination result. The present invention relates to a fingerprint authentication device and a method for enabling real-time processing by performing authentication.

Recently, attempts have been made to incorporate biometrics into computer systems. The biggest feature of these biometrics is that there is no fear of loss, theft, forgetting, or duplication by external factors under any circumstances. The advantage is that it can be built completely.

In particular, the user authentication technology using a fingerprint has been actively commercialized in recent years, and the user authentication using such a fingerprint has a merit that it is easy to access and carry by authenticating a user by using a unique characteristic of a person. Various studies are underway and many developments are being made.

In the case of authentication technology using a fingerprint, a user's fingerprint is typically registered in a security token such as a smart card or a USB token, and the user is authenticated by comparing the fingerprint with the fingerprint in the security token without leaking the registration fingerprint. If only the result is transmitted to the outside, it is more secure than a system that manages fingerprint data with a central database or a system that transmits registered fingerprint data to perform external fingerprint comparison from an external device. By blocking the can ensure the stability of the biological data that can cause a big problem in the outflow.

In general, fingerprint authentication methods are classified into image-based fingerprint authentication methods and feature-based fingerprint authentication methods. Feature-based fingerprint authentication is a universal method that consists of two processes: minutiae extraction and matching. Various image processing techniques such as smoothing, separation of foreground and background areas, binarization, and thinning Apply the spatial features of the extracted feature points. That is, the feature-based fingerprint authentication method is a method of comparing an authentication fingerprint and a registration fingerprint by using a feature point, and a method of checking similarity between two feature points is mainly used.

The image-based fingerprint authentication method uses ridge information. The overall directionality of the fingerprint image is applied by applying techniques such as Gaber filter, Fast Fourier Transform (FFT), slope, directional histogram, and projection. It is one of the classic ways of using information. In a typical ridge-based fingerprint authentication method, the entire fingerprint area is divided into small areas, the direction value of the ridges existing in the small areas is extracted to complete the directional map of the fingerprint, and the two directional maps are convolved to determine the degree of similarity. .

On the other hand, the fingerprint authentication method based on binary image is a method using a fingerprint image image expressed in two types of black and white. In general, image processing data can be classified into color, gray, and binary. Color data uses color separation and contrast, gray data uses contrast without color separation, and binary data uses gray image. The data is handled in two ways, black and white, using a threshold.

However, in the feature-based fingerprint authentication method, due to the miniaturization of the fingerprint reader, only a part of the fingerprint image is acquired, and the overlapping area of the enrolled fingerprint and the authentication fingerprint is reduced. In addition, due to the missing feature points, false rejection of the fingerprint can occur, as well as the distribution of feature points extracted from two different fingerprints may be similar due to the missing and incorrectly extracted feature points. Since this may occur, there is a problem that there is a limit in recognition performance such as FAR.

In addition, the binary image-based fingerprint authentication method requires a lot of storage space for storing the image because the entire fingerprint image is used, and there is a problem that the performance of the fingerprint authentication process is slow.

The present invention was devised to solve the above problems, and by using two fingerprint comparison processes using fingerprint feature points and binary image information of a fingerprint, more accurate authentication is possible, and similarity with respect to a user fingerprint image is also provided. It is an object of the present invention to provide a fingerprint authentication device and a method for performing real-time processing by performing a binary image based authentication only according to the determination result.

According to an aspect of the present invention, there is provided a fingerprint authentication device comprising: a database unit for storing a registered fingerprint image; A fingerprint image input unit configured to receive a user fingerprint image from a user; A feature point based fingerprint matching unit extracting a feature point from the user fingerprint image inputted through the fingerprint image input unit and the registered fingerprint image stored in the database unit, and performing a feature point based fingerprint matching based on the extracted feature point; A similarity determination unit that determines whether or not the similarity between the user fingerprint image and the registered fingerprint image exists within a set range; Binary image based fingerprint matching unit performing binary image based fingerprint matching; And performing a binary image-based fingerprint authentication when the similarity is within the set range in the result of the similarity determining unit, and performing a feature-based fingerprint authentication when the similarity is out of the set range in the result of the similarity determining unit. It is characterized by.

The above-described fingerprint authentication device further comprises a feature point correcting unit for correcting a difference in at least one of a position, a direction, a distance, and an angle for each ridge information of a range of similarity of feature points extracted from the user fingerprint image and the registered fingerprint image. It may include.

The binary image-based fingerprint matching unit may perform fingerprint matching based on a binary image by using a fingerprint binary image generated when the feature point is extracted and a correction value of the feature point corrector.

According to an aspect of the present invention, there is provided a fingerprint authentication method comprising: receiving a user fingerprint image from a user; Extracting a feature point from the input user fingerprint image and a registered fingerprint image stored in a database, and performing feature-point based fingerprint matching based on the extracted feature point; Determining whether a similarity between the user fingerprint image and the registered fingerprint image is within a set range; If it is determined that the similarity is within the set range by the similarity determination step, performing the fingerprint matching based on the binary image using the fingerprint binary image generated when the feature point extraction and the correction value of the feature point correction unit; It features.

The fingerprint authentication method may further include performing feature-point based fingerprint authentication when the similarity is determined to be out of the set range by the similarity determining step.

The fingerprint authentication method may further include correcting a difference of at least one of a position, a direction, a distance, and an angle with respect to each ridge information of a range of similarity of feature points extracted from the user fingerprint image and the registered fingerprint image. can do.

According to the present invention, by using two fingerprint comparison processes using fingerprint feature points and binary image information of the fingerprint, more accurate authentication is possible, and in the fingerprint authentication process, a similarity distribution that does not always undergo binary fingerprint image matching process is used. Fingerprint authentication is performed by hierarchical fingerprint authentication.

1 is a view schematically showing a fingerprint authentication device according to an embodiment of the present invention.

2 is a diagram illustrating an example of a fingerprint image, where (a) shows an image of a registered fingerprint and (b) shows an image of an authentication fingerprint.

3 is a diagram showing an example by bin accumulation as an example of feature point correction.

4 is a diagram illustrating a fingerprint authentication similarity distribution form based on general feature points.

5 is a diagram illustrating an example of a binarized fingerprint image.

6 is a flowchart illustrating a fingerprint authentication method using the fingerprint authentication device of FIG. 1.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description, the detailed description can be omitted for techniques well known to those skilled in the art.

In addition, in describing the components of the present invention, different reference numerals may be given to components having the same name according to the drawings, and the same reference numerals may be given even though they are different drawings. However, even in such a case, it does not mean that the corresponding components have different functions according to the embodiments, or does not mean that they have the same functions in different embodiments, and the functions of the respective components may be implemented. Judgment should be made based on the description of each component in the example.

In addition, in describing the embodiments of the present invention, when it is determined that the detailed description of the related well-known configuration or function may obscure the gist of the present invention, the detailed description may be omitted.

1 is a view schematically showing a fingerprint authentication device according to an embodiment of the present invention. Referring to the drawings, the fingerprint authentication apparatus 100 includes a database unit 110, a fingerprint image input unit 120, a feature point based fingerprint matching unit 140, a similarity determination unit 150, and a binary image based fingerprint matching unit 160. And an authentication performing unit 150. Preferably, the fingerprint authentication device 100 may further include a feature point corrector 130.

The database unit 110 stores the registered fingerprint image. At this time, the database unit 110 may store the feature point information analyzed for the registered fingerprint image. One fingerprint curve representing a fingerprint is called a ridge, which is a continuous ridge, an end that breaks in the middle, and a bifurcation where two or more ridges meet, which are called minutiae. do. Since the feature points vary from person to person, the database unit 110 obtains a registered fingerprint image from a registered subscriber, analyzes the location and number of feature points, and stores the database.

The fingerprint image input unit 120 receives a user fingerprint image from a user for authentication.

The feature point-based fingerprint matching unit 130 extracts feature points from a fingerprint image of a user for authentication input through the fingerprint image input unit 120 and a registered fingerprint image stored in the database unit 110, and based on the extracted feature points Based fingerprint matching.

In general, fingerprint feature information used in a fingerprint recognition system, as shown in Figure 2a, a bifurcation point 220 is divided into an end point (210) through which the ridge passes in the fingerprint image and one ridge is surrounded. Use One feature point extracted from the fingerprint image may have a coordinate of the feature point and type information of the feature point and may be represented by (x, y, θ, type). On the other hand, even if the fingerprint of the same person, as shown in Fig. 2b each time the fingerprint is input to the fingerprint input device, the coordinate value of the feature point is translated and the direction is rotated. For the same person, FIG. 2A is a fingerprint image input when registering and FIG. 2B is a fingerprint image input when authenticating. The end point 210 of FIG. 2A and the end point 230 of FIG. 2B are the same feature point pairs, and similarly, the branch point 220 of FIG. 2A and the branch point 240 of FIG. 2B are the same feature point pairs. In this way, all the feature points extracted from the two fingerprints can be identified based on the difference in position and direction, and all pairs of feature points determined to be similar can be found, or scores can be obtained based on the similarity to determine whether the threshold is greater than or equal to the threshold. This is a method of comparing absolute phases assuming that fingerprints are input in the same position and the same direction to be input, and it is necessary to correct the two fingerprints to have the same criteria before checking the similarity of the position and the direction. That is, as shown in FIGS. 2A and 2B, even when the pair of feature points is the same, the direction of the absolute coordinates is different depending on the input time point, so that an alignment process of moving and rotating the two fingerprints by a changed amount is necessary. To this end, the feature point corrector 135 may be configured to display the position, direction, distance, and angle of each feature point extracted from the registered fingerprint image stored in the database unit 110 and the fingerprint image of the user input through the fingerprint image input unit 120. Correct the difference for at least one.

The feature point-based fingerprint matching unit 140 extracts feature point information for authentication from the user fingerprint image input through the fingerprint image input unit 120, and then stores the feature point information on the registered fingerprint image pre-stored and registered in the database 110. Read and load the data into a memory to compare and analyze the registered feature point information with the feature point information of the user fingerprint image. In this case, the feature point corrector 130 extracts a difference of at least one of a position, a direction, a distance, and an angle between the feature point information of the registered fingerprint loaded in the memory and the feature point information of the authentication fingerprint to correct the feature point. And as shown in Figure 3b, it is possible to set the area for accumulating the difference in the position, direction, distance between the two feature points and determine the position (bx1, by1) and the direction unit of each bin (bin). Here, the unit of the initial bin with respect to the position and the direction may be set to be large and then reduced to the minimum unit while changing sequentially. In FIGS. 3A and 3B, Range_X1 is associated with a detectable positional movement in the X direction to the first area of the X axis, Range_X2 is set to the area around the maximum bin at the first stage as the second area of the X axis, and Range_Y1 Is associated with the detectable positional movement in the Y direction to the first region of the Y axis, and Range_Y2 is the second region of the Y axis, set as the region around the maximum bin at the first stage. In addition, bx1 is the first unit of the X-axis, bx2 is the second unit of the X-axis, smaller than bx1, by1 is the first unit of the Y-axis, and by2 is the second unit of the Y-axis, which is smaller than by1. ΔX is the amount of change in the X-axis of the pair of feature points, ΔY is the amount of change in the Y-axis of the pair of feature points, and B means a bin having a maximum value. In addition, a bin means an area of each feature point expressed in binary.

In addition, it is determined whether all of the feature points between the feature point information of the user fingerprint image and the feature point information of the loaded registered fingerprint image are considered, and if not all feature points are generated, a pair of authentication fingerprint feature points and registered fingerprint feature points are generated. The direction difference between the feature points can be measured. In this case, by checking whether the direction difference between the two feature points is out of the allowable range, if the deviation is not out of the allowable range, the position difference and the distance difference between the two feature points may be measured. Similarly, if the position difference and distance difference between the two feature points do not deviate from the allowable range, the level of the specific bin of the set area corresponding to the obtained position, direction and distance difference is raised or accumulated, and all the feature points, ie, the direction, After considering the feature point pairs of the position and distance difference, the bin having the maximum level is obtained, and whether the unit for the position, direction, and distance of the bin is the minimum unit is determined. If the unit is the minimum unit, the difference in the position, direction, and distance corresponding to the maximum bin value, that is, the position, direction, and distance difference corresponding to B shown in FIG. 3B may be extracted. At this time, the feature point corrector corrects the feature points of the authentication fingerprint and the enrolled fingerprint based on the detected position, direction, and distance difference, and then measures the similarity between the two corrected feature points, if the measured similarity is greater than the preset threshold. It is determined that this is the same, and the authentication process of the user is performed according to the determined result.

On the other hand, the similarity distribution of the feature-based fingerprint authentication generally has a form as shown in FIG. When fingerprint authentication is performed using a threshold in the similarity distribution as shown in FIG. 4, a false match, that is, a mistake of another person's fingerprint as a registered user's fingerprint and a false rejection error (False Non) Match In other words, the user's fingerprint is misidentified as the fingerprint of another person. At this time, point a is called Zero False Non-Match Rate (ZeroFNMR) and point b is called Zero False Match Rate (ZeroFMR). When the similarity is lower than ZeroFNMR and higher than ZeroFMR, no error occurs. In addition, if the similarity is increased around the threshold, the other person's acceptance error is reduced, and if the similarity is low, the self rejection error is reduced, and the other person's acceptance error and the person's rejection error are most frequently generated around the threshold. However, if the registration fingerprint and the user fingerprint is matched based on the feature point, when the similarity is between a point and b point, an error of rejecting authentication or misidentifying another person as a person occurs by misidentifying the person as another person.

In order to improve such a problem, the fingerprint authentication apparatus 100 according to the present invention uses a similarity determination unit 150 and a binary image-based fingerprint matching unit 160 to a fingerprint image based on a feature point and a fingerprint image based on a binary image. The authentication can be performed twice. In addition, the similarity determination unit 150 may determine whether the similarity between the feature point of the user fingerprint image and the feature point of the registered fingerprint image is within a set range. If the similarity determined by the similarity determining unit 150 is not included in the set similarity range, the fingerprint authentication may be performed on the input user fingerprint image based on the fingerprint matching by the feature-based fingerprint matching unit 140. have. In addition, if the similarity determined by the similarity determination unit 150 is included in the set similarity range, the fingerprint matching based on the binary image is performed by using the fingerprint binary image generated when the feature point is extracted and the correction value by the feature point corrector 130. You can do that.

The binary image-based fingerprint matching unit 160 may perform binary image-based fingerprint matching using the fingerprint binary image generated when the feature point is extracted and the correction value of the feature point corrector 130. The range between point a and point b for performing binary image-based fingerprint matching can be set to 10%, 20%, 30%, ... using a similarity distribution based on a threshold value. As a result of experiment with FVC2002 DB1A published by fingerprint recognition experiment, the performance of fingerprint authentication is most improved when the similarity distribution ratio is 40% based on the threshold value.

5 illustrates an example of a fingerprint image input as a gray image and a binary image of a fingerprint.

Referring to FIG. 5, a general gray image has a contrast level of 256 levels. As the fingerprint has a different intensity of contrast of the ridge according to the pressure of the finger, a fingerprint image having a different intensity value is input every time the fingerprint is input. However, the binarized fingerprint image is composed of consistent ridges and bones. Therefore, when comparing two fingerprints, a fingerprint of a binary image can be clearly and simply compared to a fingerprint of a gray image. In addition, binary images have higher compression ratios than gray images because the distribution of contrast values is simple. Therefore, it has the advantage of effectively storing fingerprint images.

After matching the feature points of the user fingerprint image and the registered fingerprint image on the basis of the feature points, if the similarity is within the range set by the similarity determining unit 150, the fingerprint matching is performed using the binary image generated during the feature point extraction process.

The authentication performing unit 170 determines that the similarity between the user fingerprint image and the registered fingerprint image is out of the range set by the similarity determining unit 150 by the feature-based fingerprint matching unit 140. If smaller than the point or larger than the point b, authentication of the user's fingerprint is performed based on the feature point. In this case, as described above, no error occurs in performing authentication.

In this case, the binary image-based fingerprint matching unit 160 is the fingerprint binary image and the feature point correction unit generated when the feature point extraction when the similarity between the user fingerprint image and the registered fingerprint image is set by the feature-based fingerprint matching unit 140. The binary image-based fingerprint matching 160 is performed using the correction value of 130.

6 is a flowchart illustrating a fingerprint authentication method using the fingerprint authentication device of FIG. 1. Referring to the figure, the fingerprint image input unit 120 receives a user fingerprint for authentication from the user (S602).

The feature point-based fingerprint matching unit 140 extracts a feature point from a user fingerprint image input through the fingerprint image input unit 120 and a registered fingerprint image stored in the database unit 110 (S604), and the feature point corrector 130 extracts the feature point. Based on the respective feature points, the two fingerprints are corrected (S606). In this case, the feature point corrector 130 corrects a difference of at least one of a position, a direction, a distance, and an angle for each feature point extracted from the user fingerprint image and the registered fingerprint image. The feature point-based fingerprint matching unit 140 performs fingerprint matching on the user fingerprint image and the registered fingerprint image based on the feature points corrected by the feature point corrector 130 (S608).

The similarity determination unit 150 determines whether the similarity between the feature point of the user fingerprint image and the feature point of the registered fingerprint image is within a set range (S610). If the similarity is not included in the similarity range set by the similarity determining unit 150, the authentication performing unit 170 is input through the fingerprint image input unit 120 based on the similarity extracted by the feature-based fingerprint matching 140. Fingerprint authentication is performed on the user fingerprint image (S612). In addition, when it is determined by the feature point-based fingerprint matching unit 140 that the similarity between the feature point of the user fingerprint image and the feature point of the registered fingerprint image is within the set range, the fingerprint binary image and the feature point corrector 130 generated when the feature point is extracted The binary image-based fingerprint matching 160 is performed using the correction value. The fingerprint authentication is performed on the user fingerprint image input through the fingerprint image input unit 120 based on the similarity of the binary image-based fingerprint matching (S614).

As described above, the feature-based similarity is determined with respect to the user fingerprint image and the registered fingerprint image for authentication, and if the feature-based similarity is out of the set range, the feature-based fingerprint authentication is performed, and the feature-based similarity is determined. If it is within the set range by performing the fingerprint authentication based on the binary image, it is possible to significantly reduce the occurrence of errors during fingerprint authentication.

In addition, since the present invention performs binary image-based fingerprint authentication only when the similarity based on the feature point is within the set range, it is not necessary to compare binary images for all input user fingerprint images, thereby real-time processing of fingerprint authentication is required. It becomes possible.

In the above description, all elements constituting the embodiments of the present invention are described as being combined or operating in combination, but the present invention is not necessarily limited to these embodiments. In other words, within the scope of the present invention, all of the components may be selectively operated in combination with one or more. In addition, although all of the components may be implemented as one independent hardware, each or some of the components of the program modules are selectively combined to perform some or all of the functions combined in one or a plurality of hardware It may be implemented as a computer program having a. In addition, such a computer program may be stored in a computer readable medium such as a USB memory, a CD disk, a flash memory, and the like, and read and executed by a computer, thereby implementing embodiments of the present invention. The storage medium of the computer program may include a magnetic recording medium, an optical recording medium, a carrier wave medium, and the like.

In addition, all terms including technical or scientific terms have the same meaning as commonly understood by a person of ordinary skill in the art unless otherwise defined in the detailed description. Terms used generally, such as terms defined in a dictionary, should be interpreted to coincide with the contextual meaning of the related art, and shall not be interpreted in an ideal or excessively formal sense unless explicitly defined in the present invention.

The above description is merely illustrative of the technical idea of the present invention, and those skilled in the art to which the present invention pertains may make various modifications and changes without departing from the essential characteristics of the present invention. In addition, the embodiments disclosed in the present invention are not intended to limit the technical spirit of the present invention but to explain, and the scope of the technical spirit of the present invention is not limited by these embodiments. Therefore, the protection scope of the present invention should be interpreted by the claims, and all technical ideas within the scope equivalent thereto should be construed as being included in the scope of the present invention.

Claims

In the fingerprint authentication device,

A database unit for storing a registered fingerprint image;

A fingerprint image input unit configured to receive a user fingerprint image from a user;

A feature point based fingerprint matching unit extracting a feature point from the user fingerprint image inputted through the fingerprint image input unit and the registered fingerprint image stored in the database unit, and performing a feature point based fingerprint matching based on the extracted feature point;

A similarity determination unit that determines whether or not the similarity between the user fingerprint image and the registered fingerprint image exists within a set range;

Binary image based fingerprint matching unit performing binary image based fingerprint matching; And

And performing a binary image-based fingerprint authentication when the similarity is within the set range in the result of the similarity determining unit, and performing a feature-based fingerprint authentication when the similarity is out of the set range in the result of the similarity determining unit. Fingerprint authentication device characterized in that.
The method of claim 1,

A feature point corrector for correcting a difference in at least one of a position, a direction, a distance, and an angle for each ridge information of a range of similarities between feature points extracted from the user fingerprint image and the registered fingerprint image.

Fingerprint authentication device further comprising.
The method of claim 2,

The binary image-based fingerprint matching unit,

And fingerprint matching based on a binary image using a fingerprint binary image generated when the feature point is extracted and a correction value of the feature point corrector.
In the fingerprint authentication method,

Receiving a user fingerprint image from a user;

Extracting a feature point from the input user fingerprint image and a registered fingerprint image stored in a database, and performing feature-point based fingerprint matching based on the extracted feature point;

Determining whether a similarity between the user fingerprint image and the registered fingerprint image is within a set range;

If it is determined that the similarity is within the set range by the similarity determination step, performing a fingerprint matching based on the binary image using the fingerprint binary image generated when the feature point extraction and the correction value of the feature point correction unit

Fingerprint authentication method comprising a.
The method of claim 4, wherein

Performing a feature-based fingerprint authentication when the similarity is determined to be out of the set range by the similarity determining step.

Fingerprint authentication method further comprising.
The method of claim 4, wherein

Correcting a difference of at least one of a position, a direction, a distance, and an angle for each ridge information of a range of similarity of feature points extracted from the user fingerprint image and the registered fingerprint image;

Fingerprint authentication method further comprising.