JP2899119B2 - Fingerprint collation device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a fingerprint collating apparatus for performing pattern matching between a registered fingerprint dictionary and an input fingerprint to confirm the identity of the user.

In recent years, with the introduction of computers into a wide range of social systems, stakeholders have been interested in system security. Many questions have been raised from the aspect of security assurance regarding ID cards and passwords that have been used as means for entering a computer room or confirming the identity of a terminal when using a terminal. On the other hand, fingerprints are considered to be the most powerful means of personal identification because they have two major characteristics, that is, everyone's identity and lifelong invariance, and much research and development has been conducted on a simple personal identification system using fingerprints. I have.

[0003]

2. Description of the Related Art In a conventional fingerprint matching apparatus, the features of fingerprints are registered in advance as a dictionary, and at the time of matching, an input image is compared with feature dictionary information to confirm the identity. FIG. 8 is a conceptual diagram showing the configuration of a conventional fingerprint matching device. First, the operation at the time of registration will be described. A finger is pressed against the fingerprint sensor 1 to detect a fingerprint pattern, and is converted into digital data by an A / D converter (not shown) in the fingerprint sensor 1. Converted digital data (fingerprint data)
Is converted into binary data “0” and “1” by the following binarization circuit 2 and stored in the frame memory 3. After the fingerprint data stored in the frame memory 3 is sequentially read out, the fingerprint data enters the feature information extraction / collation circuit 4 where the feature information is extracted.

Here, the characteristic information is, for example, as shown in FIG.
And end points as shown in (b). A fingerprint can be specified based on where and how many such branch points and end points exist. The extracted feature information is
It is stored in the personal characteristic information data file 5. The above operation is repeated for a plurality of individuals, and individual characteristic information is stored in the individual characteristic information data file 5.

[0005] When the registration of the characteristic information amount in the personal characteristic information data file 5 is completed, the operation for collating the fingerprint of the individual is started. In the case of collation, a finger (a finger previously used for registration, for example, an index finger) is put on the fingerprint sensor 1, and then the user enters his / her ID number using a numeric keypad (not shown). As a result, the characteristic information extraction / collation circuit 4 determines the search range of the personal characteristic information data file 5 based on the ID number and reads it out at the time of collation, thereby narrowing the search range.

A fingerprint pattern is detected in the same manner as at the time of registration, and is converted into digital data by an A / D converter (not shown) in the fingerprint sensor 1. The converted digital data is converted into binary data “0” and “1” by the following binarization circuit 2 and stored in the frame memory 3.

[0007] The characteristic information extraction / collation circuit 4 reads the fingerprint data for collation stored in the frame memory 3, reads out the characteristic information for each individual stored in the personal characteristic information data file 5, and compares both the fingerprint data ( Pattern matching)
I do. When the number of matches of the feature information is equal to or greater than a predetermined number, it is determined that the fingerprints match.

[0008]

However, when personal identification information based on fingerprints is introduced into important facilities such as intelligent buildings and nuclear facilities, hundreds to thousands of fingers must be registered at one time. In a nuclear power plant, tens of thousands of workers may be engaged in periodic inspections. At the very end, if each individual finger is put on the fingerprint sensor of the fingerprint matching device to perform the registration process, the process of registering tens of thousands of fingers takes too much time. Also,
If the collation rate is to be further improved, the registration process becomes complicated, and it takes more time.

SUMMARY OF THE INVENTION The present invention has been made in view of the above problems, and has as its object to provide a fingerprint matching device capable of efficiently performing fingerprint registration.

[0010]

FIG. 1 is a block diagram showing the principle of the present invention. 8 are denoted by the same reference numerals. In the figure, 1 is a fingerprint sensor for reading a fingerprint image, 10 is a fingerprint image recording unit for converting the output of the fingerprint sensor 1 into a binary image and recording it, and 11 is a fingerprint image recording unit 10
Information recording medium for recording a fingerprint image output from
Is a batch processing unit which brings in the information recording medium 11 and batch-inputs the recorded information as a pair of a personal identification name and fingerprint image information. A batch processing unit 20 inputs the fingerprint image information output from the batch processing unit 12. A fingerprint image collation processing unit that collectively registers feature patterns of a plurality of individuals as a fingerprint dictionary and performs collation between an input fingerprint image and a fingerprint dictionary.

[0011]

According to the present invention, a fingerprint sensor 1 and a fingerprint image recording unit 10 are provided in each workplace, and a binary fingerprint image of a plurality of individuals read by the fingerprint sensor 1 is stored in an information recording medium 11 such as a floppy disk. To record. Then, the information recording medium 11 is brought from each workplace to the fingerprint image matching processing unit 20 installed at the center, and is read by the batch processing unit 12.

With such a configuration, there is no need for thousands of people to form a matrix and register a finger in front of the fingerprint matching device, and a fingerprint matching device capable of performing fingerprint registration efficiently can be provided. Can be provided.

[0013]

Embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 2 is a block diagram showing the configuration of an embodiment of the present invention. 1 are denoted by the same reference numerals. The fingerprint image matching processing unit 20 includes a fingerprint image capturing unit 21 for capturing a fingerprint image, a memory 22 for sequentially storing the output of the fingerprint image capturing unit 21, a fingerprint dictionary storage unit 23 for registering a characteristic pattern as a fingerprint dictionary. And extracting feature information from the fingerprint image read from the memory 22 and comparing the fingerprint images or comparing the feature pattern of the fingerprint image read from the memory 22 with the fingerprint dictionary read from the fingerprint dictionary storage unit 23. / Matching unit 24 and a dictionary evaluation unit 25 that evaluates a dictionary according to the matching result of the feature information extraction / matching unit 24 and registers an optimal fingerprint dictionary in the fingerprint dictionary storage unit 23. . The operation of the device configured as described above will be described below.

The fingerprint sensor 1 reads fingerprint images of a plurality of individuals. The read fingerprint image information is stored in the fingerprint image recording unit 1.
Enter 0. The fingerprint image recording unit 10 converts the output of the fingerprint sensor 1 into digital data by A / D conversion, and further performs a binarization process to convert the output into binary image data. The binarized image data thus generated is stored by the fingerprint image recording unit 10 on a floppy disk 11 as an information recording medium.

When the reading of one fingerprint image is completed, the fingerprint image of the next individual is read and stored in the floppy disk 11. At this time, the personal identification information and the fingerprint image data are stored correspondingly. In this manner, the floppy disk 11 stores, for example, several hundred pieces of personal fingerprint image data in one workplace unit.

The floppy disk 11 is brought to the place where the fingerprint image collation processing unit (main unit) is located. The carry-in method may be mailed or brought by a person.

The contents of the floppy disk 11 are applied to a batch processing section 12. The batch processing unit 12 batch-inputs the record information as a pair of the personal identification name and the fingerprint image information. The inputted fingerprint image data is taken into the apparatus main body 20 from the fingerprint image taking section 21. The captured fingerprint image data is temporarily stored in the memory 22.

The feature information extraction / collation unit 24 includes a memory 22
The feature information for each individual stored in the fingerprint image is extracted, and the fingerprint images are compared and compared. The dictionary evaluation unit 25 evaluates the dictionary according to the matching result of the feature information extraction / matching unit 24, and registers an optimal fingerprint dictionary in the fingerprint dictionary storage unit 23.

When the dictionary registration is completed, the feature information extracting / collating section 24 reads the image read from a fingerprint sensor (not shown) provided in the apparatus body and the fingerprint dictionary storage section 23.
Of the personal dictionary stored in the personal dictionary to identify the person.

According to the present invention, at the time of registration of the fingerprint dictionary, the fingerprint image data read for each workplace is read by the main unit of the center in batches. Therefore,
Thousands of people do not need to form a matrix in order to register a finger in front of the fingerprint collation device, and a fingerprint collation device capable of efficiently performing fingerprint registration can be provided.

Next, the details of dictionary registration will be described.
FIG. 3 is a flowchart showing an example of the operation of the present invention. First, a plurality of fingerprint images of the same finger of the same person are collected from the fingerprint sensor 1 (S1). The collected fingerprint image is
The fingerprint image is stored on the floppy disk 11 from the fingerprint image recording unit 10. Next, a fingerprint image is transferred (S2). Specifically, it indicates that the floppy disk 11 is to be brought to the apparatus main body side. However, the transfer method is not limited to this, and a memory for storing fingerprint image data is provided in the fingerprint image recording unit 10, and the contents of this memory are transferred to the apparatus main body using a line or the like. Is also good.

On the side of the apparatus main body (fingerprint image collating unit) 20, a fingerprint dictionary is created from a plurality of captured fingerprint images (S3). Specifically, one of a plurality of captured fingerprint images is selected, and a feature point (feature pattern) therein is selected.
Is extracted as a dictionary.

FIG. 4 is an explanatory diagram of feature point extraction. The spiral pattern M in the figure is a fingerprint. The feature point is this fingerprint M
Appears on the line. The □ in the figure is the feature point. A plurality of feature points are picked up from the center feature point along the periphery thereof, and are used as a fingerprint dictionary. This fingerprint dictionary is stored in the feature information extraction / collation unit 24 for the time being.

After the fingerprint dictionary is created, collation evaluation is performed on the remaining fingerprint images (S4). FIG. 5 is an explanatory diagram of the collation evaluation. It is assumed that five fingerprint images from G1 to G5 are captured. Then, a fingerprint dictionary D is created from G2 of these. When the fingerprint dictionary D is created, pattern matching is performed between the fingerprint dictionary D and the remaining fingerprint images G1, G3 to G5. In this pattern matching, a window having the same size as the feature point of □ shown in FIG. 4 is created, and this window is scanned along a fingerprint image to check whether there is a matching pattern.

Then, as a result of the collation evaluation, the dictionary evaluation unit 25
If a matching rate equal to or greater than the threshold value is obtained in response to the matching result, the temporarily determined dictionary is stored in the fingerprint dictionary storage unit 23. As a result, the temporarily determined dictionary is registered as an official dictionary.

FIG. 6 is a flowchart showing an example of another operation of the present invention. First, a plurality of fingerprint images of the same finger of the same person are collected from the fingerprint sensor 1 (S1). The collected fingerprint image is stored on the floppy disk 11 from the fingerprint image recording unit 10. Next, a fingerprint image is transferred (S2). Specifically, it indicates that the floppy disk 11 is to be brought to the apparatus main body side. However, the transfer method is not limited to this, and a memory for storing fingerprint image data is provided in the fingerprint image recording unit 10, and the contents of this memory are transferred to the apparatus main body using a line or the like. Is also good.

The apparatus body (fingerprint image collation processing unit) 20 creates a plurality of temporary fingerprint dictionaries from the plurality of captured fingerprint images (S3). More specifically, a plurality of fingerprint images are selected from a plurality of captured fingerprint images, and feature points (feature patterns) therein are extracted to be a plurality of dictionaries.

FIG. 4 shows a feature point extracting method for each fingerprint image. These fingerprint dictionaries are stored in the feature information extraction / collation unit 24 for the time being.

After the fingerprint dictionary has been created, collation evaluation is performed on the remaining fingerprint images (S4). FIG. 7 is an explanatory diagram of the collation evaluation of a plurality of dictionaries. The captured fingerprint images are G
It is assumed that there are five from 1 to G5. Then, fingerprint dictionaries D1 to D5 are created for each of these fingerprint images. After the fingerprint dictionaries D1 to D5 are created, first, pattern matching is performed between the fingerprint dictionary D1 and the remaining fingerprint images G2 to G5.

When the collation for the fingerprint dictionary D1 is completed, the collation operation for the fingerprint dictionary D2 is performed. Hereinafter, a similar collation operation is performed for the remaining fingerprint dictionaries D3 to D5. When the collation operation for all fingerprint dictionaries is completed, the dictionary evaluation unit 25 receives the collation results, and selects a dictionary having a collation rate equal to or higher than a threshold among a plurality of dictionaries and having the best collation rate as a dictionary. (S5). Next, the selected dictionary is registered in the fingerprint dictionary storage unit 23 as a formal fingerprint dictionary (S6). In FIG. 7, the case where the fingerprint dictionary is created from all of the plurality of fingerprint images has been described.
A fingerprint dictionary may be created from a part.

Then, as a result of the collation evaluation, the dictionary evaluation unit 25
If a matching rate equal to or greater than the threshold value is obtained in response to the matching result, the temporarily determined dictionary is stored in the fingerprint dictionary storage unit 23. As a result, the temporarily determined dictionary is registered as an official dictionary.

Hereinafter, modified examples of the present invention will be described. In the embodiment of FIG. 2, a function for recording an attribute other than the fingerprint image is added to the fingerprint image recording unit 10, and the attribute is also recorded on the floppy disk 11 and can be transferred to the apparatus main body side. When a fingerprint image is recorded in the fingerprint image recording unit 10, the quality of the recorded image is determined, and if it is determined that the finger is inappropriate for verification, the use of another finger may be requested. it can. The fingerprint image recording unit 10 is provided with an identity verification function, so that only qualified persons can operate the apparatus. When transferring the fingerprint image to the apparatus main body, identification of the user can be required. When the fingerprint image is transferred to the apparatus main body, the fingerprint image data can be encrypted and stored in the floppy disk 11. This has the effect of preventing misuse when the fingerprint image is stolen when it is brought into the apparatus main body. When transferring the fingerprint image to the apparatus main body, the fingerprint image can be compressed and encoded and stored in the floppy disk 11. This is the floppy disk 11
This has the effect of efficiently storing data into

[0034]

As described above in detail, according to the present invention, a fingerprint image is fetched into an information recording medium for each workplace, and the fetched information recording medium is transferred to a place where the main unit is installed. The apparatus main body performs batch processing for reading fingerprint image information from an information recording medium by bringing it in or transferring it by some means. This eliminates the need for thousands of people to form a matrix for fingerprint dictionary registration and register a finger before the fingerprint verification device, and provides a fingerprint verification device that can perform fingerprint registration efficiently. Can be.

[Brief description of the drawings]

FIG. 1 is a principle block diagram of the present invention.

FIG. 2 is a configuration block diagram showing one embodiment of the present invention.

FIG. 3 is a flowchart showing an example of the operation of the present invention.

FIG. 4 is an explanatory diagram of feature point extraction.

FIG. 5 is an explanatory diagram of collation evaluation.

FIG. 6 is a flowchart showing another operation of the present invention.

FIG. 7 is an explanatory diagram of dictionary collation evaluation.

FIG. 8 is a conceptual diagram illustrating a configuration of a conventional fingerprint matching device.

FIG. 9 is a diagram showing an example of fingerprint feature information.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 Fingerprint sensor 10 Fingerprint image recording part 11 Information recording medium 12 Batch processing part 20 Fingerprint image collation processing part

Claims (2)

(57) [Claims] And 1. A fingerprint image reading free fingerprint sensor and a fingerprint image recording unit for recording by converting the output of the fingerprint sensor into a binary image, the fingerprint image outputted fingerprint image recording unit or al an information recording medium body for recording, bring the information recording medium body, and a batch processing unit for batchwise enter that information recorded as pairs of personal identification name and fingerprint image information, and output the batch processing unit or al enter the fingerprint image information, a plurality of individual characteristic patterns and registers collectively as fingerprint dictionary is composed of a fingerprint image collation processing unit for matching the input fingerprint image and the fingerprint dictionary, the fingerprint image processing A fingerprint image capturing unit for capturing a fingerprint image, a memory for sequentially storing an output of the fingerprint image capturing unit, and a fingerprint dictionary storage unit for registering a feature pattern as a fingerprint dictionary
Feature information from the fingerprint image read from the memory,
Comparison of fingerprint images or the characteristics of fingerprint images read from memory
Between the signature pattern and the fingerprint dictionary read from the fingerprint dictionary storage unit.
A feature information extraction / matching unit that performs matching, and a dictionary evaluation according to the matching result of the feature information extraction / matching unit
And register the optimal fingerprint dictionary in the fingerprint dictionary storage unit.
The fingerprint sensor reads a plurality of fingerprint images of the same finger of the same person.
And record it on an information storage medium.
The fingerprint image matching processing unit is brought in and read by the processing unit.
Select any one of the fingerprint images and create a fingerprint dictionary
Created and used in the dictionary by the feature information detection / collation unit.
Performs collation processing on the remaining fingerprint images outside and evaluates the dictionary
Part received the matching result and obtained a matching rate above the threshold
In that case, the temporarily determined dictionary is stored in the fingerprint dictionary
A fingerprint collation device characterized by being registered as a dictionary . 2. A fingerprint image matching processing unit creates a fingerprint dictionary for a part or all of a plurality of fingerprint images, and generates a fingerprint dictionary for the remaining fingerprint images other than those used for the dictionary by the feature information detection / matching unit. The collation processing is performed, and the dictionary evaluation unit receives the collation result, and obtains a collation rate equal to or more than a threshold value among a plurality of dictionaries, and registers the one having the best collation rate as a fingerprint dictionary in the fingerprint dictionary storage unit. The fingerprint matching device according to claim 1, wherein: