JPH05266171A - Fingerprint matching device - Google Patents

Abstract

PURPOSE:To provide the small-sized, inexpensive fingerprint matching device which can be incorporated in small-sized equipment or on a card, etc., and employs simple fingerprint matching algorithm and shortens the matching time. CONSTITUTION:An image center point detection part 2 detects the center point of a fingerprint image inputted from a fingerprint image input part 1. A radial scanning part 3 scans the image radially from the image center point and a matching pattern generation part 4 performs processes such as waveform border line detection, etc., to extract a matching pattern. A matching center point detection part 6 matches the matching pattern with registered patterns stored in a registered pattern storage part 5 to detect a matching center point. If the matching center point is not detected as the image center point during the matching, the center point of the radial scanning is shifted spirally to find a matching center point. A pattern matching and discrimination part 8 matches the matching pattern with the registered patterns to find the same fingerprint and outputs the matching result to a matching result output part 9.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention performs personal identification by means of fingerprint collation that utilizes the characteristics of fingerprints that remain the same throughout life and that everyone does not differ, as means for personal identification when specifying or limiting users of facilities and equipment. The present invention relates to a fingerprint collation device.

[0002]

2. Description of the Related Art Conventionally, this type of fingerprint collation device (as described in the Institute of Image Electronics Engineers, Vol. 15, No. 3, 1986, "Automatic Technology for Fingerprint Collation") is a minutiae or minutiae which is a characteristic point of fingerprints. Individual users are checked by the number of ridges between them.

Next, the fingerprint collation operation of the above conventional example will be described. FIG. 7 is a front view of the minutiae. In FIG. 7, reference numeral 80 denotes an end point indicating a break in a ridge in a fingerprint, and 81
Is a bifurcation point that is divided into two, and the ridge end point 80 and the bifurcation point 81 are called minutiae.

FIG. 8 is a schematic flowchart of a conventional fingerprint collation device for performing fingerprint collation using a minutia.
In FIG. 8, a fingerprint image is input at step 90.
The input fingerprint image is binarized and ridges are drawn (step 9).
1-92). After correcting the breakage of the drawn ridge and the disorder of the sweat glands, the ridge is thinned to determine the center of the fingerprint and the inclination of the axis (steps 93 to 95). The position of minutiae and the number of ridges between minutiae, which are the features of fingerprints, are drawn, and individuals are collated by these features (step 9).
6-97).

According to such a conventional method, individual identification is performed when the users of facilities and equipment are specified or limited.

[0006]

However, in the above-mentioned conventional method, the input condition of fingerprint information largely depends on the influence of noise such as image resolution, inclination, and blurring, and the fingerprint information is used as a collation algorithm. Pre-processing such as binarization and thinning is required, and minutiae and ridge feature points between minutiae must be drawn.
When the fingerprint collation device is incorporated into a small device or a card, there is a problem that the collation algorithm is complicated, it takes time to collate the fingerprint, the size is large, and the cost is high.

The present invention solves such a conventional problem, in which a radial scan is performed starting from the center of a fingerprint image, and a user is identified by using a matching pattern obtained by the radial scan. Therefore, there is little dependence of input conditions, preprocessing such as binarization and thinning of images as a matching algorithm, and depiction of minutiae and ridge number feature points between minutiae are unnecessary, and small devices and It is an object of the present invention to provide a small-sized, inexpensive fingerprint collation device that can be incorporated into a card or the like, has a simple collation algorithm, a short collation time, is small in size.

[0008]

In order to achieve the above object, the present invention provides a fingerprint image input section for inputting a fingerprint image,
An image center point detection unit that detects the center point of the fingerprint image input from the fingerprint image input unit, a radial scanning unit that radially scans the fingerprint image, and a result obtained by the radial scanning , A matching pattern generation unit that detects a boundary between ridges and valleys of a fingerprint and a center point to generate a matching pattern, and a registered pattern that is pre-registered for matching an input fingerprint image are stored. Match the registered pattern storage unit with this registered pattern and the matching pattern,
A matching center point detection unit that detects the center point of the matching pattern,
In order to detect this center point, a spiral scanning unit that changes the center point of the radial scan in a spiral manner, a pattern matching identifying unit that matches the registered pattern and a matching pattern, and matches the fingerprints, By providing a matching result output unit for outputting the matching result of the pattern matching identifying unit and the detection result of the above-mentioned matching center point detecting unit, there is little dependence of input conditions, and individual identification is possible by a simple matching algorithm. ..

[0009]

Therefore, according to the present invention, fingerprints that are less dependent on input conditions and can be incorporated into a small device or card by personal identification by a simple matching algorithm, have a short matching time, are small, and are inexpensive. A matching device can be enabled.

[0010]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The structure of an embodiment of the present invention will be described below with reference to the drawings.

FIG. 1 is a schematic block diagram of a fingerprint collation device according to the present invention. In FIG. 1, reference numeral 1 is a fingerprint image input unit for inputting a fingerprint image. Reference numeral 2 denotes an image center point detection unit that detects the center point of the fingerprint image input from the fingerprint image input unit 1. Reference numeral 3 denotes a radial scanning unit that performs radial scanning on the fingerprint image. A collation pattern generation unit 4 generates a collation pattern by detecting a boundary between ridges and valleys of a fingerprint or a center point of a result obtained by radial scanning. Reference numeral 5 denotes a registered pattern storage unit that stores a registered pattern that has been pre-registered for matching the input fingerprint image. Reference numeral 6 denotes a matching center point detection unit that matches the registered pattern with the matching pattern and detects the center point of the matching pattern. Reference numeral 7 denotes a spiral scanning unit that changes the center point of radial scanning in a spiral manner to detect the center point. Reference numeral 8 denotes a pattern matching identification unit that matches the registered pattern with the matching pattern and matches the fingerprints. Reference numeral 9 denotes a matching result output unit that outputs the detection result of the matching center point detecting unit 6 and the matching result of the pattern matching identifying unit 8.

With respect to the fingerprint collation apparatus configured as described above, a schematic flowchart of FIG. 2, an image center point detection waveform diagram of FIG. 3, a radial scanning waveform diagram of FIG. 4, a collation pattern generation waveform diagram of FIG. The operation will be described with reference to the spiral scan trajectory diagram.

First, in step 11, the fingerprint image input section 1 inputs the fingerprint image 40 shown in FIG. Next, the image center detection unit 2 performs the X-axis luminance projection 41 and the Y-axis luminance projection 42 of the fingerprint image 40 to detect the X-axis image center point Xm and the Y-axis image center point Ym (steps 12 to 12). 13). In step 14, Xm is set at the radial scanning center point of the radial scanning unit 3.
And Ym. It is also possible to select one from a plurality of registered patterns from the scanning lines θ1 to θN of FIG. 4 pre-registered in the registered pattern storage unit 5 for the matching in step 15 and use all of the registered patterns as the central matching pattern. In order to shorten the matching time, it is possible to draw not a whole pattern but a certain range from the scanning center and read it as a center matching pattern. In the center matching pattern, like the matching pattern 58 of FIG. 4, the center 57 of the ridge line or the valley line is weighted so as to alleviate the positional deviation due to the change in the finger pressing force. Note that this weighting can be statistically derived from a plurality of data obtained when registering the registration pattern. It is assumed that the scanning pattern θ1 of the angle θ in FIG. 4 is selected from the registered patterns of plural scans as the center matching pattern. In step 16, the fingerprint input image 61 shown in FIG. 5 is scanned radially from the scanning center point by changing the angle, for example, by 1 degree. In step 17, the illuminance waveform 62 of the scan result is differentiated for each radial scan to obtain the boundary line waveform 63, and in step 18, the center point waveform 64 of the boundary line waveform 63 is drawn. In step 19, the registered pattern 58 of θ1 is compared with the center point waveform 64. If all the collations are not matched in the radial scanning, it is determined that the center point of the collation pattern is deviated from the center point of the registered pattern, and the center point of the collation pattern is moved according to the trajectory 70 of the spar scan in FIG. Redo the center point detection for matching from the radial scan. The spiral scanning follows the locus of the spiral scanning route 71, and determines the center point of the radial scanning from SP1 of the image center point to SP for each spiral scanning point 72.
Move sequentially from 2 to SPN. As a means for shortening the time for detecting the matching center point, it is conceivable to perform scanning by skipping the radial scanning angle by, for example, 2 to 3 degrees, or to set a valley line or a ridge as the center point of the radial scanning. In step 21, the spiral scanning point 72 is radially scanned from the specified SP1 to SPN according to the spiral scanning route 71, and the center point for the matching is detected. As a result, all the spiral scanning points 72 have the matching pattern 58 of θ1 and the registered pattern. If 64 does not match and the center point is not found, before matching with all registered patterns,
When the center point of the matching pattern is detected, it is determined that the registered pattern and the matching pattern do not match, and in step 22, the matching result is set as the fingerprint matching mismatch. In step 34, this collation result is transmitted to the collation result output unit 9. If the midpoint of the spiral scan matches the matching pattern 64 and the registered pattern 58 in step 19 before the SPN, it means that the central point for matching has been detected. In step 23, the approximate inclination angle α of the input fingerprint image can be known from the angle of the scanning line that matches the angle of the registered pattern. In step 24, the registered pattern 58 of θ1 to θN and the angle θ registered in the registered pattern storage unit are sequentially read, and the fingerprint image is read at the angle θ at which the fingerprint input image 61 from the fingerprint image input unit 1 is read by the radial scanning unit 3. In consideration of the deviation at the time of input, radial scanning is performed at θ ± α, and the illuminance waveform 62 of the scanning result is obtained by the collation pattern generation unit 4.
Is differentiated to obtain the boundary line waveform 63, the center point waveform 64 of the boundary line waveform 63 is drawn, and this is used as a matching pattern to match the registered pattern 58 (steps 24 to 29). When the collation with all registered patterns up to the scanning line θN is completed in step 30, the collation ratio between the collated pattern and the registered pattern is calculated in step 31 and compared with a specified value for determining whether the fingerprint collation matches. If the determination result in step 31 satisfies the specified value, the matching result is matched with the fingerprint matching in step 32, and if the determination result does not reach the specified value, the matching result is matched with the fingerprint matching in step 33. In step 34, this collation result is transmitted to the collation result output unit 9.

As described above, according to the above-described embodiment, since the radial scanning is performed starting from the center of the fingerprint image and the user is identified by using the collation pattern obtained by the radial scanning, the input condition There is little dependence, there is no need for preprocessing such as binarization and thinning of images as a matching algorithm, and it is not necessary to depict minutiae or ridge feature points between minutiae. It has an advantage of enabling individual identification by a matching algorithm.

[0015]

As is apparent from the above-described embodiment, the present invention has little dependency on input conditions and can be incorporated into a small device or card by personal identification by a simple collation algorithm. A small and inexpensive fingerprint collation device is realized.

[Brief description of drawings]

FIG. 1 is a schematic block diagram of an embodiment of a fingerprint matching device of the present invention.

FIG. 2 is a schematic flowchart of an embodiment of a fingerprint matching device of the present invention.

FIG. 3 is an image center point detection waveform diagram of an embodiment of the fingerprint matching device of the present invention.

FIG. 4 is a radial scanning waveform diagram of an embodiment of the fingerprint matching device of the present invention.

FIG. 5 is a matching pattern generation waveform diagram of an embodiment of the fingerprint matching device of the present invention.

FIG. 6 is a spiral scanning locus diagram of an embodiment of a fingerprint matching device of the present invention.

FIG. 7 is a front view of a minutiae of a conventional fingerprint matching device.

FIG. 8 is a schematic slow chart of a conventional fingerprint matching device.

[Explanation of symbols]

 1 Fingerprint image input unit 2 Image center detection unit 3 Radial scanning unit 4 Matching pattern generation unit 5 Registered pattern storage unit 6 Matching center point detection unit 7 Spiral scanning unit 8 Pattern matching identification unit 9 Matching result output unit 40, 61 Fingerprint input image 41 X-axis luminance projection waveform 42 Y-axis luminance projection waveform 51 Scan center point 52 Scan line 56, 57 Ridge or valley line center waveform 58 Registered pattern 62 Scan result illuminance waveform 63 Border line waveform 64 Boundary center point waveform 70 Spiral scan trajectory 71 Spiral scan route 72 Spiral scan point

 ─────────────────────────────────────────────────── ─── Continuation of the front page (72) Inventor Yoshimasa Shimizu 1-6-19 Azabudai, Minato-ku, Tokyo Ministry of Posts and Telecommunications Research Institute, Japan Post Research Institute (72) Inventor Naohisa Komatsu 1-chome, Hikarimachi, Kokubunji, Tokyo 26-24 (72) Inventor Masafumi Kinoshita 4-3-1, Tsunashima-higashi, Kohoku-ku, Yokohama-shi, Kanagawa Matsushita Communication Industrial Co., Ltd.

Claims (1)

[Claims] 1. A fingerprint image input section for inputting a fingerprint image, an image center point detecting section for detecting a center point of the fingerprint image input from the fingerprint image input section, and a radial scan for the fingerprint image. The radial scanning unit to perform, the matching pattern generation unit that detects the boundary between the ridge and valley lines of the fingerprint and the center point to generate a matching pattern for the result obtained by this radial scanning, and the input fingerprint image A registered pattern storage unit that stores a registered pattern that has been pre-registered for matching, a matching center point detection unit that matches the registered pattern with the matching pattern, and detects the center point of the matching pattern; A pattern for collating the spiral scanning unit for spirally changing the center point of the radial scanning to detect a point, the registered pattern and the collation pattern, and the same fingerprint or not And covering the identification section, the pattern matching identification section of the verification result and the fingerprint collation apparatus and a verification result output unit for outputting a detection result of the verification center point detecting section.