JP2859794B2 - Individual identification method using finger sweat glands - Google Patents
Individual identification method using finger sweat glandsInfo
- Publication number
- JP2859794B2 JP2859794B2 JP5131346A JP13134693A JP2859794B2 JP 2859794 B2 JP2859794 B2 JP 2859794B2 JP 5131346 A JP5131346 A JP 5131346A JP 13134693 A JP13134693 A JP 13134693A JP 2859794 B2 JP2859794 B2 JP 2859794B2
- Authority
- JP
- Japan
- Prior art keywords
- image
- fingerprint
- pixels
- sweat glands
- identification method
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Description
【0001】[0001]
【産業上の利用分野】この発明は、指の情報により人を
特定する際の指の汗腺による個人特定方法に関する。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a personal identification method using a sweat gland of a finger when identifying a person based on finger information.
【0002】[0002]
【従来の技術】個人を特定する場合、指紋は有効な情報
であり、例えば、指紋の隆線や特徴点の位置、パターン
マッチング等に基づき個人特定が行われる。しかしなが
ら、これらの手法において、隆線画像等と一緒に入力さ
れた汗腺画像はノイズとして扱われ、汗腺画像を排除す
る手法が主流であり、汗腺画像を有効に使用して人物を
特定する手法は存在しないのが現状である。2. Description of the Related Art When specifying an individual, a fingerprint is effective information, and the individual is specified based on, for example, positions of ridges and feature points of the fingerprint, pattern matching, and the like. However, in these methods, a sweat gland image input together with a ridge image or the like is treated as noise, and a method of eliminating a sweat gland image is mainstream. A method of effectively using a sweat gland image to specify a person is not a method. It does not exist at present.
【0003】[0003]
【発明が解決しようとする課題】この発明はこのような
従来の問題点を解消すべく創案されたもので、従来ノイ
ズとして扱われていた汗腺画像に注目し、指の汗腺によ
る個人特定方法を提供することを目的とする。SUMMARY OF THE INVENTION The present invention has been made to solve such a conventional problem, and focuses on a sweat gland image which has been conventionally treated as noise, and proposes a personal identification method using a sweat gland of a finger. The purpose is to provide.
【0004】[0004]
【課題を解決するための手段】この発明に係る指の汗腺
による個人特定方法は、指紋画像を入力して2値化し、
この2値化画像を細線化、ラベリングしてラベリング画
像における各グループの画素数をカウントして画素数が
所定値以上のグループを指紋隆線間の凹部として消去
し、指紋の所定領域における上記の凹部消去後に残った
グループを汗腺とし、その数と予め登録された数を比較
し、個人を特定する。According to the present invention, there is provided a personal identification method based on sweat glands of a finger, wherein a fingerprint image is inputted and binarized.
The binarized image is thinned and labeled, the number of pixels in each group in the labeled image is counted, groups having a number of pixels equal to or more than a predetermined value are erased as concave portions between fingerprint ridges, and The group remaining after the elimination of the concave portion is defined as a sweat gland, and the number is compared with a previously registered number to identify an individual.
【0005】[0005]
【作用】この発明に係る指の汗腺による個人特定方法
は、指紋画像を入力して画像を2値化するので指紋の隆
線部および指紋の汗腺部と隆線間の凹部を判別でき、こ
の2値化画像を細線化してラベリングして各グループの
画素数をカウントし、画素数が所定値以上のグループを
隆線の凹部として消去することができるので汗腺のみ抽
出可能となる。In the personal identification method using the sweat glands of a finger according to the present invention, a fingerprint image is input and the image is binarized, so that a ridge portion of the fingerprint and a concave portion between the sweat gland portion and the ridge of the fingerprint can be determined. The binarized image is thinned and labeled, the number of pixels in each group is counted, and a group having the number of pixels equal to or more than a predetermined value can be eliminated as a concave portion of a ridge, so that only sweat glands can be extracted.
【0006】[0006]
【実施例】次に、この発明に係る指の汗腺による個人特
定方法の1実施例を図面に基づいて説明する。図1は本
発明を実施するフローチャート、図4は本発明を実施す
るための装置のブロック図である。本装置は、例えば中
央処理部CPU、画像処理部IPUおよび画像メモリI
Mから構成され、中央処理部CPU、画像処理部IPU
及び画像メモリIMはシステムバスSBで接続されてお
り、さらに画像処理部IPUと画像メモリIMはローカ
ルバスLBでつながれている。DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Next, an embodiment of a method for specifying an individual using sweat glands of a finger according to the present invention will be described with reference to the drawings. FIG. 1 is a flowchart for implementing the present invention, and FIG. 4 is a block diagram of an apparatus for implementing the present invention. This apparatus includes, for example, a central processing unit CPU, an image processing unit IPU, and an image memory I.
M, a central processing unit CPU, an image processing unit IPU
The image memory IM is connected by a system bus SB, and the image processing unit IPU and the image memory IM are connected by a local bus LB.
【0007】まず検出面に触れている指紋画像を入力装
置(図略)で入力し(ステップ1−1)、入力画像を予
め登録してある登録データに照らして位置合わせを行う
(ステップ1−2)。この位置合わせした入力画像を画
像メモリIMに登録し(ステップ1−3)、この登録さ
れた入力画像をローカルバスLBを介して画像処理部I
PUに取り込み、ここで図2に示すように2値化する
(ステップ1−4)。これにより、指紋の隆線および指
紋の汗腺と隆線間の凹部を分ける。First, a fingerprint image touching the detection surface is input by an input device (not shown) (step 1-1), and the input image is aligned with reference to registered data (step 1-). 2). The registered input image is registered in the image memory IM (step 1-3), and the registered input image is stored in the image processing unit I via the local bus LB.
The data is taken into the PU and is binarized as shown in FIG. 2 (step 1-4). This separates the ridge of the fingerprint and the recess between the sweat gland and the ridge of the fingerprint.
【0008】次に、この2値画像に細線化処理を施す
(ステップ1−5)。細線化の結果、図3のように隆線
間の凹部の連続性は保持されるが、一つ一つ独立してい
る汗腺に細線化処理を施すと、その殆どが弧立点に近い
数個の画素からなる画像となる。次に、この細線化画像
にラベリング処理を施す(ステップ1−6)。Next, thinning processing is performed on the binary image (step 1-5). As a result of the thinning, the continuity of the concave portions between the ridges is maintained as shown in FIG. 3, but when the individual sweat glands are subjected to the thinning processing, almost all of them are close to the arcing point. The image is composed of pixels. Next, a labeling process is performed on the thinned image (step 1-6).
【0009】そして、ラベリング画像における各グルー
プの画素数を中央処理部CPUで数える(ステップ1−
7)。この場合、連続性を保持している隆線間の凹部画
像の画素数は多くなるが、孤立点に近い汗腺の画像の画
素数は逆に少なくなる。Then, the number of pixels of each group in the labeling image is counted by the central processing unit CPU (step 1-).
7). In this case, the number of pixels of the concave image between the ridges maintaining continuity increases, but the number of pixels of the image of the sweat gland near the isolated point decreases.
【0010】次に、画素数が所定値以上のラベリング画
像を消去する(ステップ1−8)。すなわち、画素数が
所定値以下の場合は汗腺とみなし、逆に、画素数が所定
値以上のラベリング画像は指紋の隆線の凹部とみなすこ
とにより、汗腺のみを残し、隆線の凹部を消去するもの
である。Next, a labeling image whose number of pixels is equal to or larger than a predetermined value is deleted (step 1-8). That is, when the number of pixels is equal to or less than a predetermined value, it is regarded as a sweat gland, and conversely, a labeling image having a number of pixels equal to or more than a predetermined value is regarded as a concave portion of a ridge of a fingerprint, thereby leaving only the sweat gland and eliminating the concave portion of the ridge. Is what you do.
【0011】次に、指紋の所定領域Aの汗腺数を数え
(ステップ1−9)、予め登録されている本人の所定領
域の汗腺数とを比較し、その差が許容範囲以内か否かを
判断する(ステップ1−10)。許容範囲以内の場合
は、本人と特定する(ステップ1−11)。しかしなが
ら、許容範囲でない場合は、本人ではないと判断するも
のである(ステップ1−12)。Next, the number of sweat glands in the predetermined region A of the fingerprint is counted (step 1-9), and the number is compared with the number of sweat glands in the predetermined region of the person registered in advance to determine whether the difference is within an allowable range. A decision is made (step 1-10). If it is within the allowable range, the user is identified (step 1-11). However, if it is not within the allowable range, it is determined that the user is not the person (step 1-12).
【0012】[0012]
【発明の効果】以上のように、この発明に係る指の汗腺
による個人特定方法は、指紋画像を入力して2値化し、
この2値化画像を細線化、ラベリングしてラベリング画
像における各グループの画素数をカウントして画素数が
所定値以上のグループを指紋隆線間の凹部として消去
し、指紋の所定領域における前述の凹部消去後に残った
グループを汗腺とし、その数と予め登録された数を比較
し、個人を特定するので、従来画像ノイズとして扱われ
ていた汗腺画像に基づき迅速かつ簡単な方法で個人特定
が可能という効果を有する。As described above, the personal identification method using the sweat glands of the finger according to the present invention inputs a fingerprint image and binarizes it.
The binarized image is thinned and labeled, the number of pixels in each group in the labeled image is counted, groups having a number of pixels equal to or more than a predetermined value are erased as recesses between fingerprint ridges, and the above-described operation in a predetermined region of the fingerprint is performed. Sweat glands are used as the remaining groups after the elimination of the depressions, and the number is compared with the pre-registered number to identify the individual, so that individuals can be identified quickly and easily based on sweat gland images that were conventionally treated as image noise. It has the effect of.
【図1】本発明の1実施例を示すフローチャートであ
る。FIG. 1 is a flowchart showing one embodiment of the present invention.
【図2】2値画像の概念図である。FIG. 2 is a conceptual diagram of a binary image.
【図3】細線化画像の概念図である。FIG. 3 is a conceptual diagram of a thinned image.
【図4】本発明を実施する装置のブロック図である。FIG. 4 is a block diagram of an apparatus for implementing the present invention.
CPU 中央処理部 IPU 画像処理部 IM 画像メモリ SL システムバス LS ローカルバス A 所定領域 CPU Central processing unit IPU Image processing unit IM Image memory SL System bus LS Local bus A Predetermined area
Claims (1)
化し、この2値化画像を細線化し、この細線化画像をラ
ベリングし、このラベリング画像における各グループの
画素数をカウントし、この画素数が所定値以上のグルー
プを消去し、指紋の所定領域における上記のグループ消
去後に残ったグループの数と予め登録された数を比較す
ることにより入力者を特定することを特徴とする指の汗
腺による個人特定方法。1. A fingerprint image is input, the input image is binarized, the binarized image is thinned, the thinned image is labeled, and the number of pixels of each group in the labeled image is counted. A group of fingers whose number of pixels is equal to or greater than a predetermined value is erased, and an input person is identified by comparing the number of groups remaining after the above-described group erasure in a predetermined area of the fingerprint with a previously registered number. Personal identification method by sweat glands.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP5131346A JP2859794B2 (en) | 1993-05-07 | 1993-05-07 | Individual identification method using finger sweat glands |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP5131346A JP2859794B2 (en) | 1993-05-07 | 1993-05-07 | Individual identification method using finger sweat glands |
Publications (2)
Publication Number | Publication Date |
---|---|
JPH08161487A JPH08161487A (en) | 1996-06-21 |
JP2859794B2 true JP2859794B2 (en) | 1999-02-24 |
Family
ID=15055795
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP5131346A Expired - Fee Related JP2859794B2 (en) | 1993-05-07 | 1993-05-07 | Individual identification method using finger sweat glands |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP2859794B2 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020240715A1 (en) | 2019-05-28 | 2020-12-03 | 日本電気株式会社 | Information processing device, information processing method, and recording medium |
US11816921B2 (en) | 2019-05-28 | 2023-11-14 | Nec Corporation | Drawing quasi-ridge line based on sweat gland pore information |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP4262471B2 (en) * | 2002-11-12 | 2009-05-13 | 富士通株式会社 | Biometric feature data acquisition device |
-
1993
- 1993-05-07 JP JP5131346A patent/JP2859794B2/en not_active Expired - Fee Related
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020240715A1 (en) | 2019-05-28 | 2020-12-03 | 日本電気株式会社 | Information processing device, information processing method, and recording medium |
US11749017B2 (en) | 2019-05-28 | 2023-09-05 | Nec Corporation | Information processing apparatus, information processing method, and storage medium |
US11816921B2 (en) | 2019-05-28 | 2023-11-14 | Nec Corporation | Drawing quasi-ridge line based on sweat gland pore information |
Also Published As
Publication number | Publication date |
---|---|
JPH08161487A (en) | 1996-06-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2859794B2 (en) | Individual identification method using finger sweat glands | |
JP2909136B2 (en) | Fingerprint image processing device | |
JP2866461B2 (en) | Fingerprint collation device | |
JP2557487B2 (en) | Personal verification device | |
JP2551631B2 (en) | Personal verification device | |
JP2974857B2 (en) | Fingerprint dictionary registration processing method | |
JP2702786B2 (en) | Fingerprint collation device | |
JP2768308B2 (en) | Feature point extraction method of face image using pattern recognition | |
JP2720995B2 (en) | Personal verification device | |
JP2868909B2 (en) | Fingerprint collation device | |
JP3033595B2 (en) | Fingerprint image registration method | |
JP3009542B2 (en) | Fingerprint collation processor | |
JP2695238B2 (en) | Personal verification device | |
JPH08110945A (en) | Method for inputting fingerprint | |
JP2919653B2 (en) | Fingerprint collation device | |
JPH02196380A (en) | Fingerprint register device | |
JP2795922B2 (en) | Fingerprint image thinning processing method | |
JP2951472B2 (en) | Fingerprint matching device and fingerprint matching method | |
JP2943814B2 (en) | Fingerprint image registration method | |
JPS63153687A (en) | Method and apparatus for detecting finger print pattern | |
JP2875055B2 (en) | Fingerprint matching method | |
JP2828820B2 (en) | Fingerprint collation device | |
JPS63229583A (en) | Method and device for fingerprint image collation | |
JPH05197792A (en) | Binarizing device for finger print collating device | |
JPS63159990A (en) | Automatic tracing method for collating point in case of fingerprint collation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20071204 Year of fee payment: 9 |
|
FPAY | Renewal fee payment (event date is renewal date of database) |
Free format text: PAYMENT UNTIL: 20081204 Year of fee payment: 10 |
|
LAPS | Cancellation because of no payment of annual fees |