JP2022060505A - Fingerprint processing device, fingerprint processing method, program, and fingerprint processing circuit - Google Patents

Fingerprint processing device, fingerprint processing method, program, and fingerprint processing circuit Download PDF

Info

Publication number
JP2022060505A
JP2022060505A JP2022026934A JP2022026934A JP2022060505A JP 2022060505 A JP2022060505 A JP 2022060505A JP 2022026934 A JP2022026934 A JP 2022026934A JP 2022026934 A JP2022026934 A JP 2022026934A JP 2022060505 A JP2022060505 A JP 2022060505A
Authority
JP
Japan
Prior art keywords
fingerprint
representative
feature points
collation
feature point
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.)
Granted
Application number
JP2022026934A
Other languages
Japanese (ja)
Other versions
JP7239034B2 (en
Inventor
聡 廣川
Satoshi Hirokawa
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
NEC Corp
Original Assignee
NEC Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Priority claimed from JP2020188189A external-priority patent/JP7031717B2/en
Application filed by NEC Corp filed Critical NEC Corp
Priority to JP2022026934A priority Critical patent/JP7239034B2/en
Publication of JP2022060505A publication Critical patent/JP2022060505A/en
Application granted granted Critical
Publication of JP7239034B2 publication Critical patent/JP7239034B2/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Collating Specific Patterns (AREA)

Abstract

PROBLEM TO BE SOLVED: To provide a fingerprint processing device which allows for quickly matching fingerprints without having to identify the centers of the fingerprints.
SOLUTION: A fingerprint processing device is configured to determine representative feature points to be used for matching processing from among a plurality of feature points of a fingerprint identified in a fingerprint image to be matched on the basis of first distance to an image area of the fingerprint image with uncertain image clarity.
SELECTED DRAWING: Figure 1
COPYRIGHT: (C)2022,JPO&INPIT

Description

本発明は、指紋処理装置、指紋処理方法、プログラム、指紋処理回路に関する。 The present invention relates to a fingerprint processing device, a fingerprint processing method, a program, and a fingerprint processing circuit.

指紋照合を行う場合には一例として指紋画像から指紋の中心(コア)を算出し、その中心を基準とした特徴点の位置等の情報を用いて、指紋照合元と指紋照合先との画像の照合を行っている。しかしながら指紋画像における指紋の中心の位置の特定を誤ると、指紋の中心と各特徴点との関係がずれることにより、照合の精度が悪化する。指紋照合に関連する技術が特許文献1~特許文献3が開示されている。 When performing fingerprint collation, as an example, the center (core) of the fingerprint is calculated from the fingerprint image, and information such as the position of the feature point with respect to the center is used to obtain the image of the fingerprint collation source and the fingerprint collation destination. We are collating. However, if the position of the center of the fingerprint in the fingerprint image is erroneously specified, the relationship between the center of the fingerprint and each feature point is deviated, and the accuracy of collation deteriorates. Patent Documents 1 to 3 disclose techniques related to fingerprint collation.

特開平10-177650号公報Japanese Unexamined Patent Publication No. 10-177650 特開2015-228070号公報JP-A-2015-228070 特許第5822303号公報Japanese Patent No. 5822303

上述のような問題点の為、指紋の中心を特定しない指紋照合であって照合速度の速い指紋処理装置が求められている。 Due to the above-mentioned problems, there is a demand for a fingerprint processing device that is a fingerprint collation that does not specify the center of the fingerprint and has a high collation speed.

そこでこの発明は、上述の課題を解決する指紋処理装置、指紋処理方法、プログラム、指紋処理回路を提供することを目的としている。 Therefore, an object of the present invention is to provide a fingerprint processing device, a fingerprint processing method, a program, and a fingerprint processing circuit that solve the above-mentioned problems.

本発明の第1の態様によれば、指紋処理装置は、照合元の指紋画像において特定した指紋の複数の特徴点のうち、他の特徴点との間の各第一の距離のうち最小の距離を示す第一度合に基づく代表値が大きい方から順に選択された所定数の特徴点を、前記指紋の照合処理に用いる代表特徴点として判定する照合処理部を有する。 According to the first aspect of the present invention, the fingerprint processing apparatus is the smallest of the first distances between the plurality of feature points of the fingerprint identified in the fingerprint image of the collation source and the other feature points. It has a collation processing unit that determines a predetermined number of feature points selected in order from the one having the largest representative value based on the first combination indicating the distance as the representative feature points used for the fingerprint collation process.

本発明の第2の態様によれば、指紋処理方法は、照合元の指紋画像において特定した指紋の複数の特徴点のうち、他の特徴点との間の各第一の距離のうち最小の距離を示す第一度合に基づく代表値が大きい方から順に選択された所定数の特徴点を、前記指紋の照合処理に用いる代表特徴点として判定する。 According to the second aspect of the present invention, the fingerprint processing method is the smallest of the first distances between the plurality of feature points of the fingerprint identified in the fingerprint image of the collation source and the other feature points. A predetermined number of feature points selected in order from the one having the largest representative value based on the first combination indicating the distance are determined as representative feature points used in the fingerprint collation process.

本発明の第3の態様によれば、プログラムは、コンピュータに、照合元の指紋画像において特定した指紋の複数の特徴点のうち、他の特徴点との間の各第一の距離のうち最小の距離を示す第一度合に基づく代表値が大きい方から順に選択された所定数の特徴点を、前記指紋の照合処理に用いる代表特徴点として判定させる。 According to a third aspect of the invention, the program tells the computer the smallest of each first distance between the plurality of feature points of the fingerprint identified in the fingerprint image of the collation source and the other feature points. A predetermined number of feature points selected in order from the one having the largest representative value based on the first combination indicating the distance of the above are determined as representative feature points used in the fingerprint collation process.

本発明の第4の態様によれば、指紋処理回路は、照合元の指紋画像において特定した指紋の複数の特徴点のうち、他の特徴点との間の各第一の距離のうち最小の距離を示す第一度合に基づく代表値が大きい方から順に選択された所定数の特徴点を、前記指紋の照合処理に用いる代表特徴点として判定する。 According to a fourth aspect of the present invention, the fingerprint processing circuit is the smallest of the first distances between the plurality of feature points of the fingerprint identified in the fingerprint image of the collation source and the other feature points. A predetermined number of feature points selected in order from the one having the largest representative value based on the first combination indicating the distance are determined as representative feature points used in the fingerprint collation process.

本発明によれば、指紋の中心を特定せずとも速度が速く照合することのできる指紋処理装置、指紋処理方法、プログラム、指紋処理回路を提供することができる。 According to the present invention, it is possible to provide a fingerprint processing device, a fingerprint processing method, a program, and a fingerprint processing circuit capable of collating at a high speed without specifying the center of the fingerprint.

指紋処理装置を含む指紋照合システムを示す図である。It is a figure which shows the fingerprint collation system including the fingerprint processing apparatus. 指紋処理装置のハードウェア構成図である。It is a hardware block diagram of the fingerprint processing apparatus. 指紋処理装置の機能ブロック図である。It is a functional block diagram of the fingerprint processing apparatus. 指紋処理装置の処理フローを示す図である。It is a figure which shows the processing flow of the fingerprint processing apparatus. 特徴点検出部が検出する特徴点を説明するための図である。It is a figure for demonstrating the feature point detected by the feature point detection part. 指紋画像において判定された鮮明領域および不鮮明領域と特徴点とを示す図である。It is a figure which shows the clear region and the unclear region and a feature point determined in the fingerprint image. 指紋画像において判定された隆線の安定度を示す図である。It is a figure which shows the stability of the ridge line determined in the fingerprint image. 代表度算出フローを示す図である。It is a figure which shows the representative degree calculation flow. 特徴点と代表特徴点を視覚的に示す図である。It is a figure which visually shows the characteristic point and the representative characteristic point. 代表特徴点の特徴量の特定概要を示す第一の図である。It is the first figure which shows the specific outline of the feature quantity of a representative feature point. 代表特徴点の特徴量を付与する処理フローを示す第一の図である。It is the first figure which shows the processing flow which gives the feature amount of a representative feature point. 指紋特徴量に基づく類似度の計算概要を示す第一の図である。FIG. 1 is a first diagram showing an outline of calculation of similarity based on fingerprint features. 代表特徴点の特徴量の特定概要を示す第二の図である。It is a second figure which shows the specific outline of the feature quantity of a representative feature point. 代表特徴点の特徴量の特定概要を示す第三の図である。It is a third figure which shows the specific outline of the feature quantity of a representative feature point. 代表特徴点の特徴量を付与する処理フローを示す第二の図である。It is a second figure which shows the processing flow which gives the feature amount of a representative feature point. 指紋特徴量に基づく類似度の計算概要を示す第二の図である。FIG. 2 is a second diagram showing an outline of calculation of similarity based on fingerprint features. 指紋処理装置の最少構成を示す図である。It is a figure which shows the minimum structure of the fingerprint processing apparatus.

以下、本発明の一実施形態による指紋処理装置を図面を参照して説明する。
図1は同実施形態による指紋処理装置を含む指紋照合システムを示す図である。
指紋照合システムは、図1に示すように指紋処理装置1、指紋読取機2、データベース3を含んで構成されている。指紋処理装置1は指紋読取機2と通信ケーブルを介して接続されている。また指紋処理装置1はデータベース3と通信ケーブルを介して接続されている。指紋処理装置1は指紋読取機2から取得した指紋画像から得た指紋情報と、データベース3に格納されている指紋情報とを比較することにより指紋照合の処理を行う。データベース3には、予め多くの人の指紋画像から得られた指紋情報が記録される。
Hereinafter, the fingerprint processing apparatus according to the embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a diagram showing a fingerprint verification system including a fingerprint processing device according to the same embodiment.
As shown in FIG. 1, the fingerprint verification system includes a fingerprint processing device 1, a fingerprint reader 2, and a database 3. The fingerprint processing device 1 is connected to the fingerprint reader 2 via a communication cable. Further, the fingerprint processing device 1 is connected to the database 3 via a communication cable. The fingerprint processing device 1 performs fingerprint collation processing by comparing the fingerprint information obtained from the fingerprint image acquired from the fingerprint reader 2 with the fingerprint information stored in the database 3. Fingerprint information obtained from fingerprint images of many people in advance is recorded in the database 3.

図2は指紋処理装置のハードウェア構成図である。
指紋処理装置1は、CPU(Central Processing Unit)11,RAM(Random Access Memory)12、ROM(Read Only Memory)13、SSD(Solid State Drive)14、通信モジュール15、表示画面16、IF(Interface)17などを備えてよい。指紋処理装置1はこのような各機能を備えたコンピュータである。
FIG. 2 is a hardware configuration diagram of the fingerprint processing device.
The fingerprint processing device 1 includes a CPU (Central Processing Unit) 11, a RAM (Random Access Memory) 12, a ROM (Read Only Memory) 13, an SSD (Solid State Drive) 14, a communication module 15, a display screen 16, and an IF (Interface). 17 and the like may be provided. The fingerprint processing device 1 is a computer having each of these functions.

図3は指紋処理装置の機能ブロック図である。
指紋処理装置1はCPU11において指紋処理プログラムを実行する。これにより指紋処理装置1には、画像取得部21、鮮明度判定部22、隆線品質判定部23、特徴点検出部24、照合処理部25の機能を備える。また指紋処理装置1は記憶部15を備える。
FIG. 3 is a functional block diagram of the fingerprint processing device.
The fingerprint processing device 1 executes a fingerprint processing program in the CPU 11. As a result, the fingerprint processing device 1 is provided with the functions of an image acquisition unit 21, a sharpness determination unit 22, a ridge quality determination unit 23, a feature point detection unit 24, and a collation processing unit 25. Further, the fingerprint processing device 1 includes a storage unit 15.

画像取得部21は指紋読取機2より指紋画像を取得する。
鮮明度判定部22は指紋画像中の各画素の指紋の鮮明度を判定して分類する。
隆線品質判定部23は指紋画像中の各画素に写る指紋の隆線の品質を判定する。
特徴点検出部24は指紋画像に映る指紋の特徴点を検出する。
照合処理部25は画像取得部21の取得した指紋画像から得た指紋情報と、データベース3に記録されている複数の人の指紋情報との比較による照合処理を行う。
The image acquisition unit 21 acquires a fingerprint image from the fingerprint reader 2.
The sharpness determination unit 22 determines and classifies the sharpness of the fingerprint of each pixel in the fingerprint image.
The ridge quality determination unit 23 determines the quality of the ridge of the fingerprint reflected in each pixel in the fingerprint image.
The feature point detection unit 24 detects the feature points of the fingerprint reflected in the fingerprint image.
The collation processing unit 25 performs collation processing by comparing the fingerprint information obtained from the fingerprint image acquired by the image acquisition unit 21 with the fingerprint information of a plurality of people recorded in the database 3.

本実施形態において照合処理部25は、照合元の指紋画像において特定した指紋の特徴点のうち、他の特徴点との間の距離が長いことを示す第一度合に基づいて当該第一度合の値が大きい複数の特徴点を、指紋照合に用いる代表特徴点と判定する。
または照合処理部25は、照合元の指紋画像において特定した指紋の特徴点のうち、指紋画像において特定された画像の鮮明さが不明な画素領域までの距離が長いことを示す第二度合に基づいて当該第二度合の値が大きい複数の特徴点を、代表特徴点と判定する。
または照合処理部25は、他の特徴点との間の距離が長いことを示す第一度合と、指紋画像において特定された画像の鮮明さが不明な画素領域までの距離が長いことを示す第二度合とを用いて複数の代表特徴点を判定する。例えば、第一度合に第二度合を乗じ、この値に基づいて代表度を算出し、当該代表度に基づいて複数の代表特徴点を判定してよい。
In the present embodiment, the collation processing unit 25 is based on the first case indicating that the distance between the feature points of the fingerprint specified in the fingerprint image of the collation source and the other feature points is long. A plurality of feature points having a large total value are determined to be representative feature points used for fingerprint verification.
Alternatively, the collation processing unit 25 is based on a second degree indicating that among the feature points of the fingerprint specified in the fingerprint image of the collation source, the distance to the pixel region where the sharpness of the image specified in the fingerprint image is unknown is long. Therefore, a plurality of feature points having a large second degree value are determined to be representative feature points.
Alternatively, the collation processing unit 25 indicates that the distance to the first pixel region, which indicates that the distance to the other feature points is long, and the pixel region, which indicates that the sharpness of the image specified in the fingerprint image is unknown, is long. A plurality of representative feature points are determined using the second degree. For example, the first degree may be multiplied by the second degree, the representative degree may be calculated based on this value, and a plurality of representative feature points may be determined based on the representative degree.

照合処理部25は指紋画像において特定した指紋の特徴点に対応する画素における隆線の安定度合をさらに用いて代表度を算出し、当該代表度に基づいて代表特徴点を判定してよい。 The collation processing unit 25 may further calculate the representativeness by using the stability of the ridge in the pixel corresponding to the characteristic point of the fingerprint specified in the fingerprint image, and determine the representative characteristic point based on the representativeness.

そして照合処理部25は、代表度の高い特徴を示す複数の代表特徴点を特定し、照合元の指紋画像におけるそれら複数の代表特徴点と、データベース3に記録されている照合先の指紋画像における複数の代表特徴点とを用いて照合処理を行う。 Then, the collation processing unit 25 identifies a plurality of representative feature points showing features having a high degree of representativeness, and in the plurality of representative feature points in the fingerprint image of the collation source and the fingerprint image of the collation destination recorded in the database 3. Collation processing is performed using a plurality of representative feature points.

図4は指紋処理装置の処理フローを示す図である。
次に指紋処理装置の処理の詳細について順を追って説明する。
まず指紋処理装置1において画像取得部21が指紋読取機2から指紋画像を取得する(ステップS101)。画像取得部21は指紋画像を一時的にRAM12などに記録する。すると鮮明度判定部22は指紋画像をRAM12から読み取り、指紋画像中全体に渡って設定した各矩形領域の鮮明度を判定する(ステップS102)。各矩形領域は画素に対応する領域であってもよいし、画素とは別に設定した矩形の領域であってもよい。鮮明度判定部22は各矩形領域の鮮明度を判定すると、指紋画像中の矩形領域を特定するIDと鮮明度とをRAM12に記録する。鮮明度は例えば鮮明か不鮮明かを示す2値であってよい。鮮明度の判定方法はどのような方法であってもよい。例えば鮮明度判定部22は特開平10-177650号公報に記述されている品質指標抽出手段の行う処理と同様の処理により鮮明度を算出してよい。
FIG. 4 is a diagram showing a processing flow of the fingerprint processing apparatus.
Next, the details of the processing of the fingerprint processing apparatus will be described step by step.
First, in the fingerprint processing device 1, the image acquisition unit 21 acquires a fingerprint image from the fingerprint reader 2 (step S101). The image acquisition unit 21 temporarily records the fingerprint image in the RAM 12 or the like. Then, the sharpness determination unit 22 reads the fingerprint image from the RAM 12 and determines the sharpness of each rectangular region set over the entire fingerprint image (step S102). Each rectangular area may be an area corresponding to a pixel, or may be a rectangular area set separately from the pixel. When the sharpness determination unit 22 determines the sharpness of each rectangular area, the RAM 12 records an ID for specifying the rectangular area in the fingerprint image and the sharpness. The sharpness may be, for example, a binary value indicating whether it is sharp or unclear. Any method may be used for determining the sharpness. For example, the sharpness determination unit 22 may calculate the sharpness by the same processing as that performed by the quality index extraction means described in JP-A No. 10-177650.

また隆線品質判定部23は指紋画像をRAM12から読み取り、指紋画像中の上記矩形領域のうち隆線が映る画素を特定し、その画素における隆線の安定度を判定する(ステップS103)。隆線の安定度とは隆線の幅の安定度合を意味する。隆線品質判定部23による隆線の安定度は、一例として設定した矩形領域における指紋隆線を示す黒色画像と指紋隆線間を示す白色画像の両方の分散値により示される。隆線品質判定部23は指紋隆線を示す黒色画像と指紋隆線間を示す白色画像の両方の分散値が閾値より高い矩形領域を、隆線の安定度が高い矩形領域と判定する。他方、隆線品質判定部23は指紋隆線を示す黒色画像または指紋隆線間を示す白色画像のいずれかの分散値が閾値以下の矩形領域を、隆線の安定度が低い矩形領域と判定する。隆線品質判定部23は、矩形領域のIDと、隆線の安定度が高いか低いかを示すフラグとを対応付けた情報をRAM12等に記録する。隆線の安定度のより詳細な算出は、例えば、特許第5822303号公報のステップS301~ステップS305として記述されている技術等を利用してよい。 Further, the ridge quality determination unit 23 reads the fingerprint image from the RAM 12, identifies a pixel in which the ridge is reflected in the rectangular region in the fingerprint image, and determines the stability of the ridge in that pixel (step S103). The stability of the ridge means the stability of the width of the ridge. The stability of the ridge line by the ridge line quality determination unit 23 is indicated by the dispersion value of both the black image showing the fingerprint ridge line and the white image showing the distance between the fingerprint ridge lines in the rectangular region set as an example. The ridge quality determination unit 23 determines a rectangular region in which the dispersion values of both the black image showing the fingerprint ridge and the white image showing the distance between the fingerprint ridges are higher than the threshold value as the rectangular region having high stability of the ridge. On the other hand, the ridge quality determination unit 23 determines that a rectangular region having a dispersion value of either a black image showing the fingerprint ridge or a white image showing the distance between the fingerprint ridges is equal to or less than the threshold value is a rectangular region having low stability of the ridge. do. The ridge quality determination unit 23 records information in the RAM 12 or the like in which the ID of the rectangular region and the flag indicating whether the stability of the ridge is high or low are associated with each other. For more detailed calculation of the stability of the ridge line, for example, the technique described as step S301 to step S305 of Japanese Patent No. 5822303 may be used.

特徴点検出部24は指紋画像をRAM12から読み取り、当該指紋画像に映る指紋の特徴点を検出する(ステップS104)。特徴点の検出は従来の検出手法を用いてよい。より具体的には特徴点検出部24は、2種類の特徴点を指紋画像から抽出する。 The feature point detection unit 24 reads the fingerprint image from the RAM 12 and detects the feature points of the fingerprint reflected in the fingerprint image (step S104). Conventional detection methods may be used to detect feature points. More specifically, the feature point detection unit 24 extracts two types of feature points from the fingerprint image.

図5は特徴点検出部が検出する特徴点を説明するための図である。
特徴点検出部24が対象とする第1の特徴点は、隆線の終点(端点)である。図5(a)には、2本の隆線501、502に挟まれた第1特徴点P1が図示されている。特徴点検出部24は、図5(a)に示す第1特徴点P1のような隆線の端点を、入力された指紋画像の第1特徴点P1として検出する。具体的には、特徴点検出部24は、指紋画像の全体を走査しながら第1特徴点P1を検出していく。
FIG. 5 is a diagram for explaining the feature points detected by the feature point detection unit.
The first feature point targeted by the feature point detection unit 24 is the end point (end point) of the ridge. FIG. 5A shows a first feature point P1 sandwiched between two ridges 501 and 502. The feature point detection unit 24 detects the end point of the ridge like the first feature point P1 shown in FIG. 5A as the first feature point P1 of the input fingerprint image. Specifically, the feature point detection unit 24 detects the first feature point P1 while scanning the entire fingerprint image.

特徴点検出部24が対象とする第2の特徴点は、隆線の分岐点である。図5(b)には、隆線511が2本の隆線512、513に分岐する第2特徴点P2が図示されている。特徴点検出部24は、図5(b)に示す第2特徴点P2のような隆線の分岐点を、入力された指紋画像の第2特徴点P2として検出する。 The second feature point targeted by the feature point detection unit 24 is a branch point of a ridge. FIG. 5B illustrates a second feature point P2 in which the ridge 511 branches into two ridges 512 and 513. The feature point detection unit 24 detects the branch point of the ridge like the second feature point P2 shown in FIG. 5B as the second feature point P2 of the input fingerprint image.

次に、特徴点検出部24は、検出した各特徴点から延びる指紋の隆線の延伸方向を算出する。第1特徴点P1に関しては、図5(a)に示すように、第1特徴点P1から隆線500が発生する方向(矢印504の方向)が、第1特徴点P1からの隆線の延伸方向と定義される。 Next, the feature point detection unit 24 calculates the extending direction of the ridge of the fingerprint extending from each detected feature point. Regarding the first feature point P1, as shown in FIG. 5A, the direction in which the ridge line 500 is generated from the first feature point P1 (direction of arrow 504) is the extension of the ridge line from the first feature point P1. Defined as direction.

第2特徴点P2に関しては、図5(b)に示すように、隆線511が第2特徴点P2にて2本の隆線512、513に分岐している場合、第2特徴点P2から2本の隆線の間(ベクトルの中間)を進行する方向(矢印514の方向)が、第2特徴点P2からの隆線の延伸方向と定義される。 Regarding the second feature point P2, as shown in FIG. 5B, when the ridge line 511 branches into two ridge lines 512 and 513 at the second feature point P2, the ridge line starts from the second feature point P2. The direction (direction of arrow 514) traveling between the two ridges (middle of the vector) is defined as the extension direction of the ridge from the second feature point P2.

特徴点検出部24は、指紋画像において検出した特徴点の位置情報や当該特徴点から延びる隆線の延伸方向の情報(延伸方向情報)をRAM12に記録する。なお、検出された第1特徴点P1、第2特徴点P2に関する位置情報(座標)は、指紋画像内でのピクセル位置や矩形領域のIDの形式で記録されてよい。また、各特徴点を原点に設定したXY座標系におけるX軸と特徴点からの隆線の延伸方向との間の角度が、各特徴点からの隆線の延伸方向として記録されてよい。 The feature point detection unit 24 records in the RAM 12 the position information of the feature points detected in the fingerprint image and the information in the stretching direction of the ridge extending from the feature point (stretching direction information). The detected position information (coordinates) regarding the first feature point P1 and the second feature point P2 may be recorded in the format of the pixel position in the fingerprint image or the ID of the rectangular area. Further, the angle between the X axis in the XY coordinate system in which each feature point is set as the origin and the extension direction of the ridge line from the feature point may be recorded as the extension direction of the ridge line from each feature point.

図6は指紋画像において判定された鮮明領域および不鮮明領域と特徴点とを示す図である。
この図が示す指紋画像における網掛け表示されている領域は、鮮明度が閾値未満の不鮮明領域E1を示している。また網掛け表示されていない領域は、鮮明度が閾値以上の鮮明領域E2を示している。このような指紋画像において、当該画像中の丸印や四角印で囲まれている局所点が特徴点を示している。特徴点のうち丸印で示す特徴点は第1特徴点P1を示す。特徴点のうち四角印で示す特徴点は第2特徴点P2を示す。丸印や四角印から出ている直線が各特徴点から延伸する隆線の延伸方向を示している。
FIG. 6 is a diagram showing a clear region, an unclear region, and a feature point determined in the fingerprint image.
The shaded area in the fingerprint image shown in this figure indicates an unclear area E1 whose sharpness is less than the threshold value. Further, the area not shaded indicates a clear area E2 whose sharpness is equal to or higher than the threshold value. In such a fingerprint image, local points surrounded by circles and squares in the image indicate feature points. Of the feature points, the feature points indicated by circles indicate the first feature point P1. Of the feature points, the feature points indicated by the square marks indicate the second feature point P2. The straight lines from the circles and squares indicate the extending direction of the ridges extending from each feature point.

図7は指紋画像において判定された隆線の安定度を示す図である。
図7で示す指紋画像は、鮮明領域E2において隆線の安定度(品質)の高い白部分の領域と、隆線の安定度が閾値より低い黒部分の領域を示している。ステップS103の処理の結果、指紋処理装置1は、このような図7で示す隆線の安定度の分布を示す画像を出力するようにしてもよい。
FIG. 7 is a diagram showing the stability of the ridge line determined in the fingerprint image.
The fingerprint image shown in FIG. 7 shows a region of a white portion where the stability (quality) of the ridge line is high and a region of a black portion where the stability of the ridge line is lower than the threshold value in the clear region E2. As a result of the processing in step S103, the fingerprint processing apparatus 1 may output such an image showing the distribution of the stability of the ridge line shown in FIG. 7.

照合処理部25は、特徴点検出部24の検出した各特徴点についての位置情報と延伸方向情報を用いて、各特徴点の代表度eval_pを算出する(ステップS105)。この代表度は、指紋画像において特定された特徴点のうち、他の特徴点から離れているほど値が大きい度数である。代表度eval_pは、指紋画像において特定された特徴点のうち、他の特徴点からの距離が長く、鮮明度が高いことを示す度数であってよい。 The collation processing unit 25 calculates the representative degree equal_p of each feature point by using the position information and the stretching direction information for each feature point detected by the feature point detection unit 24 (step S105). This representative degree is a frequency having a larger value as the distance from the other feature points among the feature points specified in the fingerprint image increases. The representative degree equal_p may be a frequency indicating that, among the feature points specified in the fingerprint image, the distance from the other feature points is long and the sharpness is high.

図8は代表度算出フローを示す図である。
照合処理部25は、代表度eval_pの算出においては、まず、特徴点検出部24の検出した各特徴点についての位置情報と延伸方向情報をRAM12から取得する。照合処理部25は各特徴点の中から一つの選択特徴点を選択し、その選択特徴点と他の全ての特徴点の距離を算出する(ステップS1051)。照合処理部25は算出した複数の距離のうち最も値の小さい距離の情報を、選択特徴点の最近傍特徴点までの距離Lmp(第一度合)と決定する(ステップS1052)。
FIG. 8 is a diagram showing a representativeness calculation flow.
In the calculation of the representative degree equal_p, the collation processing unit 25 first acquires the position information and the stretching direction information for each feature point detected by the feature point detection unit 24 from the RAM 12. The collation processing unit 25 selects one selected feature point from each feature point, and calculates the distance between the selected feature point and all the other feature points (step S1051). The collation processing unit 25 determines the information of the distance having the smallest value among the calculated plurality of distances as the distance Lmp (first combination) to the nearest feature point of the selected feature point (step S1052).

照合処理部25は次に、選択特徴点の位置情報と不鮮明領域E1を示す全ての矩形領域の位置情報とを用いて、それらの距離を算出する(ステップS1053)。照合処理部25は算出したその距離のうち最も値の小さい距離の情報を、選択特徴点の最近傍の不鮮明領域E1を示す矩形領域までの距離ucz(第一度合)と決定する(ステップS1054)。また照合処理部25は選択特徴点に対応する画素の隆線の安定度mRqlの情報をRAM12から取得する。そして選択特徴点の代表度eval_pを式(1)により算出する(ステップS1055)。 Next, the collation processing unit 25 calculates the distance between the selected feature points using the position information and the position information of all the rectangular areas indicating the unclear area E1 (step S1053). The collation processing unit 25 determines the information of the distance having the smallest value among the calculated distances as the distance ucci (first combination) to the rectangular region indicating the unclear region E1 closest to the selected feature point (step S1054). ). Further, the collation processing unit 25 acquires information on the stability mRql of the ridges of the pixels corresponding to the selected feature points from the RAM 12. Then, the representativeness equal_p of the selected feature points is calculated by the equation (1) (step S1055).

Figure 2022060505000002
Figure 2022060505000002

式(1)においてA,Bは定数を示している。また式(1)中の「/」は除算(÷)を意味する。定数Aは、選択特徴点の最近傍特徴点までの距離Lmpと、選択特徴点の最近傍の不鮮明領域E1を示す矩形領域までの距離uczとを乗じた値が大きくなりすぎないよう調整するための定数である。定数Bは選択特徴点に対応する画素の隆線の安定度mRqlの値を調整するための定数である。式(1)により、選択特徴点が、他の特徴点からの距離と鮮明度とが高いか否かの度数を示す代表度eval_pを算出することができる。なお、式(1)のように選択特徴点の最近傍の不鮮明領域E1を示す矩形領域までの距離uczを用いて代表度eval_pを算出することにより、不鮮明領域E1に他の特徴点が存在する場合を想定した代表度eval_pの算出を行うことができる。式(1)においては選択特徴点に対応する画素の隆線の安定度mRqlに関する情報を加えているが、この情報を加えない態様で、代表度eval_pが算出されてもよい。また式(1)においては選択特徴点の最近傍の不鮮明領域E1を示す矩形領域までの距離uczの情報を加えているが、この情報を加えない態様で、代表度eval_pが算出されてもよい。 In equation (1), A and B represent constants. Further, "/" in the equation (1) means division (÷). The constant A is adjusted so that the value obtained by multiplying the distance Lmp to the nearest feature point of the selected feature point and the distance ucci to the rectangular region indicating the unclear region E1 closest to the selected feature point does not become too large. Is a constant of. The constant B is a constant for adjusting the value of the stability mRql of the ridge of the pixel corresponding to the selected feature point. From the equation (1), it is possible to calculate the representative degree equal_p indicating the frequency of whether or not the selected feature point has a high distance from other feature points and a high sharpness. It should be noted that there are other feature points in the unclear region E1 by calculating the representativeness equal_p using the distance ucci to the rectangular region indicating the unclear region E1 closest to the selected feature point as in the equation (1). It is possible to calculate the representativeness equal_p assuming a case. In the formula (1), the information regarding the stability mRql of the ridge of the pixel corresponding to the selected feature point is added, but the representative degree equal_p may be calculated in a mode in which this information is not added. Further, in the equation (1), the information of the distance ucci to the rectangular region indicating the unclear region E1 in the nearest neighbor of the selected feature point is added, but the representative degree equal_p may be calculated in a mode in which this information is not added. ..

照合処理部25は指紋画像に現れる全ての特徴点について選択特徴点として代表度eval_pの算出処理を行ったかを判定する(ステップS106)。照合処理部25は指紋画像に現れる全ての特徴点について選択特徴点として代表度eval_pの算出処理が終わるまで代表度eval_pの算出を繰り返す。照合処理部25は、全ての特徴点について算出した代表度eval_pを大きい順に探索し、代表度eval_pの大きい複数の所定数の特徴点を、代表特徴点と特定する(ステップS107)。所定数は例えば20や30などの数であってよい。 The collation processing unit 25 determines whether or not the calculation processing of the representative degree equal_p has been performed as the selected feature points for all the feature points appearing in the fingerprint image (step S106). The collation processing unit 25 repeats the calculation of the representative degree equal_p as the selected feature points for all the feature points appearing in the fingerprint image until the calculation process of the representative degree equal_p is completed. The collation processing unit 25 searches for the representative degree equal_p calculated for all the feature points in descending order, and identifies a plurality of predetermined number of feature points having a large representative degree equal_p as the representative feature points (step S107). The predetermined number may be, for example, a number such as 20 or 30.

図9は特徴点と代表特徴点を視覚的に示す図である。
図9で示すように指紋画像には多くの特徴点が検出される。照合処理部25は各特徴点の代表度eval_pを算出し、大きい順に選択した所定の数の特徴点を、代表特徴点と判定する。図9において特徴点を示す印を黒く表示している特徴点は代表度eval_pが高く、色の薄い印を示す特徴点は代表度eval_pが低いことを表している。
FIG. 9 is a diagram visually showing feature points and representative feature points.
As shown in FIG. 9, many feature points are detected in the fingerprint image. The collation processing unit 25 calculates the representative degree equal_p of each feature point, and determines that a predetermined number of feature points selected in descending order are representative feature points. In FIG. 9, the feature points showing the marks indicating the feature points in black indicate that the representative degree equal_p is high, and the feature points showing the light-colored marks indicate that the representative degree equal_p is low.

図10は代表特徴点の特徴量の特定概要を示す第一の図である。
図11は代表特徴点の特徴量を付与する処理フローを示す第一の図である。
照合処理部25は次に複数の代表特徴点にそれぞれ特徴量を付与する(ステップS108)。具体的には照合処理部25は、複数の代表特徴点のうち1つの代表特徴点を選択する(ステップS108-1)。この選択した代表特徴点を選択代表特徴点と呼ぶ。照合処理部25は選択代表特徴点についての位置情報と延伸方向情報(代表延伸方向)とをRAM12から読み取る。また照合処理部25は指紋画像中の他の特徴点の位置情報と延伸方向情報とをRAM12から読み取る。照合処理部25は選択代表特徴点についての延伸方向情報(代表延伸方向)が示す延伸方向を垂直軸のプラス方向と仮定して、選択代表特徴点を中心とし延伸方向情報に基づく垂直軸を基準として指紋画像平面上の360度方向を45度角毎に分割した第一象限~第八象限までの分割領域を特定する(ステップS108-2)。
FIG. 10 is a first diagram showing a specific outline of the feature amount of the representative feature point.
FIG. 11 is a first diagram showing a processing flow for imparting a feature amount of a representative feature point.
Next, the collation processing unit 25 assigns a feature amount to each of the plurality of representative feature points (step S108). Specifically, the collation processing unit 25 selects one representative feature point from the plurality of representative feature points (step S108-1). This selected representative feature point is called a selected representative feature point. The collation processing unit 25 reads the position information and the stretching direction information (representative stretching direction) about the selected representative feature points from the RAM 12. Further, the collation processing unit 25 reads the position information and the stretching direction information of other feature points in the fingerprint image from the RAM 12. The collation processing unit 25 assumes that the stretching direction indicated by the stretching direction information (representative stretching direction) for the selected representative feature point is the plus direction of the vertical axis, and refers to the vertical axis based on the stretching direction information centering on the selected representative feature point. As a result, the divided region from the first quadrant to the eighth quadrant obtained by dividing the 360-degree direction on the fingerprint image plane into 45-degree angles is specified (step S108-2).

今、照合処理部25は図10において1番の符号が振られている代表特徴点を選択代表特徴点と設定しているものとする。この場合、図10において1番の選択代表特徴点を原点として延伸方向情報が示す延伸方向に延びる軸を軸aと呼ぶ。1番の選択代表特徴点を中心に軸aから45度左に回転した軸を軸bと呼ぶ。1番の選択代表特徴点を中心に軸bから45度左に回転した軸を軸cと呼ぶ。1番の選択代表特徴点を中心に軸cから45度左に回転した軸を軸dと呼ぶ。1番の選択代表特徴点を中心に軸dから45度左に回転した軸を軸eと呼ぶ。1番の選択代表特徴点を中心に軸eから45度左に回転した軸を軸fと呼ぶ。1番の選択代表特徴点を中心に軸fから45度左に回転した軸を軸gと呼ぶ。1番の選択代表特徴点を中心に軸gから45度左に回転した軸を軸hと呼ぶ。 Now, it is assumed that the collation processing unit 25 sets the representative feature point to which the first reference numeral is assigned in FIG. 10 as the selected representative feature point. In this case, the axis extending in the stretching direction indicated by the stretching direction information with the first selected representative feature point as the origin in FIG. 10 is referred to as a shaft a. The axis rotated 45 degrees to the left from the axis a around the first selected representative feature point is called the axis b. The axis rotated 45 degrees to the left from the axis b around the first selected representative feature point is called the axis c. The axis rotated 45 degrees to the left from the axis c around the first selected representative feature point is called the axis d. The axis rotated 45 degrees to the left from the axis d around the first selected representative feature point is called the axis e. The axis rotated 45 degrees to the left from the axis e around the first selected representative feature point is called the axis f. The axis rotated 45 degrees to the left from the axis f around the first selected representative feature point is called the axis g. The axis rotated 45 degrees to the left from the axis g around the first selected representative feature point is called the axis h.

照合処理部25は軸aと軸bとの間の第一象限において1番の選択代表特徴点から最も距離の近い9番の特徴点を特定する(ステップS108-3)。また照合処理部25は軸bと軸cとの間の第二象限において1番の選択代表特徴点から最も距離の近い17番の特徴点を特定する。同様に照合処理部25は各軸で分割された第三象限~第八象限において1番の選択代表特徴点から最も距離の近い特徴点を特定する。照合処理部25は、第一象限から第八象限において特定した各特徴点までの1番の選択代表特徴点からの距離と、第一象限から第八象限において特定した各特徴点についての延伸方向情報と、1番の選択代表特徴点について算出した代表度との全てを、1番の選択代表特徴点の特徴量を決定する(ステップS108-4)。照合処理部25は全ての代表特徴点について特徴量を特定したかを判定する(ステップS108-5)。照合処理部25は全ての代表特徴点について特徴量を特定していない場合には特徴量の特定の処理を繰り返す。 The collation processing unit 25 identifies the ninth feature point closest to the first selected representative feature point in the first quadrant between the axes a and b (step S108-3). Further, the collation processing unit 25 identifies the 17th feature point closest to the 1st selected representative feature point in the second quadrant between the axis b and the axis c. Similarly, the collation processing unit 25 identifies the feature point closest to the first selected representative feature point in the third quadrant to the eighth quadrant divided by each axis. The collation processing unit 25 determines the distance from the first selected representative feature point from the first quadrant to each feature point specified in the eighth quadrant, and the stretching direction for each feature point specified in the first quadrant to the eighth quadrant. All of the information and the representativeness calculated for the first selected representative feature point are used to determine the feature amount of the first selected representative feature point (step S108-4). The collation processing unit 25 determines whether or not the feature quantities have been specified for all the representative feature points (step S108-5). When the feature amount is not specified for all the representative feature points, the collation processing unit 25 repeats the process of specifying the feature amount.

照合処理部25は、全ての代表特徴点についての特徴量を特定すると、それら全ての代表特徴点についての特徴量から成る情報を、指紋読取機2から取得した指紋画像についての指紋特徴量と決定する(ステップS109)。指紋読取機2から取得した指紋画像を以下、認証指紋画像と呼ぶ。照合処理部25はデータベース3に記録されている1つ目の指紋画像の指紋特徴量を読み取る。データベース3に記録されている指紋画像を、以下探索先指紋画像と呼ぶ。探索先指紋画像の指紋特徴量は、認証指紋画像の指紋特徴量の算出と同様に算出された特徴量である。照合処理部25は、認証指紋画像の指紋特徴量と探索先指紋画像の指紋特徴量とを用いて類似度を計算する(ステップS110)。類似度の計算は照合処理の一態様である。 When the collation processing unit 25 specifies the feature amounts for all the representative feature points, the collation processing unit 25 determines the information consisting of the feature amounts for all the representative feature points as the fingerprint feature amount for the fingerprint image acquired from the fingerprint reader 2. (Step S109). The fingerprint image acquired from the fingerprint reader 2 is hereinafter referred to as an authenticated fingerprint image. The collation processing unit 25 reads the fingerprint feature amount of the first fingerprint image recorded in the database 3. The fingerprint image recorded in the database 3 is hereinafter referred to as a search destination fingerprint image. The fingerprint feature amount of the search destination fingerprint image is a feature amount calculated in the same manner as the calculation of the fingerprint feature amount of the authenticated fingerprint image. The collation processing unit 25 calculates the similarity using the fingerprint feature amount of the authenticated fingerprint image and the fingerprint feature amount of the search destination fingerprint image (step S110). The calculation of similarity is one aspect of the collation process.

図12は指紋特徴量に基づく類似度の計算概要を示す第一の図である。
図12に示すように、照合処理部25は認証指紋画像において特定した複数の代表特徴点それぞれについて、代表度と、第一象限~第八象限において特定した最近傍特徴点までの距離と、当該最近傍特徴点から延びる隆線の延伸方向を示す延伸方向情報と、から成る指紋特徴量の情報をRAM12に記録している。データベース3に記録される複数の探索先指紋画像も同様の指紋特徴量の情報から構成される。
FIG. 12 is a first diagram showing an outline of calculation of similarity based on fingerprint features.
As shown in FIG. 12, the collation processing unit 25 describes the representativeness, the distance to the nearest feature point specified in the first quadrant to the eighth quadrant, and the corresponding representative feature points for each of the plurality of representative feature points specified in the authenticated fingerprint image. The RAM 12 records information on the extension direction indicating the extension direction of the ridge extending from the nearest feature point and information on the fingerprint feature amount including the extension direction information. The plurality of search destination fingerprint images recorded in the database 3 are also composed of information on the same fingerprint feature amount.

照合処理部25は、認証指紋画像側の各代表特徴点と、探索先指紋画像の各代表特徴点との差分を総当たりで算出する。認証指紋画像側の1つの代表特徴点と探索先指紋画像の1つの代表特徴点との差分を計算する場合には、対応する同一象限について、最近傍特徴点までの距離の差と、延伸方向情報が示す方向の差のそれぞれに認証指紋画像側の代表度を乗じた上で加算した値を算出し、その値の八象限分の累積値を求める。この値が認証指紋画像側の1つの代表特徴点と探索先指紋画像の1つの代表特徴点との差分である。 The collation processing unit 25 calculates the difference between each representative feature point on the authenticated fingerprint image side and each representative feature point on the search destination fingerprint image in a round-robin manner. When calculating the difference between one representative feature point on the authenticated fingerprint image side and one representative feature point on the searched fingerprint image, the difference in distance to the nearest feature point and the stretching direction for the corresponding same quadrant. Calculate the value obtained by multiplying each difference in the direction indicated by the information by the representative degree on the authentication fingerprint image side, and obtain the cumulative value for eight quadrants of that value. This value is the difference between one representative feature point on the authenticated fingerprint image side and one representative feature point on the search destination fingerprint image.

認証指紋画像において特定した代表特徴点を1~n、探索先指紋画像において特定されている代表特徴点を1~Nとすると、照合処理部25は認証指紋画像における1つの代表特徴点と探索先指紋画像における各代表特徴点との差分をそれぞれ算出する。
照合処理部25は認証指紋画像における1つの代表特徴点を代表特徴点1とすると、その認証指紋画像における代表特徴点1と、探索先指紋画像の代表特徴点1~Nそれぞれとの差分S(11,12,…1N)を算出する。
照合処理部25は算出したそれらの差分Sのうち、最も差分Sの小さい探索先指紋画像の代表特徴点を特定する。この処理により照合処理部25は認証指紋画像において特定した1つの代表特徴点1に近い、探索指紋画像に含まれる代表特徴点を特定できる。
照合処理部25は、認証指紋画像における全ての代表特徴点(1~n)について、探索先指紋画像中の差分Sの小さい代表特徴点を特定する。
照合処理部25は認証指紋画像における代表特徴点(1~n)それぞれについて特定した探索先指紋画像中の代表特徴点との間の差分Sを小さい順にソートして、小さい順に一定数(2~4)の値の平均を算出する。照合処理部25は、その平均値を定数から減算することで、認証指紋画像と探索先指紋画像との間の類似度を算出する。類似度の高い探索指紋画像の値は、定数からの減算の値が小さいため、その値は高くなる。
Assuming that the representative feature points specified in the authenticated fingerprint image are 1 to n and the representative feature points specified in the search destination fingerprint image are 1 to N, the collation processing unit 25 has one representative feature point and the search destination in the authenticated fingerprint image. The difference from each representative feature point in the fingerprint image is calculated.
Assuming that one representative feature point in the authenticated fingerprint image is the representative feature point 1, the collation processing unit 25 sets the difference S between the representative feature point 1 in the authenticated fingerprint image and the representative feature points 1 to N of the search destination fingerprint image. 11, 12, ... 1N) is calculated.
The collation processing unit 25 identifies a representative feature point of the search destination fingerprint image having the smallest difference S among the calculated differences S. By this processing, the collation processing unit 25 can specify a representative feature point included in the search fingerprint image, which is close to one representative feature point 1 specified in the authenticated fingerprint image.
The collation processing unit 25 identifies the representative feature points having a small difference S in the search destination fingerprint image for all the representative feature points (1 to n) in the authenticated fingerprint image.
The collation processing unit 25 sorts the difference S between the representative feature points (1 to n) in the authenticated fingerprint image and the representative feature points in the search destination fingerprint image specified in ascending order, and sets a fixed number (2 to 2) in ascending order. Calculate the average of the values in 4). The collation processing unit 25 calculates the degree of similarity between the authenticated fingerprint image and the search destination fingerprint image by subtracting the average value from the constant. The value of the search fingerprint image having a high degree of similarity is high because the value of subtraction from the constant is small.

照合処理部25は、データベース3に含まれる全ての探索先指紋画像を用いて、認証指紋画像との類似度を算出する。照合処理部25は類似度が基準閾値より高い探索先指紋画像を、認証指紋画像との間でより詳細に照合判定を行う照合候補と決定する(ステップS111)。照合処理部25は、認証指紋画像と照合候補と決定した探索先指紋画像との間の照合を、各指紋画像に含まれる特徴点を用いて行う(ステップS112)。当該照合の処理は特徴点を用いて照合判定を行う公知の技術を用いてよい。照合処理部25は、照合判定の結果、基準値よりも類似度の高い探索先指紋画像のうち、最も類似度の高い探索先指紋画像を認証指紋画像に一致する指紋画像と判定して出力する(ステップS113)。照合処理部25は、照合判定の結果、類似度の高い探索先指紋画像を検索できない場合には、一致無を示す情報を出力する(ステップS114)。 The collation processing unit 25 calculates the degree of similarity with the authenticated fingerprint image by using all the search destination fingerprint images included in the database 3. The collation processing unit 25 determines the search destination fingerprint image having a similarity higher than the reference threshold value as a collation candidate for performing a collation determination with the authentication fingerprint image in more detail (step S111). The collation processing unit 25 performs collation between the authenticated fingerprint image and the search destination fingerprint image determined as the collation candidate by using the feature points included in each fingerprint image (step S112). The collation process may use a known technique for performing collation determination using feature points. As a result of the collation determination, the collation processing unit 25 determines and outputs the search destination fingerprint image having the highest similarity among the search destination fingerprint images having a higher similarity than the reference value as the fingerprint image matching the authenticated fingerprint image. (Step S113). The collation processing unit 25 outputs information indicating no match when the search destination fingerprint image having a high degree of similarity cannot be searched as a result of the collation determination (step S114).

上述の処理を簡略して説明すると、まず、照合処理部25は、複数の代表特徴点から抽出した一つの抽出代表特徴点について、当該抽出代表特徴点から延びる指紋の隆線の代表延伸方向を特定する。また照合処理部25は、抽出代表特徴点に基づいて決定した近傍特徴点までの距離と、当該近傍特徴点から延びる指紋の隆線の代表延伸方向を基準とした延伸方向と、当該近傍特徴点の代表度とに基づいて決定される特徴量を抽出代表特徴点に付与する。そして照合処理部25は、抽出代表特徴点それぞれに同様に付与した特徴量を用いて、照合元の指紋画像(認証指紋画像)におけるそれら複数の代表特徴点と、照合先の指紋画像(探索先指紋画像)における複数の代表特徴点とによる指紋の照合処理を行う。 Briefly explaining the above processing, first, the collation processing unit 25 determines the representative extension direction of the ridge of the fingerprint extending from the extraction representative feature point for one extraction representative feature point extracted from the plurality of representative feature points. Identify. Further, the collation processing unit 25 has a distance to a nearby feature point determined based on the extraction representative feature point, an extension direction based on the representative extension direction of the fingerprint ridge extending from the vicinity feature point, and the vicinity feature point. The feature amount determined based on the representativeness of is given to the extracted representative feature points. Then, the collation processing unit 25 uses the feature amounts similarly assigned to each of the extracted representative feature points, and uses the plurality of representative feature points in the fingerprint image (authentication fingerprint image) of the collation source and the fingerprint image (search destination) of the collation destination. Performs fingerprint collation processing with a plurality of representative feature points in the fingerprint image).

図13は代表特徴点の特徴量の特定概要を示す第二の図である。
図14は代表特徴点の特徴量の特定概要を示す第三の図である。
図15は代表特徴点の特徴量を付与する処理フローを示す第二の図である。
照合処理部25は、図10~図12を用いて説明した処理以外の方法で、照合候補の探索先指紋画像を特定するようにしてもよい。
照合処理部25は複数の代表特徴点にそれぞれ特徴量を付与する(ステップS108)。具体的には照合処理部25は、複数の代表特徴点のうち1つの代表特徴点を選択する(ステップS108-11)。図13においては符号1で示す代表特徴点を選択代表特徴点としている。この選択した代表特徴点を選択代表特徴点と呼ぶ。照合処理部25は選択代表特徴点についての位置情報と延伸方向情報とをRAM12から読み取る。照合処理部25は指紋画像中の他の特徴点(代表特徴点以外の特徴点も含む)の位置情報と延伸方向情報とをRAM12から読み取る。照合処理部25は選択代表特徴点についての延伸方向情報が示す延伸方向を垂直軸のプラス方向と仮定して、他の特徴点の延伸方向が垂直軸の延伸方向に逆向きとなる特徴点の近傍の画素を白色、他の特徴点の延伸方向が垂直軸の延伸方向に同一方向となる特徴点の近傍の画素を黒色とした隆線延伸方向判定画像(図13)を生成する(ステップS108-12)。隆線延伸方向判定画像において黒色や白色と特定されていない画像については、近傍の他の画素の色(画素値)に基づいて、補間された色の値が算出されて、黒色から白色までの階調の値のうちの何れかの階調の画素値を有するようにしてもよい。図13において選択代表特徴点1の隆線の延伸方向と同一方向の延伸方向となっている特徴点50についてはその周囲が黒色の画素となっていることが分かる。また図13において選択代表特徴点1の隆線の延伸方向と逆方向の延伸方向となっている特徴点9や特徴点6についてはその周囲が白色の画素となっていることが分かる。
FIG. 13 is a second diagram showing a specific outline of the feature amount of the representative feature point.
FIG. 14 is a third diagram showing a specific outline of the feature amount of the representative feature point.
FIG. 15 is a second diagram showing a processing flow for imparting a feature amount of a representative feature point.
The collation processing unit 25 may specify the search destination fingerprint image of the collation candidate by a method other than the processing described with reference to FIGS. 10 to 12.
The collation processing unit 25 assigns a feature amount to each of the plurality of representative feature points (step S108). Specifically, the collation processing unit 25 selects one representative feature point from the plurality of representative feature points (step S108-11). In FIG. 13, the representative feature point indicated by reference numeral 1 is used as the selected representative feature point. This selected representative feature point is called a selected representative feature point. The collation processing unit 25 reads the position information and the stretching direction information about the selected representative feature points from the RAM 12. The collation processing unit 25 reads the position information and the stretching direction information of other feature points (including feature points other than the representative feature points) in the fingerprint image from the RAM 12. The collation processing unit 25 assumes that the stretching direction indicated by the stretching direction information for the selected representative feature point is the plus direction of the vertical axis, and the stretching direction of the other feature points is opposite to the stretching direction of the vertical axis. A ridge stretching direction determination image (FIG. 13) is generated (step S108) in which the pixels in the vicinity are white and the pixels in the vicinity of the feature points whose stretching directions of the other feature points are in the same direction as the stretching direction of the vertical axis are black. -12). For an image that is not specified as black or white in the ridge extension direction determination image, the interpolated color value is calculated based on the color (pixel value) of other pixels in the vicinity, and the color is from black to white. It may have a pixel value of any gradation among the gradation values. In FIG. 13, it can be seen that the periphery of the feature point 50, which has a stretching direction in the same direction as the stretching direction of the ridge of the selected representative feature point 1, is a black pixel. Further, in FIG. 13, it can be seen that the surroundings of the feature points 9 and the feature points 6 which are in the stretching direction in the direction opposite to the stretching direction of the ridge of the selected representative feature point 1 are white pixels.

照合処理部25は、選択代表特徴点1について生成した隆線延伸方向判定画像(図13)において、選択代表特徴点1の位置を中心とした24点の特徴抽出点の画素値を抽出する(ステップS108-13)。図14には選択代表特徴点1の位置を中心とした24点の特徴抽出点(1)~(24)の位置を図示している。照合処理部25は、特徴抽出点(1)~(24)の画素値を並べた値と、代表特徴点について算出した隆線の安定度とを示す情報を、選択代表特徴点1の指紋特徴量と決定する(ステップS108-14)。照合処理部25は全ての代表特徴点について指紋特徴量を算出したかを判定する(ステップS108-15)。照合処理部25は全ての代表特徴点について指紋特徴量を算出していない場合には他の代表特徴点について同様の手法により指紋特徴量を生成する。 The collation processing unit 25 extracts the pixel values of the 24 feature extraction points centered on the position of the selected representative feature point 1 in the ridge extension direction determination image (FIG. 13) generated for the selected representative feature point 1 (FIG. 13). Step S108-13). FIG. 14 illustrates the positions of 24 feature extraction points (1) to (24) centered on the position of the selected representative feature point 1. The collation processing unit 25 selects the fingerprint feature of the selected representative feature point 1 with information indicating the value obtained by arranging the pixel values of the feature extraction points (1) to (24) and the stability of the ridge line calculated for the representative feature point. The amount is determined (step S108-14). The collation processing unit 25 determines whether the fingerprint feature amount has been calculated for all the representative feature points (step S108-15). When the collation processing unit 25 has not calculated the fingerprint feature amount for all the representative feature points, the collation processing unit 25 generates the fingerprint feature amount for the other representative feature points by the same method.

照合処理部25は、認証指紋画像において特定した全ての代表特徴点についての指紋特徴量を算出すると、それら全ての代表特徴点についての指紋特徴量から成る情報を、認証指紋画像についての指紋特徴量と決定する(ステップS109)。探索先指紋画像の指紋特徴量は、認証指紋画像の指紋特徴量の算出と同様に算出された特徴量である。認証指紋画像における代表特徴点の位置と特徴抽出点(1)~(24)の位置との関係と、探索先指紋画像における代表特徴点の位置と特徴抽出点(1)~(24)の位置との関係とは同じである。照合処理部25は、認証指紋画像の指紋特徴量と探索先指紋画像の指紋特徴量とを用いて類似度を計算する(ステップS110)。 When the collation processing unit 25 calculates the fingerprint feature amount for all the representative feature points specified in the authenticated fingerprint image, the collation processing unit 25 obtains the information consisting of the fingerprint feature amount for all the representative feature points and the fingerprint feature amount for the authenticated fingerprint image. Is determined (step S109). The fingerprint feature amount of the search destination fingerprint image is a feature amount calculated in the same manner as the calculation of the fingerprint feature amount of the authenticated fingerprint image. The relationship between the position of the representative feature point in the authenticated fingerprint image and the position of the feature extraction points (1) to (24), the position of the representative feature point in the search destination fingerprint image, and the position of the feature extraction points (1) to (24). The relationship with is the same. The collation processing unit 25 calculates the similarity using the fingerprint feature amount of the authenticated fingerprint image and the fingerprint feature amount of the search destination fingerprint image (step S110).

図16は指紋特徴量に基づく類似度の計算概要を示す第二の図である。
この図が示すように認証指紋画像の指紋特徴量には、多くの特徴点の中から特定した複数の代表特徴点に対応する画素(又は矩形領域)における隆線の安定度(隆線品質)と、その代表特徴点を基準とした周囲の特徴抽出点(1)~(24)の画素値が含まれる。データベース3に記録される複数の探索先指紋画像も同様の指紋特徴量の情報から構成される。
FIG. 16 is a second diagram showing an outline of calculation of similarity based on fingerprint features.
As shown in this figure, the fingerprint feature amount of the authenticated fingerprint image includes the stability (ridge quality) of the ridge in the pixel (or rectangular area) corresponding to a plurality of representative feature points specified from many feature points. And the pixel values of the surrounding feature extraction points (1) to (24) with respect to the representative feature point are included. The plurality of search destination fingerprint images recorded in the database 3 are also composed of information on the same fingerprint feature amount.

照合処理部25は、認証指紋画像側の各代表特徴点と、探索先指紋画像の各代表特徴点との差分を総当たりで算出する。認証指紋画像側の1つの代表特徴点と探索先指紋画像の1つの代表特徴点との差分Sを計算する場合には、対応する特徴抽出点の画素値の差に、認証指紋画像の隆線の安定度を乗じた値を、24の特徴抽出点それぞれについて算出し累積する。この値が認証指紋画像側の1つの代表特徴点と探索先指紋画像の1つの代表特徴点との差分Sである。 The collation processing unit 25 calculates the difference between each representative feature point on the authenticated fingerprint image side and each representative feature point on the search destination fingerprint image in a round-robin manner. When calculating the difference S between one representative feature point on the authenticated fingerprint image side and one representative feature point on the searched fingerprint image, the difference S in the pixel values of the corresponding feature extraction points is the ridge of the authenticated fingerprint image. The value multiplied by the stability of is calculated and accumulated for each of the 24 feature extraction points. This value is the difference S between one representative feature point on the authenticated fingerprint image side and one representative feature point on the search destination fingerprint image.

認証指紋画像において特定した代表特徴点を1~n、探索先指紋画像において特定されている代表特徴点を1~Nとすると、照合処理部25は認証指紋画像における1つの代表特徴点と探索先指紋画像における各代表特徴点との差分Sをそれぞれ算出する。
照合処理部25は認証指紋画像における1つの代表特徴点を代表特徴点1とすると、その認証指紋画像における代表特徴点1と、探索先指紋画像の代表特徴点1~Nそれぞれとの差分S(11,12,…1N)を算出する。
照合処理部25は算出したそれらの差分Sのうち、最も差分Sの小さい探索先指紋画像の代表特徴点を特定する。この処理により照合処理部25は認証指紋画像において特定した1つの代表特徴点1に近い、探索指紋画像に含まれる代表特徴点を特定できる。
照合処理部25は、認証指紋画像における全ての代表特徴点(1~n)について、探索先指紋画像中の差分Sの小さい代表特徴点を特定する。
照合処理部25は認証指紋画像における代表特徴点(1~n)それぞれについて特定した探索先指紋画像中の代表特徴点との間の差分Sを小さい順にソートして、小さい順に一定数(2~4)の値の平均を算出する。照合処理部25は、その平均値を定数から減算することで、認証指紋画像と探索先指紋画像との間の類似度を算出する。類似度の高い探索指紋画像の値は、定数からの減算の値が小さいため、その値は高くなる。
Assuming that the representative feature points specified in the authenticated fingerprint image are 1 to n and the representative feature points specified in the search destination fingerprint image are 1 to N, the collation processing unit 25 has one representative feature point and the search destination in the authenticated fingerprint image. The difference S from each representative feature point in the fingerprint image is calculated.
Assuming that one representative feature point in the authenticated fingerprint image is the representative feature point 1, the collation processing unit 25 sets the difference S between the representative feature point 1 in the authenticated fingerprint image and the representative feature points 1 to N of the search destination fingerprint image. 11, 12, ... 1N) is calculated.
The collation processing unit 25 identifies a representative feature point of the search destination fingerprint image having the smallest difference S among the calculated differences S. By this processing, the collation processing unit 25 can specify a representative feature point included in the search fingerprint image, which is close to one representative feature point 1 specified in the authenticated fingerprint image.
The collation processing unit 25 identifies the representative feature points having a small difference S in the search destination fingerprint image for all the representative feature points (1 to n) in the authenticated fingerprint image.
The collation processing unit 25 sorts the difference S between the representative feature points (1 to n) in the authenticated fingerprint image and the representative feature points in the search destination fingerprint image specified in ascending order, and sets a fixed number (2 to 2) in ascending order. Calculate the average of the values in 4). The collation processing unit 25 calculates the degree of similarity between the authenticated fingerprint image and the search destination fingerprint image by subtracting the average value from the constant. The value of the search fingerprint image having a high degree of similarity is high because the value of subtraction from the constant is small.

照合処理部25は、データベース3に含まれる全ての探索先指紋画像を用いて、認証指紋画像との類似度を算出する。照合処理部25は類似度が基準閾値より高い探索先指紋画像を、認証指紋画像との間でより詳細に照合判定を行う照合候補と決定する(ステップS111)。照合処理部25は、認証指紋画像と照合候補と決定した探索先指紋画像との間の照合を、各指紋画像に含まれる特徴点を用いて行う。当該照合の処理は特徴点を用いて照合判定を行う公知の技術を用いてよい。照合処理部25は、照合判定の結果、最も類似度の高い探索先指紋画像を認証指紋画像に一致する指紋画像と判定する(ステップS112)。照合処理部25は、照合判定の結果、類似度の高い探索先指紋画像を検索できない場合には、一致無を示す情報を出力する(ステップS113)。 The collation processing unit 25 calculates the degree of similarity with the authenticated fingerprint image by using all the search destination fingerprint images included in the database 3. The collation processing unit 25 determines the search destination fingerprint image having a similarity higher than the reference threshold value as a collation candidate for performing a collation determination with the authentication fingerprint image in more detail (step S111). The collation processing unit 25 performs collation between the authenticated fingerprint image and the search destination fingerprint image determined as the collation candidate by using the feature points included in each fingerprint image. The collation process may use a known technique for performing collation determination using feature points. As a result of the collation determination, the collation processing unit 25 determines that the search destination fingerprint image having the highest similarity is a fingerprint image that matches the authentication fingerprint image (step S112). The collation processing unit 25 outputs information indicating no match when the search destination fingerprint image having a high degree of similarity cannot be searched as a result of the collation determination (step S113).

上述の処理を簡略して説明すると、まず、照合処理部25は、複数の前記代表特徴点から抽出した一つの抽出代表特徴点について、当該抽出代表特徴点から延びる指紋の隆線の代表延伸方向を特定する。次に照合処理部25は、抽出代表特徴点に基づいて決定した近傍特徴点から延びる指紋の隆線の代表延伸方向を基準とした延伸方向と、代表延伸方向との一致度が高いことを示す当該近傍特徴点の画素値と、代表延伸方向との一致度が低いことを示す当該近傍特徴点の画素値とを示す隆線延伸方向判定画像を生成する。そして照合処理部25は、隆線延伸方向判定画像において対応する抽出代表特徴点の位置を基準とした所定位置の複数の画素値を示す特徴量を代表特徴点に付与する。照合処理部25は、代表特徴点それぞれに同様に付与した特徴量を用いて、照合元の指紋画像におけるそれら複数の代表特徴点と、照合先の指紋画像における複数の代表特徴点とによる指紋の照合処理を行う。 Briefly explaining the above-mentioned processing, first, the collation processing unit 25 first, with respect to one extraction representative feature point extracted from the plurality of representative feature points, the representative extension direction of the ridge of the fingerprint extending from the extraction representative feature point. To identify. Next, the collation processing unit 25 shows that the degree of coincidence between the stretching direction based on the representative stretching direction of the ridge of the fingerprint extending from the neighboring feature points determined based on the extraction representative feature points and the representative stretching direction is high. A ridge stretching direction determination image showing the pixel value of the neighborhood feature point and the pixel value of the neighborhood feature point indicating that the degree of coincidence with the representative stretching direction is low is generated. Then, the collation processing unit 25 imparts a feature amount indicating a plurality of pixel values at a predetermined position based on the position of the corresponding extraction representative feature point in the ridge extension direction determination image to the representative feature point. The collation processing unit 25 uses the feature amount similarly assigned to each of the representative feature points to obtain a fingerprint of the plurality of representative feature points in the fingerprint image of the collation source and the plurality of representative feature points in the fingerprint image of the collation destination. Perform collation processing.

以上本発明の実施形態について説明したが、上述の処理によれば、指紋の中心を特定することなく照合処理を行っているため、指紋の中心の特定精度を必要とせずに、照合処理を行うことができる。
また上述の照合候補の探索先指紋画像を決定する処理において簡易な四則演算とソート処理を利用し、また算出に用いる特徴点を代表特徴点や特徴抽出点などの少ない特徴点に限定している。これにより照合候補を決定する処理を軽減することができる。
また照合処理においても照合候補として特定した探索先指紋画像のみを用いて認証指紋画像との照合処理を行うため、処理を軽減することができる。
Although the embodiment of the present invention has been described above, according to the above-mentioned process, since the collation process is performed without specifying the center of the fingerprint, the collation process is performed without requiring the accuracy of specifying the center of the fingerprint. be able to.
In addition, simple four arithmetic operations and sorting processing are used in the process of determining the search destination fingerprint image of the above-mentioned collation candidate, and the feature points used for the calculation are limited to a few feature points such as representative feature points and feature extraction points. .. This can reduce the process of determining the collation candidate.
Further, in the collation process as well, since the collation process with the authenticated fingerprint image is performed using only the search destination fingerprint image specified as the collation candidate, the process can be reduced.

上述の説明において指紋処理装置1は、図10~図12を用いて説明した類似度の計算と、図13~図16を用いて説明した類似度の計算との何れかを行うものとして説明したが、両方の類似度の計算を行って、それぞれ類似度の高い照合候補を特定してもよい。 In the above description, the fingerprint processing apparatus 1 has been described as performing either the calculation of the similarity described with reference to FIGS. 10 to 12 and the calculation of the similarity described with reference to FIGS. 13 to 16. However, both similarity calculations may be performed to identify matching candidates with high similarity, respectively.

図17は指紋処理装置の最少構成を示す図である。
この図で示すように指紋処理装置1は少なくとも、照合元の指紋画像において特定した指紋の特徴点のうち、他の特徴点との間の距離が長いことを示す第一度合に基づいて当該第一度合の値が大きい複数の特徴点を、指紋照合に用いる代表特徴点と判定する照合処理部25を有している。
なお本実施形態による指紋処理装置1は、少なくとも上記の照合処理部25の機能を備えた照合処理回路であると定義されてもよい。
FIG. 17 is a diagram showing a minimum configuration of the fingerprint processing device.
As shown in this figure, the fingerprint processing device 1 is said to be at least based on the first case indicating that the distance between the feature points of the fingerprint specified in the fingerprint image of the collation source and the other feature points is long. It has a collation processing unit 25 for determining a plurality of feature points having a large first-order value as representative feature points used for fingerprint collation.
The fingerprint processing device 1 according to the present embodiment may be defined as a collation processing circuit having at least the function of the collation processing unit 25 described above.

上述の指紋処理装置1は内部に、コンピュータシステムを有している。そして、指紋処理装置1に上述した各処理を行わせるためのプログラムは、当該~装置のコンピュータ読み取り可能な記録媒体に記憶されており、このプログラムを~装置のコンピュータが読み出して実行することによって、上記処理が行われる。ここでコンピュータ読み取り可能な記録媒体とは、磁気ディスク、光磁気ディスク、CD-ROM、DVD-ROM、半導体メモリ等をいう。また、このコンピュータプログラムを通信回線によってコンピュータに配信し、この配信を受けたコンピュータが当該プログラムを実行するようにしても良い。 The fingerprint processing device 1 described above has a computer system inside. A program for causing the fingerprint processing device 1 to perform each of the above-described processes is stored in a computer-readable recording medium of the device, and the program is read and executed by the computer of the device. The above processing is performed. Here, the computer-readable recording medium means a magnetic disk, a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, or the like. Further, this computer program may be distributed to a computer via a communication line, and the computer receiving the distribution may execute the program.

また、上記プログラムは、前述した各処理部の機能の一部を実現するためのものであっても良い。さらに、前述した機能をコンピュータシステムにすでに記録されているプログラムとの組み合わせで実現できるもの、いわゆる差分ファイル(差分プログラム)であっても良い。 Further, the above program may be for realizing a part of the functions of the above-mentioned processing units. Further, a so-called difference file (difference program) may be used, which can realize the above-mentioned function in combination with a program already recorded in the computer system.

1・・・指紋処理装置
2・・・指紋読取機
3・・・データベース
11・・・CPU
12・・・RAM
13・・・ROM
14・・・SSD
15・・・通信モジュール
16・・・表示画面
17・・・IF(インタフェース)
21・・・画像取得部
22・・・鮮明度判定部
23・・・隆線品質判定部
24・・・特徴点検出部
25・・・照合処理部
1 ... Fingerprint processing device 2 ... Fingerprint reader 3 ... Database 11 ... CPU
12 ... RAM
13 ... ROM
14 ... SSD
15 ... Communication module 16 ... Display screen 17 ... IF (interface)
21 ... Image acquisition unit 22 ... Sharpness determination unit 23 ... Ridge quality determination unit 24 ... Feature point detection unit 25 ... Collation processing unit

Claims (12)

照合元の指紋画像において特定した指紋の複数の特徴点のうち、前記指紋画像において画像の鮮明さが不明な画素領域までの第一距離に基づき、前記指紋の照合処理に用いる代表特徴点を決定する照合処理部を有する、
指紋処理装置。
Of the plurality of feature points of the fingerprint specified in the fingerprint image of the collation source, the representative feature points used for the fingerprint collation process are determined based on the first distance to the pixel region where the sharpness of the image is unknown in the fingerprint image. Has a collation processing unit
Fingerprint processing device.
前記照合処理部は、前記複数の特徴点のうち、他の特徴点との第二距離に基づき、前記指紋の照合処理に用いる代表特徴点を決定する、
請求項1に記載の指紋処理装置。
The collation processing unit determines a representative feature point to be used for the fingerprint collation process based on the second distance from the other feature points among the plurality of feature points.
The fingerprint processing apparatus according to claim 1.
前記照合処理部は、前記第二距離のうち最小の距離を示す第二度合に基づく代表値が大きい方から順に選択された所定数の特徴点を、前記代表特徴点として決定する照合処理部を有する、
請求項2に記載の指紋処理装置。
The collation processing unit determines a predetermined number of feature points selected in order from the one having the largest representative value based on the second degree indicating the minimum distance among the second distances as the representative feature points. Have,
The fingerprint processing apparatus according to claim 2.
前記照合処理部は、前記第二度合に、前記第一距離が長いことを示す第一度合を乗じた値に基づいて代表度を算出し、当該代表度に基づいて前記代表特徴点を決定する
請求項3に記載の指紋処理装置。
The collation processing unit calculates the representative degree based on the value obtained by multiplying the second degree by the first degree indicating that the first distance is long, and determines the representative feature point based on the representative degree. The fingerprint processing apparatus according to claim 3.
前記照合処理部は、前記指紋画像において特定した指紋の特徴点に対応する画素における隆線の安定度合をさらに用いて代表度を算出し、当該代表度に基づいて前記代表特徴点を決定する
請求項1から4のいずれか一項に記載の指紋処理装置。
The collation processing unit further calculates the representativeness by using the stability of the ridge in the pixel corresponding to the characteristic point of the fingerprint specified in the fingerprint image, and determines the representative feature point based on the representativeness. The fingerprint processing apparatus according to any one of Items 1 to 4.
前記照合処理部は、前記代表度の高い特徴を示す複数の前記代表特徴点を特定し、前記照合元の指紋画像におけるそれら複数の代表特徴点と、照合先の指紋画像における複数の代表特徴点とを用いて照合処理を行う
請求項4または請求項5に記載の指紋処理装置。
The collation processing unit identifies a plurality of the representative feature points showing the features having a high degree of representativeness, the plurality of representative feature points in the fingerprint image of the collation source, and the plurality of representative feature points in the fingerprint image of the collation destination. The fingerprint processing apparatus according to claim 4 or 5, wherein collation processing is performed using and.
前記照合処理部は、複数の前記代表特徴点から抽出した一つの抽出代表特徴点について、当該抽出代表特徴点から延びる指紋の隆線の代表延伸方向を特定し、前記抽出代表特徴点に基づいて決定した近傍特徴点までの距離と、当該近傍特徴点から延びる指紋の隆線の前記代表延伸方向を基準とした延伸方向と、当該近傍特徴点の前記代表度とに基づいて決定される特徴量を付与し、前記代表特徴点それぞれに同様に付与した特徴量を用いて、前記照合元の指紋画像におけるそれら複数の代表特徴点と、照合先の指紋画像における複数の代表特徴点とによる指紋の照合処理を行う
請求項6に記載の指紋処理装置。
The collation processing unit specifies the representative extension direction of the ridge of the fingerprint extending from the extracted representative feature point for one extracted representative feature point extracted from the plurality of representative feature points, and is based on the extracted representative feature point. A feature amount determined based on the distance to the determined neighborhood feature point, the stretching direction based on the representative stretching direction of the fingerprint ridge extending from the neighborhood feature point, and the representativeness of the neighborhood feature point. And using the feature amount similarly assigned to each of the representative feature points, the fingerprint of the plurality of representative feature points in the fingerprint image of the collation source and the plurality of representative feature points in the fingerprint image of the collation destination. The fingerprint processing apparatus according to claim 6, which performs collation processing.
前記照合処理部は、前記近傍特徴点は前記抽出代表特徴点についての前記代表延伸方向を基準として前記抽出代表特徴点を原点とした8象限の領域それぞれにおける当該抽出代表特徴点に近傍の特徴点である
請求項7に記載の指紋処理装置。
In the collation processing unit, the neighborhood feature points are feature points in the vicinity of the extraction representative feature points in each of the eight quadrant regions with the extraction representative feature points as the origin with respect to the representative stretching direction of the extraction representative feature points. The fingerprint processing apparatus according to claim 7.
前記照合処理部は、複数の前記代表特徴点から抽出した一つの抽出代表特徴点について、当該抽出代表特徴点から延びる指紋の隆線の代表延伸方向を特定し、前記抽出代表特徴点に基づいて決定した近傍特徴点から延びる指紋の隆線の前記代表延伸方向を基準とした延伸方向と、前記代表延伸方向との一致度が高いことを示す当該近傍特徴点の画素値と、前記代表延伸方向との一致度が低いことを示す当該近傍特徴点の画素値とを示す隆線延伸方向判定画像を生成し、前記隆線延伸方向判定画像において対応する前記抽出代表特徴点の位置を基準とした所定位置の複数の画素値を示す特徴量を付与し、前記代表特徴点それぞれに同様に付与した特徴量を用いて、前記照合元の指紋画像におけるそれら複数の代表特徴点と、照合先の指紋画像における複数の代表特徴点とによる指紋の照合処理を行う
請求項6に記載の指紋処理装置。
The collation processing unit specifies the representative extension direction of the ridge of the fingerprint extending from the extracted representative feature point for one extracted representative feature point extracted from the plurality of representative feature points, and is based on the extracted representative feature point. The pixel value of the neighborhood feature point indicating that the degree of coincidence between the stretch direction of the ridge of the fingerprint extending from the determined neighborhood feature point with respect to the representative stretch direction and the representative stretch direction is high, and the representative stretch direction. A ridge extension direction determination image showing the pixel value of the neighborhood feature point indicating that the degree of coincidence with is low is generated, and the position of the extraction representative feature point corresponding to the ridge extension direction determination image is used as a reference. A feature amount indicating a plurality of pixel values at a predetermined position is given, and using the feature amount similarly given to each of the representative feature points, the plurality of representative feature points in the fingerprint image of the collation source and the fingerprint of the collation destination are used. The fingerprint processing apparatus according to claim 6, which performs fingerprint collation processing with a plurality of representative feature points in an image.
指紋処理装置が、
照合元の指紋画像において特定した指紋の複数の特徴点のうち、前記指紋画像において画像の鮮明さが不明な画素領域までの第一距離に基づき、前記指紋の照合処理に用いる代表特徴点を決定する、
指紋処理方法。
Fingerprint processing device,
Of the plurality of feature points of the fingerprint specified in the fingerprint image of the collation source, the representative feature points used for the fingerprint collation process are determined based on the first distance to the pixel region where the sharpness of the image is unknown in the fingerprint image. do,
Fingerprint processing method.
コンピュータに、
照合元の指紋画像において特定した指紋の複数の特徴点のうち、前記指紋画像において画像の鮮明さが不明な画素領域までの第一距離に基づき、前記指紋の照合処理に用いる代表特徴点を決定させる
プログラム。
On the computer
Of the plurality of feature points of the fingerprint specified in the fingerprint image of the collation source, the representative feature points used for the fingerprint collation process are determined based on the first distance to the pixel region where the sharpness of the image is unknown in the fingerprint image. Program to let you.
照合元の指紋画像において特定した指紋の複数の特徴点のうち、前記指紋画像において画像の鮮明さが不明な画素領域までの第一距離に基づき、前記指紋の照合処理に用いる代表特徴点を決定する、
指紋処理回路。
Of the plurality of feature points of the fingerprint specified in the fingerprint image of the collation source, the representative feature points used for the fingerprint collation process are determined based on the first distance to the pixel region where the sharpness of the image is unknown in the fingerprint image. do,
Fingerprint processing circuit.
JP2022026934A 2020-11-11 2022-02-24 Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit Active JP7239034B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2022026934A JP7239034B2 (en) 2020-11-11 2022-02-24 Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2020188189A JP7031717B2 (en) 2020-11-11 2020-11-11 Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit
JP2022026934A JP7239034B2 (en) 2020-11-11 2022-02-24 Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
JP2020188189A Division JP7031717B2 (en) 2020-11-11 2020-11-11 Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit

Publications (2)

Publication Number Publication Date
JP2022060505A true JP2022060505A (en) 2022-04-14
JP7239034B2 JP7239034B2 (en) 2023-03-14

Family

ID=87884845

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2022026934A Active JP7239034B2 (en) 2020-11-11 2022-02-24 Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit

Country Status (1)

Country Link
JP (1) JP7239034B2 (en)

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0498468A (en) * 1990-08-11 1992-03-31 Omron Corp Feature point selecting method in fingerprint collating device
JPH0757092A (en) * 1993-08-11 1995-03-03 Yamatake Honeywell Co Ltd Fingerprint collating device
US6072895A (en) * 1996-12-13 2000-06-06 International Business Machines Corporation System and method using minutiae pruning for fingerprint image processing
JP2001307102A (en) * 2000-04-27 2001-11-02 Fujitsu Ltd Personal authentication system and method using living body information and registration device, authentication device and pattern information input medium for the system
JP2001344604A (en) * 2000-03-31 2001-12-14 Fujitsu Ltd Method, device and program for composing fingerprint data, computer-readable recording medium with the program recorded thereon and living body feature data composing method
JP2005346518A (en) * 2004-06-04 2005-12-15 Dainippon Printing Co Ltd Personal identification method
JP2006012080A (en) * 2004-06-29 2006-01-12 Secom Co Ltd Biological information authentication device
JP2006277146A (en) * 2005-03-28 2006-10-12 Sanyo Electric Co Ltd Collating method and collating device
JP2007328502A (en) * 2006-06-07 2007-12-20 Hitachi Information & Control Solutions Ltd Biometrics method and system
WO2010119500A1 (en) * 2009-04-13 2010-10-21 富士通株式会社 Biometric information registration device, biometric information registration method, computer program for registering biometric information, biometric authentication device, biometric authentication method, and computer program for biometric authentication
JP2011141744A (en) * 2010-01-07 2011-07-21 Nec Infrontia Corp Fingerprint characteristic amount extraction device, fingerprint input device, fingerprint authentication device and fingerprint characteristic amount extraction method
WO2012127630A1 (en) * 2011-03-22 2012-09-27 富士通株式会社 Biometric authentication system, biometric authentication method, and biometric authentication program

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4098468B2 (en) 2000-06-27 2008-06-11 株式会社リコー High voltage power supply
JP7057092B2 (en) 2017-10-12 2022-04-19 キヤノン株式会社 Toner and toner manufacturing method

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0498468A (en) * 1990-08-11 1992-03-31 Omron Corp Feature point selecting method in fingerprint collating device
JPH0757092A (en) * 1993-08-11 1995-03-03 Yamatake Honeywell Co Ltd Fingerprint collating device
US6072895A (en) * 1996-12-13 2000-06-06 International Business Machines Corporation System and method using minutiae pruning for fingerprint image processing
JP2001344604A (en) * 2000-03-31 2001-12-14 Fujitsu Ltd Method, device and program for composing fingerprint data, computer-readable recording medium with the program recorded thereon and living body feature data composing method
JP2001307102A (en) * 2000-04-27 2001-11-02 Fujitsu Ltd Personal authentication system and method using living body information and registration device, authentication device and pattern information input medium for the system
JP2005346518A (en) * 2004-06-04 2005-12-15 Dainippon Printing Co Ltd Personal identification method
JP2006012080A (en) * 2004-06-29 2006-01-12 Secom Co Ltd Biological information authentication device
JP2006277146A (en) * 2005-03-28 2006-10-12 Sanyo Electric Co Ltd Collating method and collating device
JP2007328502A (en) * 2006-06-07 2007-12-20 Hitachi Information & Control Solutions Ltd Biometrics method and system
WO2010119500A1 (en) * 2009-04-13 2010-10-21 富士通株式会社 Biometric information registration device, biometric information registration method, computer program for registering biometric information, biometric authentication device, biometric authentication method, and computer program for biometric authentication
JP2011141744A (en) * 2010-01-07 2011-07-21 Nec Infrontia Corp Fingerprint characteristic amount extraction device, fingerprint input device, fingerprint authentication device and fingerprint characteristic amount extraction method
WO2012127630A1 (en) * 2011-03-22 2012-09-27 富士通株式会社 Biometric authentication system, biometric authentication method, and biometric authentication program

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
中村 高宏、外2名: ""不一致特徴点の信頼性評価を用いた指紋照合"", 電子情報通信学会技術研究報告, vol. 105, no. 674, JPN6021044391, 10 March 2006 (2006-03-10), JP, pages 167 - 172, ISSN: 0004978520 *

Also Published As

Publication number Publication date
JP7239034B2 (en) 2023-03-14

Similar Documents

Publication Publication Date Title
JP6794766B2 (en) Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit
JP6347827B2 (en) Method, apparatus and device for detecting lane boundaries
KR101701069B1 (en) Matching process device, matching process method, and inspection device employing same
Zhang et al. Core-based structure matching algorithm of fingerprint verification
EP1093079A2 (en) Apparatus and method for matching fingerprint
JP4877392B2 (en) Feature attribute calculation device, feature quantity extraction device, pattern matching device, method and program
KR20170133262A (en) Object recognition apparatus, objection recognition method, and program
CN110348307B (en) Path edge identification method and system for crane metal structure climbing robot
CN114549400A (en) Image identification method and device
US20180121757A1 (en) System and method for automated object recognition
JP7031717B2 (en) Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit
US7386172B2 (en) Image recognition method
JP6591257B2 (en) Image processing apparatus, image processing method, and program
JP7239034B2 (en) Fingerprint processing device, fingerprint processing method, program, fingerprint processing circuit
JPH09229646A (en) Object recognition method
US11915498B2 (en) Reading system, reading device, and storage medium
JP6540577B2 (en) Object recognition device
JP3460824B2 (en) Shape recognition method and device
CN113610790B (en) Image recognition-based gas diffusion layer fiber measurement method
JP6278757B2 (en) Feature value generation device, feature value generation method, and program
JP4552409B2 (en) Image processing device
KR100564762B1 (en) Authentication method and apparatus using fingerprint
JP2001243479A (en) Method and device for image processing and recording medium having image processing program recorded thereon
WO2024047847A1 (en) Detection device, detection method, and detection program
Kundu et al. Accurate localizations of reference points in a fingerprint image

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20220224

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20230131

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20230213

R151 Written notification of patent or utility model registration

Ref document number: 7239034

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R151