JP4480832B2 - Fingerprint verification device and verification method thereof - Google Patents

Fingerprint verification device and verification method thereof Download PDF

Info

Publication number
JP4480832B2
JP4480832B2 JP2000012437A JP2000012437A JP4480832B2 JP 4480832 B2 JP4480832 B2 JP 4480832B2 JP 2000012437 A JP2000012437 A JP 2000012437A JP 2000012437 A JP2000012437 A JP 2000012437A JP 4480832 B2 JP4480832 B2 JP 4480832B2
Authority
JP
Japan
Prior art keywords
fingerprint
degree
coincidence
calculated
matching
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
Application number
JP2000012437A
Other languages
Japanese (ja)
Other versions
JP2001202513A (en
Inventor
満則 足達
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.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric 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
Application filed by Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Priority to JP2000012437A priority Critical patent/JP4480832B2/en
Publication of JP2001202513A publication Critical patent/JP2001202513A/en
Application granted granted Critical
Publication of JP4480832B2 publication Critical patent/JP4480832B2/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Images

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
    • G06V40/1365—Matching; Classification

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Collating Specific Patterns (AREA)

Description

【０００１】
【発明の属する技術分野】
この発明は、指紋センサで読み取った指紋と、登録された指紋とを照合する指紋照合装置及びその照合方法に関するものである。
【０００２】
【従来の技術】
図６は従来の指紋照合装置を示す機能構成図である。
利用者が指を指紋センサ部１に置くことにより、指紋センサ部１は指紋を読み取り、画像処理特徴抽出手段２により画像処理されて指紋の特徴量を抽出する。一致度計算手段４は特徴量メモリ３に登録されている指紋の特徴量と、上記抽出された特徴量とを比較して、その一致度を計算する。この一致度は比較手段５でしきい値６と比較され、本人認証結果が出力され照合履歴メモリ７に記録される。
【０００３】
【発明が解決しようとする課題】
上記のような従来の指紋照合装置では、一致度を判定するしきい値は一定値に設定されているため、何らかの原因で一致度が低下した場合には、本人が本人であると判定される率が下がり、本人認証に支障が生じる。更に、それを避けるためには、定期的に一致度の履歴を見て、しきい値を変更する等の保守が必要となり繁雑になるという問題点がある。
【０００４】
この発明は上記問題点を解消するためになされたもので、誤認識率を下げ、かつ繁雑な定期保守を低減することができるようにした指紋照合装置及びその照合方法を提供することを目的とする。
【０００５】
【課題を解決するための手段】
この発明の第１発明に係る指紋照合装置は、入力された指紋の特徴量と登録された指紋の特徴量との一致度を、しきい値と比較して判定結果を出力するとともに、異なる指毎に指紋の一致度が計算される度に、計算された一致度を記憶し、記憶された一致度の平均値を計算して、この平均一致度が所定値以下になると異常発報するようにしたものである。
また、第２発明に係る指紋照合装置は、入力された指紋の特徴量と登録された指紋の特徴量との一致度を、しきい値と比較して判定結果を出力するとともに、異なる指毎に指紋の一致度が計算される度に、計算された一致値と判定結果を記憶し、判定結果が合格となった一致度を積算し、上記合格となった一致度の所定回数分の積算値が基準値以下のとき異常発報するようにしたものである。
【０００６】
また、第３発明に係る指紋照合装置は、第１発明又は第２発明のものにおいて、平均一致度に従ってしきい値を変化させるようにしたものである。
また、第４発明に係る指紋照合装置は、第３発明のものにおいて、平均一致度が低いときはしきい値も低く、平均一致度が高いときはしきい値も高く設定するようにしたものである。
【０００９】
また、第５発明に係る指紋照合方法は、指紋センサで読み取った指紋画像から指紋の特徴量を抽出し、この抽出された指紋の特徴量とあらかじめ登録された指紋の特徴量とを比較して指紋の一致度を計算し、この計算された一致度を所定のしきい値と比較して判定結果を出力し、異なる指毎に指紋の一致度が計算される度に、計算された一致度を記憶し、この記憶された一致度の平均値を計算し、この計算された平均一致度が所定値以下になると異常発報する各ステップを備えたものである。
また、第６発明に係る指紋照合方法は、指紋センサで読み取った指紋画像から指紋の特徴量を抽出し、この抽出された指紋の特徴量とあらかじめ登録された指紋の特徴量とを比較して指紋の一致度を計算し、この計算された一致度を所定のしきい値と比較して判定結果を出力し、異なる指毎に指紋の一致度が計算される度に、計算された一致度と判定結果を記憶し、判定結果が合格となった一致度を積算し、合格となった一致度の所定回数分の積算値が基準値以下のとき異常発報する各ステップを備えたものである。
【００１０】
【発明の実施の形態】
実施の形態１．
図１〜図３はこの発明の第１、第２及び第５発明の一実施の形態を示す図で、図１は機能構成図、図２は照合履歴メモリの内容図、図３はしきい値曲線図である。
図１において、１は指紋画像を読み取る指紋センサ部、２は指紋センサ部１からの指紋画像を処理して、その特徴量（指紋の分岐点、端点など）を抽出する画像処理・特徴抽出手段である。
【００１１】
３は画像処理・特徴抽出手段２から出力される指紋特徴量を記憶する特徴量メモリ、４は特徴量メモリ３に記憶された登録時の特徴量と、画像処理・特徴抽出部２からの照合時の特徴量を比較して一致度を計算する一致度計算手段、５は一致度計算手段４からの一致度と、しきい値設定手段６からのしきい値を比較して、登録指紋と照合指紋が同一であるかを判定する比較手段である。
【００１２】
７は一致度計算手段４からの一致度と、比較手段５からの判定結果を記憶する照合履歴メモリ、８は照合履歴メモリ７からの一致度の平均値を計算する平均一致度計算手段、９は平均一致度計算手段８で計算された平均一致度により本人判定のしきい値を変更するしきい値変更手段である。
【００１３】
次に、この実施の形態の動作を説明する。
（１） 指紋登録時
利用者が指を指紋センサ部１に置くことにより、指紋センサ部１は指紋を読み取る。読み取られた指紋画像は画像処理・特徴抽出手段２へ送られ、ここで画像処理して、指紋特徴量を抽出する。そして、その特徴量は特徴量メモリ３に記憶、すなわち指紋が登録される。
【００１４】
（２） 指紋照合時
指紋登録時と同様に、利用者が指を指紋センサ部１に置くと、画像処理・特徴抽出手段２で特徴量が抽出され、一致度計算手段４へ送られる。一致度計算手段４は特徴量メモリ３に登録された登録指紋特徴量と、照合時の画像処理・特徴抽出手段２からの照合指紋特徴量とを比較して、その一致度を計算する。この一致度は、登録指紋特徴量と照合指紋特徴量が全く同一であれば１００％、全く異なっていれば０％であり、通常０〜１００％の値となる。
【００１５】
この一致度は比較手段５へ送られ、しきい値設定手段６からのしきい値と比較され、本人認証結果が出力される。指紋照合装置としては、以上の動作で完了するが、通常保守を容易にするために、照合履歴を記録するようにしている。すなわち、比較手段５からの本人認証結果と一致度計算手段４からの一致度を、照合履歴メモリ７に記憶する。照合履歴メモリ７の内容を図２に示す。図中、ＩＤ番号は指に固有な番号であり、判定結果の○は本人、×は他人、一致度は０〜１００％の値である。
【００１６】
タイマ（図示しない）が所定時刻に達するか、新たな履歴件数が所定値に達する度に、平均一致度計算手段８は照合履歴メモリ７の一致度の項目を平均化する。ただし、他人がいたずらをする可能性を排除するために平均化する際に一致度が一定値（例えば３０％）以上である場合だけの平均値を計算する。更に、その平均値をしきい値変更手段９へ送出し、本人判定のしきい値を変化させる。
【００１７】
例えば、図３に示すように、一致度の平均値が低ければ、しきい値も低く設定し、一致度の平均値が高ければ、しきい値も高く設定する。ただし、変化させる下限値Ｔｈ１と上限値Ｔｈ２を設けて、しきい値を下限値Ｔｈ１〜上限値Ｔｈ２に抑えて、本人認証の性能の範囲内に変化幅が入るようにする。これにより、本人の一致度が低下した場合に、自動的にしきい値を下げて、本人認証の率を従来と同様に保つことが可能となる。
【００１８】
このようにして、照合履歴メモリ７に記憶された一致度の平均値を計算して、平均一致度が低い場合には、本人判定のしきい値を低めに設定し、平均一致度が高い場合には、本人判定のしきい値を高めに設定するようにしたため、指紋照合における誤認識率を下げることが可能となる。
【００１９】
実施の形態２．
図４はこの発明の第３発明の一実施の形態を示す機能構成図であり、図１と同様の部分は同一符号で示す。（以下の実施の形態も同じ。）なお、図２及び図３は実施の形態２にも共用する。
この実施の形態は、図１のものからしきい値変更手段９を削除し、平均一致度計算手段８に発報装置１０を接続し、異常発報信号１０ａを出力させるようにしたものである。
【００２０】
次に、この実施の形態の動作を、実施の形態１と異なる部分について説明する。
平均一致度計算手段８から出力される平均一致度が所定のしきい値よりも低下すると、発報装置１０は異常発報信号１０ａを出力して異常を発報する。
このようにして、平均一致度が極端に低下した場合に、異常を発報するようにしたため、繁雑な定期保守の機会が低減され、保守を容易にすることが可能となる。
【００２１】
実施の形態３．
図５はこの発明の第４発明の一実施の形態を示す機能構成図である。なお、図２及び図３は実施の形態３にも共用する。
この実施の形態は、図１のものにおいて、発報装置１０及び判定結果積算手段１１を追加したものである。
【００２２】
次に、この実施の形態の動作を、実施の形態２と異なる部分について説明する。
判定結果積算手段１１は照合履歴メモリ７に記憶された判定結果を積算する。ただし、判定結果の積算時に、他人のいたずらを排除するため、一致度が一定値（例えば３０％）以上の場合だけ、図２の判定結果○の一致度について積算する。次に、判定結果積算手段１１からの積算値が基準値以下になった場合、発報装置１０は異常発報信号１０ａを出力する。
【００２３】
このようにして、判定結果の積算値、すなわち判定結果が合格となった一致度の積算値が極端に低下した場合に、異常を発報するようにしたため、繁雑な定期保守の機会が低減され、保守を容易にすることが可能となる。
【００２４】
【発明の効果】
以上説明したとおりこの発明の第１及び第５発明では、入力された指紋の特徴量と登録された指紋の特徴量との一致度を、しきい値と比較して判定結果を出力するとともに、異なる指毎に指紋の一致度が計算される度に、計算された一致度を記憶し、記憶された一致度の平均値を計算して、この平均一致度が所定値以下になると異常発報するようにしたので、繁雑な定期保守の機会が低減され、保守を容易にすることができる。
また、第２発明及び第６発明では、入力された指紋の特徴量と登録された指紋の特徴量との一致度を、しきい値と比較して判定結果を出力するとともに、異なる指毎に計算される度に、計算された一致度と判定結果を記憶し、判定結果が合格となった一致度を積算し、上記合格となった一致度の所定回数分の積算値が基準値以下のとき異常発報するようにしたので、繁雑な定期保守の機会が低減され、保守を容易にすることができる。
また、第３発明では、入力された指紋の特徴量と登録された指紋の特徴量との一致度を、しきい値と比較して判定結果を出力するとともに、一致度の平均値を計算して、この平均一致度に従ってしきい値を変化させ、第４発明では、平均一致度が低いときはしきい値も低く、平均一致度が高いときはしきい値も高く設定するようにしたので、指紋照合における誤認識率を下げることができる。
【図面の簡単な説明】
【図１】 この発明の実施の形態１を示す機能構成図。
【図２】 図１の照合履歴メモリの内容図。
【図３】 この発明の実施の形態１を示すしきい値曲線図。
【図４】 この発明の実施の形態２を示す機能構成図。
【図５】 この発明の実施の形態３を示す機能構成図。
【図６】 従来の指紋照合装置を示す機能構成図。
【符号の説明】
１ 指紋センサ部、２ 画像処理・特徴抽出手段、３ 特徴量メモリ、４ 一致度計算手段、５ 比較手段、６ しきい値設定手段、７ 照合履歴メモリ、８平均一致度計算手段、９ しきい値変更手段、１０ 発報装置、１０ａ 異常発報信号[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a fingerprint collation apparatus that collates a fingerprint read by a fingerprint sensor with a registered fingerprint and a collation method thereof.
[0002]
[Prior art]
FIG. 6 is a functional block diagram showing a conventional fingerprint collation apparatus.
When the user places his / her finger on the fingerprint sensor unit 1, the fingerprint sensor unit 1 reads the fingerprint and performs image processing by the image processing feature extraction unit 2 to extract the feature amount of the fingerprint. The degree of coincidence calculation means 4 compares the feature quantity of the fingerprint registered in the feature quantity memory 3 with the extracted feature quantity, and calculates the degree of coincidence. The degree of coincidence is compared with the threshold value 6 by the comparison means 5, and the personal authentication result is output and recorded in the collation history memory 7.
[0003]
[Problems to be solved by the invention]
In the conventional fingerprint collation device as described above, the threshold value for determining the degree of coincidence is set to a constant value. Therefore, if the degree of coincidence decreases for some reason, it is determined that the person is the person himself / herself. The rate will drop and will interfere with identity verification. Furthermore, in order to avoid this, there is a problem that maintenance such as periodically changing the threshold value by looking at the history of coincidence becomes complicated and complicated.
[0004]
The present invention was made to solve the above problems, and an object thereof is to provide a fingerprint collation apparatus and a collation method thereof that can reduce the false recognition rate and reduce complicated periodic maintenance. To do.
[0005]
[Means for Solving the Problems]
The fingerprint collation apparatus according to the first aspect of the present invention compares the degree of coincidence between the input fingerprint feature quantity and the registered fingerprint feature quantity with a threshold value and outputs a determination result, and also provides a different finger each time the degree of matching fingerprint is computed for each, and stores the calculated degree of matching, and calculates the average value of the stored degree of matching, that abnormally onset report this average degree of coincidence is equal to or less than a predetermined value It is what I did.
Further, the fingerprint collation device according to the second aspect of the invention compares the degree of coincidence between the input fingerprint feature quantity and the registered fingerprint feature quantity with a threshold value and outputs a determination result. Every time the fingerprint matching degree is calculated, the calculated matching value and the judgment result are stored, and the degree of matching that the judgment result is passed is integrated, and the above matching degree of integration is accumulated for a predetermined number of times. When the value is below the reference value, an abnormal report is issued.
[0006]
A fingerprint collation device according to a third aspect of the present invention is the one according to the first aspect or the second aspect, wherein the threshold value is changed according to the average matching degree.
The fingerprint collation device according to the fourth invention is the one according to the third invention, wherein the threshold value is set low when the average matching degree is low, and the threshold value is set high when the average matching degree is high. It is.
[0009]
The fingerprint collation method according to the fifth aspect of the present invention extracts a fingerprint feature amount from a fingerprint image read by a fingerprint sensor, and compares the extracted fingerprint feature amount with a pre-registered fingerprint feature amount. Calculates the degree of matching of the fingerprint, compares the calculated degree of matching with a predetermined threshold value, outputs a determination result, and calculates the degree of matching calculated each time the degree of matching of the fingerprint is calculated for each different finger. storing the average value of the stored degree of matching is calculated, the calculated average degree of matching is obtained with the steps that abnormally onset report becomes a predetermined value or less.
The fingerprint collation method according to the sixth aspect of the present invention extracts a fingerprint feature amount from a fingerprint image read by a fingerprint sensor, and compares the extracted fingerprint feature amount with a pre-registered fingerprint feature amount. Calculates the degree of matching of the fingerprint, compares the calculated degree of matching with a predetermined threshold value, outputs a determination result, and calculates the degree of matching calculated each time the degree of matching of the fingerprint is calculated for each different finger. Is stored with the determination result, and the degree of coincidence that the determination result is passed is integrated, and each step that issues an abnormality when the integrated value for a predetermined number of times the degree of agreement that has passed is below the reference value is provided. is there.
[0010]
DETAILED DESCRIPTION OF THE INVENTION
Embodiment 1 FIG.
1 to 3 are diagrams showing an embodiment of the first, second and fifth inventions of the present invention. FIG. 1 is a functional configuration diagram, FIG. 2 is a content diagram of a verification history memory, and FIG. 3 is a threshold. It is a value curve figure.
In FIG. 1, 1 is a fingerprint sensor unit for reading a fingerprint image, 2 is an image processing / feature extraction unit for processing a fingerprint image from the fingerprint sensor unit 1 and extracting feature amounts (eg, fingerprint branch points and end points). It is.
[0011]
Reference numeral 3 denotes a feature amount memory for storing the fingerprint feature amount output from the image processing / feature extraction means 2, and 4 denotes a feature amount at the time of registration stored in the feature amount memory 3 and collation from the image processing / feature extraction unit 2. The degree-of-matching calculation means 5 compares the feature quantities at the time to calculate the degree of coincidence, and 5 compares the degree of coincidence from the degree-of-matching calculation means 4 with the threshold value from the threshold value setting means 6, It is a comparison means for determining whether the collation fingerprints are the same.
[0012]
7 is a collation history memory for storing the coincidence degree from the coincidence degree calculation means 4 and the determination result from the comparison means 5, 8 is an average coincidence degree calculation means for calculating the average value of the coincidence degrees from the collation history memory 7, 9 Is a threshold value changing means for changing the threshold value for personal identification based on the average matching degree calculated by the average matching degree calculating means 8.
[0013]
Next, the operation of this embodiment will be described.
(1) When a user places a finger on the fingerprint sensor unit 1 during fingerprint registration, the fingerprint sensor unit 1 reads the fingerprint. The read fingerprint image is sent to the image processing / feature extraction means 2, where the image processing is performed to extract the fingerprint feature amount. The feature quantity is stored in the feature quantity memory 3, that is, a fingerprint is registered.
[0014]
(2) At the time of fingerprint collation As in the case of fingerprint registration, when a user places a finger on the fingerprint sensor unit 1, the feature amount is extracted by the image processing / feature extraction unit 2 and sent to the matching degree calculation unit 4. The degree of coincidence calculation means 4 compares the registered fingerprint feature quantity registered in the feature quantity memory 3 with the collation fingerprint feature quantity from the image processing / feature extraction means 2 at the time of collation, and calculates the degree of coincidence. The degree of coincidence is 100% if the registered fingerprint feature quantity and the matching fingerprint feature quantity are exactly the same, and 0% if they are completely different, and is usually a value of 0 to 100%.
[0015]
This degree of coincidence is sent to the comparison means 5, compared with the threshold value from the threshold setting means 6, and a personal authentication result is output. The fingerprint collation apparatus is completed by the above operation, but collation history is recorded in order to facilitate normal maintenance. That is, the identity authentication result from the comparison unit 5 and the coincidence degree from the coincidence degree calculation unit 4 are stored in the collation history memory 7. The contents of the verification history memory 7 are shown in FIG. In the figure, the ID number is a number unique to the finger, the determination result ○ is the person, x is the other person, and the degree of coincidence is 0 to 100%.
[0016]
Each time a timer (not shown) reaches a predetermined time or a new history count reaches a predetermined value, the average coincidence calculation means 8 averages the items of coincidence in the collation history memory 7. However, an average value is calculated only when the degree of coincidence is a certain value (for example, 30%) or more when averaging is performed in order to eliminate the possibility of mischief by others. Further, the average value is sent to the threshold value changing means 9 to change the threshold value for identity determination.
[0017]
For example, as shown in FIG. 3, if the average value of the degree of coincidence is low, the threshold value is set low, and if the average value of the degree of coincidence is high, the threshold value is also set high. However, the lower limit value Th1 and the upper limit value Th2 to be changed are provided, and the threshold value is suppressed to the lower limit value Th1 to the upper limit value Th2, so that the range of change is within the range of the performance of personal authentication. As a result, when the identity of the person falls, the threshold value is automatically lowered, and the identity authentication rate can be maintained as in the conventional case.
[0018]
In this way, the average value of the degree of coincidence stored in the matching history memory 7 is calculated, and when the average degree of coincidence is low, the threshold value for identity determination is set lower, and the average degree of coincidence is high. Since the threshold value for the person identification is set higher, it is possible to reduce the false recognition rate in fingerprint collation.
[0019]
Embodiment 2. FIG.
FIG. 4 is a functional block diagram showing an embodiment of the third invention of the present invention, and the same parts as those in FIG. (The same applies to the following embodiments.) FIGS. 2 and 3 are also used in the second embodiment.
In this embodiment, the threshold value changing means 9 is deleted from the one shown in FIG. 1, and a reporting device 10 is connected to the average coincidence calculating means 8 to output an abnormal reporting signal 10a. .
[0020]
Next, the operation of this embodiment will be described for parts different from the first embodiment.
When the average coincidence degree output from the average coincidence degree calculating means 8 falls below a predetermined threshold value, the alarm device 10 outputs an abnormal alarm signal 10a to issue an abnormality.
In this way, when the average degree of coincidence is extremely lowered, an abnormality is reported, so that the opportunity for complicated periodic maintenance is reduced, and maintenance can be facilitated.
[0021]
Embodiment 3 FIG.
FIG. 5 is a functional block diagram showing an embodiment of the fourth invention of the present invention. 2 and 3 are also used in the third embodiment.
In this embodiment, a reporting device 10 and a determination result integrating means 11 are added to that of FIG.
[0022]
Next, the operation of this embodiment will be described with respect to the differences from the second embodiment.
The determination result integration unit 11 integrates the determination results stored in the verification history memory 7. However, in order to eliminate other people's mischief at the time of integration of the determination results, the determination results are integrated with respect to the coincidence degree of the determination result ◯ only when the coincidence degree is a certain value (for example, 30%) or more. Next, when the integrated value from the determination result integrating means 11 becomes equal to or less than the reference value, the alarm device 10 outputs an abnormal alarm signal 10a.
[0023]
In this way, when the integrated value of the determination result, that is, the integrated value of the degree of coincidence in which the determination result has passed is extremely lowered, an abnormality is reported, so that the opportunity for complicated periodic maintenance is reduced. Maintenance can be facilitated.
[0024]
【The invention's effect】
As described above, according to the first and fifth aspects of the present invention, the degree of coincidence between the input feature quantity of the fingerprint and the registered fingerprint feature quantity is compared with a threshold value, and a determination result is output. Every time a fingerprint matching degree is calculated for each different finger, the calculated matching degree is stored, and an average value of the stored matching degrees is calculated, and when this average matching degree becomes a predetermined value or less, an abnormal alarm is generated. As a result, complicated periodic maintenance opportunities are reduced, and maintenance can be facilitated.
In the second and sixth inventions, the degree of coincidence between the input fingerprint feature quantity and the registered fingerprint feature quantity is compared with a threshold value, and a determination result is output. Every time it is calculated, the calculated degree of coincidence and determination result are stored, and the degree of coincidence that the determination result has passed is integrated. Occasionally, an abnormal alarm is issued, so that the chances of complicated periodic maintenance are reduced and the maintenance can be facilitated.
In the third aspect of the invention, the degree of coincidence between the input fingerprint feature quantity and the registered fingerprint feature quantity is compared with a threshold value to output a determination result, and an average value of the coincidence degree is calculated. In the fourth aspect of the invention, the threshold value is set to be low when the average match value is low, and the threshold value is set to be high when the average match value is high. The false recognition rate in fingerprint verification can be reduced.
[Brief description of the drawings]
FIG. 1 is a functional configuration diagram showing a first embodiment of the present invention.
FIG. 2 is a content diagram of the verification history memory in FIG. 1;
FIG. 3 is a threshold curve diagram showing the first embodiment of the present invention.
FIG. 4 is a functional configuration diagram showing Embodiment 2 of the present invention.
FIG. 5 is a functional configuration diagram showing Embodiment 3 of the present invention.
FIG. 6 is a functional configuration diagram showing a conventional fingerprint collation apparatus.
[Explanation of symbols]
DESCRIPTION OF SYMBOLS 1 Fingerprint sensor part, 2 Image processing and feature extraction means, 3 Feature-value memory, 4 Matching degree calculation means, 5 Comparison means, 6 Threshold setting means, 7 Collation history memory, 8 Average matching degree calculation means, 9 Threshold Value change means, 10 alarm device, 10a abnormal alarm signal

Claims (6)

指紋センサで読み取った指紋画像から指紋の特徴量を抽出する特徴抽出手段と、
上記特徴抽出手段に抽出された指紋の特徴量とあらかじめ登録された指紋の特徴量とを比較して指紋の一致度を計算し、この一致度を所定のしきい値と比較して判定結果を出力する比較手段と、
異なる指毎に上記比較手段が指紋の一致度を計算する度に、計算された一致度を記憶するメモリと、
異なる指毎に上記比較手段が指紋の一致度を計算する度に上記メモリが記憶した一致度の平均値を計算する平均一致度計算手段と、
上記計算された平均一致度が所定値以下になると異常発報する発報装置と
を備えたことを特徴とする指紋照合装置。 A feature extraction means for extracting a feature amount of a fingerprint from a fingerprint image read by a fingerprint sensor;
The fingerprint feature amount extracted by the feature extraction means is compared with the fingerprint feature amount registered in advance to calculate the fingerprint matching degree, and the matching degree is compared with a predetermined threshold value to obtain a determination result. Comparing means for outputting;
A memory for storing the calculated degree of coincidence each time the comparison means calculates the degree of coincidence of the fingerprint for each different finger;
An average coincidence degree calculating means for calculating an average value of the coincidence degree stored in the memory every time the comparison means calculates a fingerprint coincidence degree for each different finger ;
A fingerprint collation apparatus comprising: an alarm device that issues an abnormality when the calculated average coincidence falls below a predetermined value. 指紋センサで読み取った指紋画像から特徴量を抽出する特徴抽出手段と、
上記特徴抽出手段に抽出された指紋の特徴量とあらかじめ登録された特徴量とを比較して指紋の一致度を計算し、この一致度を所定のしきい値と比較して判定結果を出力する比較手段と、
異なる指毎に上記比較手段が指紋の一致度を計算する度に、計算された一致度と判定結果とを記憶するメモリと、
上記メモリに記憶された判定結果が合格となった一致度を積算する判定結果積算手段と、
上記合格となった一致度の所定回数分の積算値が基準値以下のとき異常発報する発報装置と
を備えたことを特徴とする指紋照合装置。 Feature extraction means for extracting a feature amount from a fingerprint image read by a fingerprint sensor;
The feature quantity of the fingerprint extracted by the feature extraction means is compared with a pre-registered feature quantity to calculate the degree of matching of the fingerprint, and the degree of coincidence is compared with a predetermined threshold value and a determination result is output. A comparison means;
A memory for storing the calculated degree of coincidence and the determination result each time the comparison unit calculates the degree of coincidence of the fingerprint for each different finger;
A determination result integrating means for integrating the degree of coincidence that the determination result stored in the memory has passed;
Fingerprint verification device you comprising the <br/> the alarm device integrated value of a predetermined number of times of coincidence degree becomes the pass abnormally alarm when less than a reference value. 上記計算された平均一致度に従って上記しきい値を変化させるしきい値変更手段を備えたことを特徴とする請求項１又は請求項２記載の指紋照合装置。 Upper SL calculated average matched fingerprint identification apparatus according to claim 1 or claim 2, wherein further comprising a threshold changing hands stage for changing the threshold according to the degree. しきい値変更手段は、平均一致度が低いときはしきい値も低く、上記平均一致度が高いときは上記しきい値も高く設定するものとしたことを特徴とする請求項３記載の指紋照合装置。4. The fingerprint according to claim 3 , wherein the threshold value changing means sets the threshold value to be low when the average degree of coincidence is low, and sets the threshold value to be high when the average degree of coincidence is high. Verification device. 指紋センサで読み取った指紋画像から指紋の特徴量を抽出するステップと、
この抽出された指紋の特徴量とあらかじめ登録された指紋の特徴量とを比較して指紋の一致度を計算するステップと、
この計算された一致度を所定のしきい値と比較して判定結果を出力するステップと、
異なる指毎に指紋の一致度が計算される度に、計算された一致度を記憶するステップと、
異なる指毎に指紋の一致度が計算される度に記憶された一致度の平均値を計算するステップと、
この計算された平均一致度が所定値以下になると異常発報するステップと
を備えてなる指紋照合方法。Extracting a fingerprint feature from a fingerprint image read by a fingerprint sensor;
Comparing the extracted fingerprint feature quantity with a pre-registered fingerprint feature quantity to calculate a fingerprint matching degree;
Comparing the calculated degree of coincidence with a predetermined threshold value and outputting a determination result;
Storing the calculated degree of matching each time the degree of matching of the fingerprint is calculated for each different finger ;
Calculating an average value of the degree of coincidence stored each time the degree of fingerprint coincidence is calculated for each different finger ;
Fingerprint verification method the calculated average degree of coincidence is provided with a step that abnormally onset report becomes a predetermined value or less. 指紋センサで読み取った指紋画像から指紋の特徴量を抽出するステップと、Extracting a fingerprint feature from a fingerprint image read by a fingerprint sensor;
この抽出された指紋の特徴量とあらかじめ登録された指紋の特徴量とを比較して指紋の一致度を計算するステップと、Comparing the extracted fingerprint feature quantity with a pre-registered fingerprint feature quantity to calculate a fingerprint matching degree;
この計算された一致度を所定のしきい値と比較して判定結果を出力するステップと、Comparing the calculated degree of coincidence with a predetermined threshold value and outputting a determination result;
異なる指毎に指紋の一致度が計算される度に、計算された一致度と判定結果を記憶するステップと、A step of storing the calculated degree of matching and the determination result each time the degree of matching of the fingerprint is calculated for each different finger;
判定結果が合格となった一致度を積算するステップと、A step of accumulating the degree of coincidence that the determination result is passed,
合格となった一致度の所定回数分の積算値が基準値以下のとき異常発報するステップとA step of issuing an abnormality when the integrated value for a predetermined number of coincidences that have passed is below a reference value;
を備えてなる照合指紋方法。A verification fingerprint method comprising:
JP2000012437A 2000-01-21 2000-01-21 Fingerprint verification device and verification method thereof Expired - Fee Related JP4480832B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2000012437A JP4480832B2 (en) 2000-01-21 2000-01-21 Fingerprint verification device and verification method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP2000012437A JP4480832B2 (en) 2000-01-21 2000-01-21 Fingerprint verification device and verification method thereof

Publications (2)

Publication Number Publication Date
JP2001202513A JP2001202513A (en) 2001-07-27
JP4480832B2 true JP4480832B2 (en) 2010-06-16

Family

ID=18540153

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2000012437A Expired - Fee Related JP4480832B2 (en) 2000-01-21 2000-01-21 Fingerprint verification device and verification method thereof

Country Status (1)

Country Link
JP (1) JP4480832B2 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093209A (en) * 2013-01-23 2013-05-08 深圳市亚略特生物识别科技有限公司 Fingerprint verification system
CN110751760A (en) * 2019-10-22 2020-02-04 珠海格力电器股份有限公司 Adjusting method of biological information identification level, intelligent door lock and control method thereof

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20030070183A (en) * 2002-02-21 2003-08-29 엘지전자 주식회사 Iris recording and recognition method of forged distingction of iris recognition system
JP2004054327A (en) * 2002-07-16 2004-02-19 Mitsubishi Electric Corp Fingerprint collating device
JP5017873B2 (en) * 2006-02-07 2012-09-05 コニカミノルタホールディングス株式会社 Personal verification device and personal verification method
KR100778891B1 (en) * 2006-04-05 2007-11-22 (주)니트 젠 Method and apparatus for dynamically changing matching score threshold value in biomass authentication
JP5003242B2 (en) * 2007-03-28 2012-08-15 富士通株式会社 Verification device, verification method and verification program
JP2010039846A (en) * 2008-08-06 2010-02-18 Fujitsu Ltd Authentication method controller, authentication method control method and authentication method control program
JP5932317B2 (en) * 2011-12-02 2016-06-08 綜合警備保障株式会社 Face authentication database management method, face authentication database management apparatus, and face authentication database management program
JP6049253B2 (en) * 2011-12-02 2016-12-21 綜合警備保障株式会社 Face authentication database management method, face authentication database management apparatus, and face authentication database management program
KR101773233B1 (en) * 2014-07-25 2017-09-12 이동광 Managing method for repeating fail of biometric recognition
CN105160320B (en) * 2015-09-02 2019-03-01 小米科技有限责任公司 Fingerprint identification method, device and mobile terminal
JP2018124800A (en) * 2017-02-01 2018-08-09 富士通株式会社 Authentication device, authentication program, and authentication method
JP6648769B2 (en) 2018-01-12 2020-02-14 日本電気株式会社 Face recognition device

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08115422A (en) * 1994-10-19 1996-05-07 Secom Co Ltd Individual identification device
JPH10105708A (en) * 1996-09-25 1998-04-24 Sony Corp Image collation device
JPH11104112A (en) * 1997-09-30 1999-04-20 Glory Ltd Individual recognition device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH08115422A (en) * 1994-10-19 1996-05-07 Secom Co Ltd Individual identification device
JPH10105708A (en) * 1996-09-25 1998-04-24 Sony Corp Image collation device
JPH11104112A (en) * 1997-09-30 1999-04-20 Glory Ltd Individual recognition device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103093209A (en) * 2013-01-23 2013-05-08 深圳市亚略特生物识别科技有限公司 Fingerprint verification system
CN110751760A (en) * 2019-10-22 2020-02-04 珠海格力电器股份有限公司 Adjusting method of biological information identification level, intelligent door lock and control method thereof

Also Published As

Publication number Publication date
JP2001202513A (en) 2001-07-27

Similar Documents

Publication Publication Date Title
JP4480832B2 (en) Fingerprint verification device and verification method thereof
JP5012247B2 (en) Authentication device, entrance management device, entrance / exit management device, entrance management system, entrance / exit management system, authentication processing method and program
US6993166B2 (en) Method and apparatus for enrollment and authentication of biometric images
US8079061B2 (en) Authentication system managing method
JP5932317B2 (en) Face authentication database management method, face authentication database management apparatus, and face authentication database management program
US20070183634A1 (en) Auto Individualization process based on a facial biometric anonymous ID Assignment
JP2013077068A (en) Face authentication database management method, face authentication database management device, and face authentication database management program
JP4037009B2 (en) Iris recognition device and identification system
CN108230518B (en) Access control system
CN105006077A (en) ATM safe operation method and system based on fingerprint identification, and ATM
JP2002236666A (en) Personal authentication device
WO2017031969A1 (en) Fingerprint verification method, fingerprint verification device and terminal
JP6962248B2 (en) Biometric authentication system, biometric authentication device, automatic ticket gate, biometric authentication method, and program
CN108615286B (en) Intelligent management method and system for cell
CN106157405A (en) A kind of entry and exit hall identity verification system
JP3990907B2 (en) Composite authentication system
US20120011586A1 (en) Biometric authentication device and biometric authentication method
CN112489276A (en) Gate inhibition control method and device based on gait recognition and storage medium
US20120219192A1 (en) Method of controlling a session at a self-service terminal, and a self-service terminal
JP2003044858A (en) Device and method for personal identification
JP5276554B2 (en) Biometric information authentication apparatus and biometric information authentication program
CN115394454A (en) Data verification method and related equipment
JPH0883342A (en) Human body collating device
JP2012123526A (en) Biometric authentication device and biometric authentication method
JP2004054888A (en) Face collating device

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20061205

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20100202

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20100224

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: 20100316

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20100317

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20130326

Year of fee payment: 3

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20130326

Year of fee payment: 3

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20140326

Year of fee payment: 4

LAPS Cancellation because of no payment of annual fees