Deprecated: The each() function is deprecated. This message will be suppressed on further calls in /home/zhenxiangba/zhenxiangba.com/public_html/phproxy-improved-master/index.php on line 456
JPH054517B2 - - Google Patents
[go: Go Back, main page]

JPH054517B2 - - Google Patents

Info

Publication number
JPH054517B2
JPH054517B2 JP58059555A JP5955583A JPH054517B2 JP H054517 B2 JPH054517 B2 JP H054517B2 JP 58059555 A JP58059555 A JP 58059555A JP 5955583 A JP5955583 A JP 5955583A JP H054517 B2 JPH054517 B2 JP H054517B2
Authority
JP
Japan
Prior art keywords
person
input
judgment
administrator
similarity
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 - Lifetime
Application number
JP58059555A
Other languages
Japanese (ja)
Other versions
JPS59185269A (en
Inventor
Yasushi Ishikawa
Kunio Nakajima
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 JP58059555A priority Critical patent/JPS59185269A/en
Publication of JPS59185269A publication Critical patent/JPS59185269A/en
Publication of JPH054517B2 publication Critical patent/JPH054517B2/ja
Granted legal-status Critical Current

Links

Landscapes

  • Lock And Its Accessories (AREA)
  • Collating Specific Patterns (AREA)
  • Burglar Alarm Systems (AREA)

Description

【発明の詳細な説明】 この発明は、掌紋、指紋、音声等の個人に特有
なパターンの比較による本人確認装置を用いる入
出門管理システムに関するものである。
DETAILED DESCRIPTION OF THE INVENTION The present invention relates to an entrance/exit management system using an identification device that compares patterns unique to individuals such as palm prints, fingerprints, and voices.

掌紋、指紋、音声等に含まれる個人に特有の特
徴パターンを記憶しておき、入力された特徴パタ
ーンとの類似度を求め、本人か否かを判定する本
人確認装置を用いれば登録者以外の入、出門を禁
ずるビル等の入出門管理を行うことができる。と
ころで本人確認装置においては類似度がある閾値
以上なら本人とし、閾値より下ならば詐称者と判
定するが、100%の認識率を得ることは不可能で
あり、誤認識として本人が拒否される場合、又は
詐称者が受理される場合がある。そのため本人確
認装置の判定結果のみで入出門管理を行うことは
困難である。また、本人認識装置として、音声の
特徴パターンの比較により話者照合装置を用いる
場合、音声の経時変化に対応するため、記憶され
ている登録者の参照パターンを入力パターンを用
いて更新することが考えられるが、詐称者を本人
として受理する誤認識を行つた場合、詐称者の入
力パターンが参照パターン更新に用いられる危険
性もあり、またそれを避けようとする類似度が比
較的小さい本人の入力パターンが参照パターン更
新に利用できず、有効な更新ができず認識率の低
下につながるという欠点もあつた。
If you use an identity verification device that memorizes characteristic patterns unique to individuals, such as palm prints, fingerprints, and voices, and determines the degree of similarity with the input characteristic pattern, it is possible to identify someone other than the registrant. Entrance/exit control can be performed for buildings, etc., where entry and exit are prohibited. By the way, in an identity verification device, if the degree of similarity is above a certain threshold, it is determined to be the real person, and if it is below the threshold, it is judged to be an impostor, but it is impossible to obtain a 100% recognition rate, and the person is rejected as a false recognition. or an impostor may be accepted. Therefore, it is difficult to perform entrance/exit management based only on the determination results of the personal identification device. Furthermore, when a speaker verification device is used as a person recognition device by comparing voice feature patterns, the stored reference pattern of the registrant may be updated using the input pattern in order to cope with changes in voice over time. This is possible, but if a misrecognition is made in which the impostor is accepted as the principal, there is a risk that the imposter's input pattern will be used to update the reference pattern. Another drawback was that the input pattern could not be used to update the reference pattern, making it impossible to update effectively and leading to a decrease in recognition rate.

この発明は、これらの欠点を改善するためにな
されたもので、誤認識の減少、および参照パター
ン更新の有効な学習機能を備えた入出門管理シス
テムを提案するもので、以下本人確認装置として
話者照合装置を用いた場合を例にこの発明を詳細
に説明する。
This invention was made to improve these drawbacks, and proposes an entrance/exit management system that reduces false recognition and has an effective learning function for updating reference patterns. The present invention will be explained in detail by taking as an example a case in which a person verification device is used.

第1図はこの発明による入出門管理システムの
一構成例を示すものであり、1a,1bはドア、
2a,2bはドア1a,1bを自動開閉させるド
ア制御装置、3は登録番号入力装置、4はマイク
ロフオン、5は話者照合装置、6はテレビカメ
ラ、7は管理者のいる部屋に置かれる話者照合装
置5の判定結果の表示および管理者が判定入力を
行う端末装置、8は登録者の肖像画像情報を記録
している記憶装置、9はテレビカメラ6の画像お
よび記録装置8に記憶されている画像を表示する
表示装置である。
FIG. 1 shows an example of the configuration of an entrance/exit management system according to the present invention, in which 1a and 1b are doors,
2a and 2b are door control devices that automatically open and close the doors 1a and 1b, 3 is a registration number input device, 4 is a microphone, 5 is a speaker verification device, 6 is a television camera, and 7 is placed in the room where the administrator is located. A terminal device for displaying the judgment results of the speaker verification device 5 and for the administrator to input the judgment; 8 a storage device for recording portrait image information of the registrant; 9 an image of the television camera 6 and storage in the recording device 8; This is a display device that displays images that are being displayed.

次に図を用いてこの発明の動作について説明す
る。入門もしくは出門しようとする者は通常開か
れているドア1aを通り、登録番号を登録番号入
力装置3に入力し、話者照合装置内の自分の参照
パターンを要求し、マイクロフオン4に向い決め
られた言葉を発声する。話者照合装置5では入力
音声を特徴パラメータのパターンに変換し、先に
要求された参照パターンと比較を行い類似度を求
める。第2図は登録した本人が発声した場合と、
本人以外の詐称者が発生した場合の類似度分布を
示す図であり、アは本人の、イの詐称者の類似度
の分布である。またL1、L2は判定に用いる閾値
である。話者照合装置5では求めた類似度を閾値
との比較が行われ、類似度がL2より大きい場合、
入力者は本人であるという判定結果を、またL1
より小さい場合、入力者は詐称者であるという判
定結果を得る。一方類似度がL1、L2間の値とな
つた場合は判定を保留する。判定保留となつた場
合は管理者に判定保留が起きたことを端末装置7
上に表示し通報すると共に、登録番号が記憶装置
8に送られ、記憶されている登録者の肖像画像が
話者照合装置5からの信号で動作を開始したテレ
ビカメラ6の画像と共に表示装置9に表示され
る。管理者は両画像を比較し、入力者が本人であ
るか詐称者であるかの判定結果を端末装置7から
話者照合装置5に送信する。話者照合装置5およ
び管理者の判定情報により、入力者が本人と判定
された場合はドア制御装置2bに信号が送られ、
ドア1bが開き入門もしくは出門を許可する。ま
た詐称者と判定された場合は、ドア制御装置2a
に信号が送られ、ドア1aが閉じ、詐称者を拘束
すると共に、端末装置7に詐称者が進入したこと
を表示し、テレビカメラ6が動作し表示装置9に
映像を写す。一方話者照合装置5における参照パ
ターンの更新において、管理者の判定情報を利用
することで、類似度がL1、L2間にある場合につ
いても本人の入力パターンのみを更新に利用する
ことが可能となり、効果的な学習を行うことがで
き、話者照合装置5の認識率の向上を計ることが
できる。なおここでは話者照合装置を用いて説明
したが、掌紋、指紋等を個人性特徴パターンとし
て用いる本人確認装置においても、第2図に示す
類似度分布と同様の類似度分布が得られるため動
作は話者照合装置の場合と同様である。
Next, the operation of the present invention will be explained using the drawings. A person wishing to enter or exit the gate passes through the normally open door 1a, enters the registration number into the registration number input device 3, requests his or her reference pattern in the speaker verification device, and faces the microphone 4. utter the words that were asked. The speaker matching device 5 converts the input speech into a pattern of feature parameters, and compares the pattern with the previously requested reference pattern to determine the degree of similarity. Figure 2 shows the case where the registered person speaks,
It is a diagram showing the similarity distribution when an impostor other than the principal occurs, where A is the distribution of similarity between the principal and B the impostor. Further, L 1 and L 2 are threshold values used for determination. The speaker matching device 5 compares the obtained degree of similarity with a threshold value, and if the degree of similarity is greater than L2 ,
The judgment result that the inputter is the person himself or herself, and the L 1
If it is smaller than that, a determination result is obtained that the inputter is an impostor. On the other hand, if the similarity is between L 1 and L 2 , the determination is suspended. If the judgment is pending, the terminal device 7 informs the administrator that the judgment is pending.
At the same time, the registration number is sent to the storage device 8, and the stored portrait image of the registrant is displayed on the display device 9 together with the image of the television camera 6 that started operating in response to the signal from the speaker verification device 5. will be displayed. The administrator compares both images and transmits the determination result as to whether the input person is the real person or the impostor from the terminal device 7 to the speaker verification device 5. If the person making the input is determined to be the person himself or herself based on the determination information of the speaker verification device 5 and the administrator, a signal is sent to the door control device 2b.
Door 1b opens to allow entry or exit. In addition, if it is determined that the person is an impostor, the door control device 2a
A signal is sent to the door 1a, the door 1a is closed, the impostor is restrained, the terminal device 7 displays that the imposter has entered, and the television camera 6 is operated to project an image on the display device 9. On the other hand, when updating the reference pattern in the speaker verification device 5, by using the administrator's judgment information, even if the degree of similarity is between L1 and L2 , only the person's input pattern can be used for updating. This makes it possible to perform effective learning and improve the recognition rate of the speaker verification device 5. Although the explanation has been made using a speaker verification device, an identity verification device that uses palm prints, fingerprints, etc. as personal characteristic patterns can also operate because a similarity distribution similar to that shown in Fig. 2 can be obtained. is the same as in the case of the speaker verification device.

以上説明したように、本願発明によれば入出門
管理者の判断結果を用いて標準パターンの更新を
行うことで、利用者の負担を増すことなしに標準
パターンの適正な更新による効果的な学習が可能
となるという効果がある。
As explained above, according to the present invention, by updating the standard pattern using the judgment result of the entrance/exit manager, effective learning can be achieved by appropriately updating the standard pattern without increasing the burden on the user. This has the effect of making it possible.

【図面の簡単な説明】[Brief explanation of the drawing]

第1図はこの発明による入出門管理システムの
一構成例を示す構成図、第2図は本人確認装置に
おける入力パターン参照パターン間の類似度の本
人、詐称者別の分布と閾値の関係を示す図であ
る。 図中、1a,1bはドア、2a,2bはドア制
御装置、3は登録番号入力装置、4はマイクロフ
オン、5は話者照合装置、6はテレビカメラ、7
は端末装置、8は記録装置、9は表示装置であ
る。
Fig. 1 is a block diagram showing an example of the configuration of the entrance/exit management system according to the present invention, and Fig. 2 shows the relationship between the distribution of similarity between reference patterns of input patterns in an identity verification device for each person and impostor, and the threshold value. It is a diagram. In the figure, 1a and 1b are doors, 2a and 2b are door control devices, 3 is a registration number input device, 4 is a microphone, 5 is a speaker verification device, 6 is a television camera, and 7
8 is a terminal device, 8 is a recording device, and 9 is a display device.

Claims (1)

【特許請求の範囲】[Claims] 1 入力された個人に特有の特徴パターンと、あ
らかじめ記憶されている参照パターン間の類似度
を多重閾値判定し、類似度が誤識別を生じる領域
にある場合判定保留する本人確認装置と、判定保
留の場合管理者に確認を行わせる登録者の肖像画
像の記憶装置と入力者を写すテレビカメラと、そ
の両画像を比較表示する表示装置と、管理者が判
定結果を入力しその結果を本人確認装置ならびに
ドア制御装置に送信する端末装置と、本人確認装
置および管理者の判定情報によりドアの自動開閉
を行うドア制御装置とを持つ入出門管理システム
において、本人確認装置の類似度閾値判定により
入力者を本人と判定した場合に加え、類似度閾値
判定により判定保留の条件下で端末装置から受信
した管理者の判定情報が入力者を本人と判定した
ことを表す場合にも、入力パターンにより参照パ
ターンの更新学習を行うように該本人確認装置を
構成したことを特徴とする入出門管理システム。
1. An identity verification device that performs multi-threshold judgment on the degree of similarity between an input characteristic pattern unique to an individual and a pre-stored reference pattern, and suspends the determination if the degree of similarity is in an area that would cause erroneous identification; In this case, the administrator is required to confirm the registrant's portrait image storage device, a television camera that captures the input person, a display device that compares and displays both images, and the administrator inputs the judgment result and confirms the identity of the person. In an entrance/exit management system that has a terminal device that sends information to the device and door control device, and a door control device that automatically opens and closes the door based on the identification information of the identification device and the administrator, input data is input based on the similarity threshold judgment of the identification device. In addition to cases in which the person is judged to be the person in question, reference is also made to the input pattern when the administrator's judgment information received from the terminal device indicates that the user is judged to be the person in question under judgment pending conditions due to similarity threshold judgment. An entry/exit management system characterized in that the identification device is configured to perform pattern update learning.
JP58059555A 1983-04-05 1983-04-05 Entrance and exit control system Granted JPS59185269A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP58059555A JPS59185269A (en) 1983-04-05 1983-04-05 Entrance and exit control system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP58059555A JPS59185269A (en) 1983-04-05 1983-04-05 Entrance and exit control system

Publications (2)

Publication Number Publication Date
JPS59185269A JPS59185269A (en) 1984-10-20
JPH054517B2 true JPH054517B2 (en) 1993-01-20

Family

ID=13116610

Family Applications (1)

Application Number Title Priority Date Filing Date
JP58059555A Granted JPS59185269A (en) 1983-04-05 1983-04-05 Entrance and exit control system

Country Status (1)

Country Link
JP (1) JPS59185269A (en)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0631548Y2 (en) * 1986-05-30 1994-08-22 三菱電機株式会社 Fingerprint matching device
JPS63276681A (en) * 1987-05-08 1988-11-14 Nippon Denso Co Ltd Device for collating fingerprint
KR920002928B1 (en) * 1989-11-28 1992-04-10 한국과학기술연구원 Fingerprint Identification Method
JPH10222773A (en) * 1997-01-31 1998-08-21 U S C:Kk Building security system
KR100360540B1 (en) * 2000-04-28 2002-11-13 주식회사 케이코하이텍 Entrance control system and method
JP2004172680A (en) * 2002-11-15 2004-06-17 Sony Corp Doorphone device and communication system
JP2006134081A (en) * 2004-11-05 2006-05-25 Toshiba Corp Admission management system, admission control terminal, and admission management method
JP4959428B2 (en) * 2007-06-05 2012-06-20 三菱電機株式会社 Access control system
JP4556977B2 (en) * 2007-09-10 2010-10-06 沖電気工業株式会社 Identification system
JP5623110B2 (en) * 2010-03-31 2014-11-12 綜合警備保障株式会社 Monitoring device and monitoring method
JP5936100B2 (en) * 2011-08-11 2016-06-15 シンフォニアテクノロジー株式会社 Work sorting device
JP6333534B2 (en) * 2013-10-01 2018-05-30 Next Innovation合同会社 Attribute identification system
JP6123653B2 (en) * 2013-11-28 2017-05-10 キヤノンマーケティングジャパン株式会社 Information processing apparatus, information processing method, and program
JP2017152013A (en) * 2017-04-05 2017-08-31 キヤノンマーケティングジャパン株式会社 Information processing device, information processing method, and program
JPWO2023189173A1 (en) * 2022-03-29 2023-10-05

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5681781A (en) * 1979-12-05 1981-07-04 Nippon Electric Co Sound lock system
JPS6324540Y2 (en) * 1981-05-11 1988-07-05

Also Published As

Publication number Publication date
JPS59185269A (en) 1984-10-20

Similar Documents

Publication Publication Date Title
US6794986B2 (en) Access control method and apparatus for members and guests
US7110580B2 (en) Distributed biometric access control method and apparatus
JPH054517B2 (en)
US7006672B2 (en) Entrance management apparatus and entrance management method
US6111517A (en) Continuous video monitoring using face recognition for access control
EP2913799A2 (en) System and method having biometric identification intrusion and access control
KR20020081121A (en) Personal authentication method and device
WO2001091038A9 (en) Distributed biometric access control apparatus and method
JP2006031103A (en) Biometric authentication device, biometric authentication method, and traffic control device
JPH08115422A (en) Personal identification device
JP2005084824A (en) Face image matching device, face image matching method, and traffic control device
JP2006215858A (en) Entrance / exit management system and entrance / exit management method
JP2003036442A (en) Device for authenticating individual
KR20020032048A (en) Face cognition the preservation a means
JP2000339507A (en) Security system including room entry restriction release means
KR101926709B1 (en) Control apparatus for biometric and method thereof
JP2005272088A (en) Door control apparatus and method
JP4705511B2 (en) Face image matching device
JPH0896135A (en) Traffic control device
JP4705512B2 (en) Face image matching device
JP2006059242A (en) Biometric authentication device and traffic control device
JPH1063858A (en) Method for identifying individual and device therefor
JPH0243185A (en) Elevator system
JP2006059230A (en) Access control system
JP2001140518A (en) Traffic control device