EP1516278A2 - Procede et dispositif d'identification de personnes - Google Patents

Procede et dispositif d'identification de personnes

Info

Publication number
EP1516278A2
EP1516278A2 EP03740072A EP03740072A EP1516278A2 EP 1516278 A2 EP1516278 A2 EP 1516278A2 EP 03740072 A EP03740072 A EP 03740072A EP 03740072 A EP03740072 A EP 03740072A EP 1516278 A2 EP1516278 A2 EP 1516278A2
Authority
EP
European Patent Office
Prior art keywords
face
hand
area
optical sensor
detected
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.)
Withdrawn
Application number
EP03740072A
Other languages
German (de)
English (en)
Inventor
Günter DOEMENS
Frank Forster
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.)
Siemens AG
Original Assignee
Siemens AG
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 Siemens AG filed Critical Siemens AG
Publication of EP1516278A2 publication Critical patent/EP1516278A2/fr
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • 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
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation

Definitions

  • the invention relates to a method for recognizing people, in which a part of the face of a person to be recognized is detected with the aid of an optical sensor and evaluated in an evaluation unit.
  • the invention further relates to a device for person recognition with an optical sensor which interacts with an evaluation unit.
  • biometric methods The automatic identification or verification of people using biometric methods will become increasingly important in the future.
  • the aim of the further development of the biometric methods is increased recognition and deception security with simultaneous high user acceptance and low costs.
  • One area of application of the biometric method is primarily to monitor the access authorization of buildings and rooms and to monitor the access authorization to electronic systems.
  • biometric methods Two-dimensional face recognition, fingerprint evaluation, iris recognition, hand recognition and speaker recognition.
  • biometric methods None of the biometric methods has been widely adopted. This is mainly due to the limited detection security, the partly lack of user acceptance or the high system costs.
  • the recognition of fingerprints is problematic because, for reasons of hygiene, users sometimes refuse to put their hand or a finger on a sensor surface.
  • the detection of the iris of a person to be recognized is also critical because of the person-detectable with it Information not wanted on many sides. Iris detection is therefore sometimes rejected for data protection reasons.
  • two-dimensional or three-dimensional facial recognition offers significant advantages. Because two-dimensional or three-dimensional face recognition is a non-contact process that is harmless under data protection law. However, two-dimensional face recognition does not achieve the required reliability. The typical recognition rate is around 95%, with the person to be recognized being incorrectly rejected in 5% of the cases. Conversely, around 0.5% of unauthorized persons are mistakenly recognized and approved. Therefore, biometric methods are currently under development in which face recognition is carried out in three dimensions. By using three-dimensional face recognition, the recognition rate will improve significantly. However, there is still a need for further improved methods with increased recognition values, which should be achieved as far as possible without significant additional costs.
  • the invention is therefore based on the object of creating a contactless biometric method which offers higher reliability values without significantly higher system costs.
  • the invention is also based on the object of providing an apparatus for carrying out the method.
  • the optical sensor in addition to a part of the face, additionally detects a part of the hand to be recognized Person recorded and evaluated by the evaluation unit.
  • This offers the advantage that at least two strongly structured body parts characteristic of the person to be recognized are used to carry out the detection. Since the detection is not only based on the detection of a part of the face, it can be expected that the reliability values when carrying out the method are above the reliability values of a conventional method which relies exclusively on the detection of parts of the face or the hand. As a result, it is also heavier than the
  • a device for carrying out the method is therefore expediently designed such that the optical sensor and the evaluation unit are capable of detecting and recognizing a face part and a hand part of a person to be recognized.
  • the detection and the recognition of the face area and the hand area need not necessarily take place simultaneously.
  • the detection of the area of the face and the area of the hand can, however, also be carried out simultaneously. As a result, the time required to grasp the area of the face and hand is less.
  • the simultaneous detection of the face area and the hand area is carried out in such a way that an upper face area of the person to be recognized is detected and that the detection and recognition of the hand area is carried out in the area of a lower face area.
  • This is advantageous in that the facial area below the upper jaw varies greatly depending on the position of the mouth and beard and is therefore only of limited use for identifying and verifying people.
  • Figure 1 is a schematic representation of an apparatus for performing the method.
  • FIG. 2 shows the part of the face and hand that was evaluated when the method was carried out.
  • FIG. 1 shows a person 1 to be recognized, whose two-dimensional or three-dimensional image is recorded by an optical sensor 2.
  • the optical sensor 2 is connected to an evaluation unit 3.
  • the optical sensor 2 detects the facial area 4 shown in FIG. 2, which preferably begins at the upper jaw and extends to the forehead area. In addition, the optical sensor 2 detects a part of the hand 5 which preferably extends below the part of the face 4 when the person to be recognized holds his hand near the mouth.
  • the optical sensor 2 can be designed such that it is able to provide both a two-dimensional and a three-dimensional image of the face part 4 and the hand part 5. Both the hand section 5 and the face section 4 lie within an overall field of view 6 of the optical sensor 2. A single optical sensor is therefore sufficient to carry out the method. The method can therefore be carried out without significantly higher system costs. In a modified method with higher system costs, two or more optical sensors can also be used, for example to detect body parts of the user from different perspectives.
  • the usual imaging methods are used to generate a two-dimensional image of the face part 4 and the hand part 5.
  • the so-called triangulation is particularly suitable for generating a three-dimensional image of the face part 4 and the hand part 5.
  • the scanning of the face area 4 and the hand area 5 with the aid of a laser scanner or with the aid of the light section method can be considered. Both methods are known to the person skilled in the art and as such are not the subject of the application.
  • the light section method is particularly advantageous, since in this case a three-dimensional image of the face part 4 and the hand part 5 can be generated within 40 ms. In this respect, it is ensured that the three-dimensional image of the face part 4 and the hand part 5 is not falsified by a possible movement of the person to be detected.
  • the quick three-dimensional detection of face and hand can easily determine whether the detected object is a fake with rigid masks, since a movement of the face or hand can be detected with the help of successive detection processes.
  • the detection accuracy can therefore be improved further if a movement characteristic of the user is recorded and evaluated.
  • Such a movement can be, for example, the movement of a finger on one hand.
  • Such a movement can only be simulated with great effort with a mask.
  • the two-dimensional imaging of the face part 4 and the hand part 5 is not absolutely necessary.
  • the two-dimensional detection of the face part 4 and the hand part 5 can be used to determine the spatial areas to be detected for the three-dimensional detection by the two-dimensional detection of the face part 4 and the hand part 5, since in general the person 1 to be recognized holds the hand at different points leads to the face.
  • the two-dimensional image of the person 1 can be used to determine the position of the hand area 5 in relation to the face area 4.
  • Another advantage is that the process described here can be carried out quickly and without contact. It can therefore be expected that the procedure described here will be generally accepted by users.
  • both hands of the person to be recognized can also be detected and evaluated.
  • the contactlessly operating sensor according to this invention would have to be sent in for a series inspection and in critical cases a speech recognition or a fingerprint can be used.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Health & Medical Sciences (AREA)
  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Image Input (AREA)

Abstract

L'invention vise à améliorer la reconnaissance biométrique de personnes (1) à l'aide d'un seul capteur optique. A cet effet, le procédé selon l'invention consiste à détecter et à évaluer de façon tridimensionnelle une partie du visage (4) ainsi qu'une partie de la main (5) de la personne (1) devant être identifiée.
EP03740072A 2002-06-18 2003-06-10 Procede et dispositif d'identification de personnes Withdrawn EP1516278A2 (fr)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
DE10227167 2002-06-18
DE10227167A DE10227167A1 (de) 2002-06-18 2002-06-18 Verfahren und Vorrichtung zur Personenerkennung
PCT/DE2003/001911 WO2003107258A2 (fr) 2002-06-18 2003-06-10 Procede et dispositif d'identification de personnes

Publications (1)

Publication Number Publication Date
EP1516278A2 true EP1516278A2 (fr) 2005-03-23

Family

ID=29723231

Family Applications (1)

Application Number Title Priority Date Filing Date
EP03740072A Withdrawn EP1516278A2 (fr) 2002-06-18 2003-06-10 Procede et dispositif d'identification de personnes

Country Status (4)

Country Link
US (1) US20050238206A1 (fr)
EP (1) EP1516278A2 (fr)
DE (1) DE10227167A1 (fr)
WO (1) WO2003107258A2 (fr)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2007000504A1 (fr) * 2005-06-27 2007-01-04 France Telecom Procede de reconnaissance biometrique d'une main, systeme et dispositif associes
US8244025B2 (en) * 2006-03-20 2012-08-14 Siemens Energy, Inc. Method of coalescing information about inspected objects
US8477154B2 (en) * 2006-03-20 2013-07-02 Siemens Energy, Inc. Method and system for interactive virtual inspection of modeled objects
US7689003B2 (en) * 2006-03-20 2010-03-30 Siemens Energy, Inc. Combined 2D and 3D nondestructive examination
CN109426762B (zh) * 2017-08-22 2021-03-23 深圳荆虹科技有限公司 一种生物识别系统、方法和生物识别终端

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SE440961B (sv) * 1983-12-29 1985-08-26 Ericsson Telefon Ab L M Anordning for att med hjelp av karakteristiska drag hos en persons hand verifiera personens identitet
US5689575A (en) * 1993-11-22 1997-11-18 Hitachi, Ltd. Method and apparatus for processing images of facial expressions
US6714665B1 (en) * 1994-09-02 2004-03-30 Sarnoff Corporation Fully automated iris recognition system utilizing wide and narrow fields of view
WO1999053430A1 (fr) * 1998-04-13 1999-10-21 Eyematic Interfaces, Inc. Architecture video pour decrire les traits de personnes
DE19901881A1 (de) * 1999-01-19 2000-07-27 Dcs Dialog Communication Syste Verfahren und System zur Fälschungssicherung bei biometrischer Personenerkennung
JP2000293687A (ja) * 1999-02-02 2000-10-20 Minolta Co Ltd ３次元形状データ処理装置および３次元形状データ処理方法
JP4810052B2 (ja) * 2000-06-15 2011-11-09 オートモーティブ システムズ ラボラトリー インコーポレーテッド 乗員センサ

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See references of WO03107258A2 *

Also Published As

Publication number Publication date
WO2003107258A3 (fr) 2004-02-19
WO2003107258A2 (fr) 2003-12-24
DE10227167A1 (de) 2004-01-15
US20050238206A1 (en) 2005-10-27

Similar Documents

Publication Publication Date Title
EP1147494B1 (fr) Procede et systeme de protection contre la fraude en cas de reconnaissance biometrique de personnes
DE69719769T2 (de) Verfahren und vorrichtung zum bestätigen einer persönlichen unterschrift
DE60214014T2 (de) Verfahren und vorrichtung zur prüfung der identität einer person, wobei ein für den fingerabdruck konstantes koordinatensystem der bezug ist
EP1395945B1 (fr) Procede de detection de falsification dans la reconnaissance d'empreintes digitales au moyen d'une classification de texture d'images a valeurs de gris differentielles
DE69932643T2 (de) Identifizierungsvorrichtung mit gesichertem foto sowie mittel und verfahren zum authentifizieren dieser identifizierungsvorrichtung
EP3304501B1 (fr) Procédé de contrôle d'accès électronique
WO1998009246A9 (fr) Procede et installation de reconnaissance d'empreintes digitales non deroulees
WO1998009246A1 (fr) Procede et installation de reconnaissance d'empreintes digitales non deroulees
EP2550645A2 (fr) Dispositif de contrôle d'accès
EP1223538A2 (fr) Reconnaissance des mains avec détection de position
WO1998035118A1 (fr) Systeme d'identification
WO2003107258A2 (fr) Procede et dispositif d'identification de personnes
DE10260642B4 (de) Verfahren zur Erstellung einer Referenz für Fingerprints und zum Vergleich von Fingerprints
DE202020103088U1 (de) Sicherheitsschleuse zur Kontrolle von Personen
DE10123561A1 (de) Verfahren zur Personenidentifikation mittels dreidimensionaler Fingerkuppenanalyse
WO2005045746A1 (fr) Reconnaissance biometrique sans contact
DE19929671C2 (de) Verfahren zum Erkennen eines Bildes als Fingerabdruck
DE102017126207A1 (de) Sensorsystem zur Prüfung von Handvenenmustern
EP2355007A2 (fr) Système et procédé destinés à la mesure d'objet tridimensionnelle
DE10123367B4 (de) Verfahren zur Fingerabdruckerkennung unter Verwendung von Bildsequenzen
WO2001009845A1 (fr) Procede de reconnaissance biometrique
DE3834046A1 (de) Verfahren und vorrichtung zum begrenzen des zugangs zu bestimmten datenbereichen eines rechners
EP1071034A2 (fr) Enregistrement d'empreintes digitales
DE19903568B4 (de) Verfahren zum Messen und Auswerten biometrischer Merkmale eines Fingers
DE102008030088A1 (de) Betrugssicheres biometrisches Verfahren

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

17P Request for examination filed

Effective date: 20041118

AK Designated contracting states

Kind code of ref document: A2

Designated state(s): AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IT LI LU MC NL PT RO SE SI SK TR

RBV Designated contracting states (corrected)

Designated state(s): DE FR GB IT

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20110103