WO2006036086A2 - Procede d'identification biometrique - Google Patents

Procede d'identification biometrique Download PDF

Info

Publication number
WO2006036086A2
WO2006036086A2 PCT/RU2005/000473 RU2005000473W WO2006036086A2 WO 2006036086 A2 WO2006036086 A2 WO 2006036086A2 RU 2005000473 W RU2005000473 W RU 2005000473W WO 2006036086 A2 WO2006036086 A2 WO 2006036086A2
Authority
WO
WIPO (PCT)
Prior art keywords
biometric
biometric parameter
parameter
fingerprint
fake
Prior art date
Application number
PCT/RU2005/000473
Other languages
English (en)
Russian (ru)
Other versions
WO2006036086A3 (fr
Inventor
Panos Razis
Hans Rykaczewski
Ivan Sergeevich Vasiliev
Vitaly Sergeevich Kaftanov
Viktor Albertovich Minkin
Alexandr Iliich Shtam
Original Assignee
Oao 'tsnii 'elektron'
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 Oao 'tsnii 'elektron' filed Critical Oao 'tsnii 'elektron'
Publication of WO2006036086A2 publication Critical patent/WO2006036086A2/fr
Publication of WO2006036086A3 publication Critical patent/WO2006036086A3/fr

Links

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
    • 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
    • G06V40/1382—Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger
    • 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
    • G06V40/40—Spoof detection, e.g. liveness detection

Definitions

  • the invention relates to the field of biometrics and can be used to protect against fake biometric parameters in access control systems and passport systems.
  • biometric systems creates natural prerequisites for the development of systems and methods for falsifying biometric parameters, as well as the development of systems and methods for protecting against tampering with biometric identification.
  • all methods of protection against fake or falsified biometric parameters can be divided into static and dynamic.
  • Static methods of protection should include an additionally determined instantaneous value of a certain physical quantity, which should be inherent in the real biometric parameter and absent in the falsified one.
  • An example of such protection can be the determination of the electrical resistance of the skin of a finger or hand for fingerprint sensors and systems using a special electrode system (RU 2218084, MKI A61B5 / 117, publ. 10.12.2003, US 6175641, MKI A61 B5 / 117B, publ.
  • Another example of static additional protection is the measurement of the temperature of an object and other physiological parameters inherent in humans, which is used both in contact biometric identification systems, for example fingerprint systems (US 5719950, MKI G06K9 / 00, publ. 02.17.1998), and in non-contact systems, for example recognition systems for the face or retina.
  • An additionally measured physical quantity makes it possible in some cases to reject fake biometric media, however, if this physical quantity is known, then it is possible to use it in falsified biometric parameter.
  • To falsify for example, the electrical resistance of the skin, it is sufficient to produce a fake fingerprint of electrically conductive silicone having an electrical resistance similar to that of the skin of a finger.
  • Another possible method of static protection during biometric identification is a detailed analysis of the form of the input biometric parameter.
  • a fake is usually made less qualitatively than the original, which contains a huge number of small parts that are not transmitted during the manufacture of the fake.
  • a fingerprint it can be pores on the skin (poroscopy) or the shape of the edge of the papillary line (ejoscopy), which differ significantly on the original and the fake.
  • ejoscopy the shape of the shape of the biometric parameter
  • the known method includes reading information about a user's biometric parameter - registering a pulse wave by illumination of a blood-bearing tissue, converting the light flux caused by scattering on a blood-bearing tissue into an electrical signal using an optoelectronic converter, processing the resulting pulse wave using several photosensitive regions located nearby places of a blood-bearing tissue, comparison of the received information with a sample and protection against fake biometrics th parameter using information about the volume pulse (RU 2199943, MKI A61 B5 / 02, publ.
  • the method allows to successfully identify fake carriers of a fingerprint image in the presence of a normal peripheral pulse in the fingertips.
  • the peripheral pulse in a person may be practically absent, there is also a significant decrease in the peripheral pulse associated with a decrease in the size of microcapillaries, for example, when the body is cooled, or when the person is nervous. This property significantly limits the use of this method to detect fake fingerprint media.
  • this method of protection is applicable only to systems operating in the light passing through the object, and these systems form an insignificant part of the biometric market.
  • the proposed method solves the problem of increasing the reliability of the biometric identification system by reducing errors in identifying fake biometric media.
  • a fingerprint is used as a biometric parameter, and the mechanical movement of the fingerprint is measured by the time dependence of the area of the contact surface of the fingerprint.
  • the contact surface area of the fingerprint is determined using the parameters of the distribution density of the signal of the biometric carrier, for example, the width of the standard deviation.
  • the mechanical movement of the biometric parameter is measured using the time dependence of the integral value, for example, the center of gravity of the given biometric parameter.
  • Human skin is a complex multilayer structure (Skin (Structure, Function, General Pathology and Therapy), edited by E. P. Frolov, Moscow, Medicine, 1982), the mechanical properties of which are rather difficult to fake, because the surface layer of the skin consists of individual keratinized cells, and almost all fakes are made of monolithic material.
  • the fingers of a person have a certain elasticity, which is usually significantly different for people engaged in physical or mental labor.
  • the fingers which can be conditionally called rigid, move more along the horizontal axis, and the fingers, which can be conditionally called soft, make more movement along the vertical axis, with the amplitude, frequency and phase of these movements are synchronized with the passage of the pulse wave in the human body.
  • the authors were able to establish that this effect is also observed with the practical absence of a peripheral pulse at the fingertips, i.e. when the transparency of the fingers practically does not change due to the narrowing of the microcapillaries.
  • the observed phenomenon significantly reduces the possibility of manufacturing undetectable fake carriers of biometric and, above all, fingerprint information, because copying the properties of skin elasticity in addition to all other parameters is an intractable task.
  • the proposed method of biometric identification is especially important for use as part of a biometric passport system, the cost of which can be several billion dollars, and the cost of the production of a fake biometric parameter may not exceed only 100 US dollars (T. Matsumoto, H. Matsumoto, K Yamada, S. Butsho, “Fipegs on Fixture Systems. Proceedings of SPIE, vol. 4677, Japan, 2002.). Moreover, if the passport system is not able to identify a fake carrier of biometric information, then all the money will be wasted on it if the passport system is not equipped with a reliable system of protection against fake biometric carriers.
  • FIG. 1 shows a structural diagram of the proposed method of biometric identification.
  • FIG. Figure 2 shows the graphs of pulse waves obtained simultaneously for a real finger with a pronounced peripheral pulse: a) when measuring the temporal dependence of the "transparency" of the finger; b) when measuring the time dependence of the standard deviation (CKO); c) when measuring the time dependence of the mathematical center of gravity.
  • FIG. Figure 3 shows the graphs of pulse waves for a practically absent peripheral pulse: a) on a real finger when measuring the temporal dependence of the "transparency" of the finger; b) on a real finger when measuring the time dependence of CKO; c) on a real finger when measuring the time dependence of the mathematical center of gravity.
  • FIG. Figure 4 shows the graphs of pulse waves for a falsified biometric parameter mounted on a real finger: a) when measuring the temporal dependence of the "transparency" of the finger; b) when measuring the time dependence of CKO; c) when measuring the time dependence of the mathematical center of gravity.
  • FIG. Figure 5 shows the distribution density of the signal from a fingerprint scanner at the time the pulse wave passes through the finger (a) and in the normal state (b).
  • Reading information about the biometric parameter of the user is carried out by installing the user's finger in a fingerprint scanner DC21 P (see the information on the website www.elsls.ru dated 06.2004) connected to the SAMsupg REO personal computer via a parallel port operating in EPP mode. Sample information, i.e. the original print was pre-recorded in the database, as well as on a plastic card (passport) of the user (see information on the website www.elsls.ru dated 06.2004).
  • the DC Test Pulse program downloaded to a personal computer, initially compares the scanned fingerprint with the fingerprint stored in the database (with the sample), and then verifies the authenticity of the input biometric parameter, revealing the coincidence of the frequency components of the pulse waves using a fast Fourier transform for pulse curves obtained by various calculation methods and from different areas of the fingerprint.
  • the measurement results are displayed by software biometric identification on the PC screen and on an external control device. Authentication and comparison of motion parameters is carried out by analyzing the resulting spectrum of fundamental frequencies in 5 seconds. Naturally, the absence of pulse displacements or their variability of more than a certain threshold of 20% generates a "No" signal when comparing motion parameters, and the system returns to a new cycle of reading biometric information.
  • the authentication is considered to be positive, and the fingerprint image obtained is compared with the sample, after which a conclusion is made about the identification result. Otherwise, when there is no mechanical movement of the fingerprint or its variability exceeds 20%, the biometric parameter is rejected as fake and the system returns to the original reading and gives a warning sound signal.
  • the fingerprint reading frequency for the DC21 P scanner is 50 frames / s, which is quite sufficient for reliable pulse recording, and the P1600M computer power is sufficient for real-time recording of pulse waves and user identification. Let us explain the pulse curves shown in Fig 2.
  • FIG. Figure 3 shows the pulse curves for a person with a weak peripheral pulse. Studies have shown that under normal conditions, about 5 - 10% of people have this picture, and with cooling or stress, this percentage increases. These curves show that pulse waves during mechanical movement of the finger are less sensitive to peripheral pulse than a change in transparency, which means they more reliably characterize the live finger.
  • FIG. Figure 4 shows the pulse curves for the most complex, from the point of view of detecting a fake, fake finger when a transparent silicone thin pad with someone else's three-dimensional is installed on a real finger
  • the absence of a mechanical pulse in the finger may indicate the presence of a fake fingerprint carrier and give a signal about the possible falsification of the system, which is especially important for passport technology, in which it is necessary to confidently distinguish the image of a fingerprint on a document from a living finger.
  • FIG. Figure 5 shows the change in the density distribution of the fingerprint signal during the passage of the pulse wave, when the finger is pressed closer to the contact surface (Fig. 5a) and the distribution width and CKO are significantly reduced compared to the time when the blood density in the finger decreases (Fig. 5b). Since CKO is an integral and relative characteristic, it turned out that the temporal dependence of CKO is slightly sensitive to noise and artifacts and transmit pulse parameters well. It is possible to use other mathematical characteristics that reflect the distribution width or the distance between modes (distribution maxima) to obtain a pulse dependence.
  • biometric identification does not limit the possible applications of the present invention, which can be much wider and determined by the level of technology development.
  • biometric technology in this description was used fingerprint technology, as the most common and having the best characteristics.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Collating Specific Patterns (AREA)
  • Image Input (AREA)

Abstract

La présente invention relève du domaine de la biométrie et peut être utilisée pour la protection contre des paramètres biométriques falsifiés dans des systèmes de commande d'accès et des systèmes de passeport. Cette invention concerne en particulier un procédé consistant à lire (entrer) des renseignements concernant un paramètre biométrique d'un utilisateur, à comparer les renseignements reçus à un modèle et à protéger le système contre un paramètre biométrique falsifié. Pour accroître la fiabilité d'un système d'identification biométrique en réduisant le nombre d'erreurs tout en détectant les supports biométriques falsifiés, il convient d'assurer la protection contre un paramètre biométrique falsifié selon un procédé consistant à mesurer un mouvement mécanique d'un paramètre biométrique donné, à déterminer des paramètres de mouvement propres audit paramètre biométrique et à écarter le paramètre biométrique entré considéré comme falsifié lorsque ledit paramètre s'éloigne d'une norme spécifiée. Le paramètre biométrique peut se présenter sous la forme d'une empreinte digitale dont le mouvement mécanique est mesuré sur la base de la dépendance temporelle de la zone de surface de contact de ladite empreinte digitale. La zone de surface de contact de l'empreinte digitale est déterminée à l'aide de paramètres de densité de distribution d'un signal d'un support biométrique, tels que la largeur d'un écart-type.
PCT/RU2005/000473 2004-09-22 2005-09-19 Procede d'identification biometrique WO2006036086A2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
RU2004128951/09A RU2286599C2 (ru) 2004-09-22 2004-09-22 Способ биометрической идентификации
RU2004128951 2004-09-22

Publications (2)

Publication Number Publication Date
WO2006036086A2 true WO2006036086A2 (fr) 2006-04-06
WO2006036086A3 WO2006036086A3 (fr) 2006-07-20

Family

ID=36115901

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/RU2005/000473 WO2006036086A2 (fr) 2004-09-22 2005-09-19 Procede d'identification biometrique

Country Status (2)

Country Link
RU (1) RU2286599C2 (fr)
WO (1) WO2006036086A2 (fr)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2318438C1 (ru) * 2006-11-28 2008-03-10 Дмитрий Евгеньевич Антонов Устройство для получения изображения радужной оболочки глаза
RU2479300C1 (ru) * 2011-08-22 2013-04-20 Андрей Николаевич Алексеев Способ проведения гидромассажных процедур динамического вида
RU2627926C1 (ru) * 2016-07-18 2017-08-14 Самсунг Электроникс Ко., Лтд. Оптическая система для биометрической идентификации пользователя
RU2667373C1 (ru) * 2017-06-06 2018-09-19 Наиль Рафкатович Музафаров Биометрическая система формирования 3D изображения поверхности объекта или его частей
RU2667371C1 (ru) * 2017-06-06 2018-09-19 Наиль Рафкатович Музафаров Биометрическая система формирования изображения вен

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
RU2148274C1 (ru) * 1998-08-17 2000-04-27 Пензенский научно-исследовательский электротехнический институт Способ идентификации личности по особенностям подписи
US6175641B1 (en) * 1995-10-06 2001-01-16 Dermo Corporation, Ltd. Detector for recognizing the living character of a finger in a fingerprint recognizing apparatus
US6181808B1 (en) * 1997-07-29 2001-01-30 Nec Corporation Living body discriminating apparatus
RU2199943C2 (ru) * 2001-02-16 2003-03-10 Многопрофильное предприятие ООО "Элсис" Способ и устройство регистрации пульсовой волны и биометрическая система

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6175641B1 (en) * 1995-10-06 2001-01-16 Dermo Corporation, Ltd. Detector for recognizing the living character of a finger in a fingerprint recognizing apparatus
US6181808B1 (en) * 1997-07-29 2001-01-30 Nec Corporation Living body discriminating apparatus
RU2148274C1 (ru) * 1998-08-17 2000-04-27 Пензенский научно-исследовательский электротехнический институт Способ идентификации личности по особенностям подписи
RU2199943C2 (ru) * 2001-02-16 2003-03-10 Многопрофильное предприятие ООО "Элсис" Способ и устройство регистрации пульсовой волны и биометрическая система

Also Published As

Publication number Publication date
WO2006036086A3 (fr) 2006-07-20
RU2286599C2 (ru) 2006-10-27
RU2004128951A (ru) 2006-03-10

Similar Documents

Publication Publication Date Title
Adeoye A survey of emerging biometric technologies
Baldisserra et al. Fake fingerprint detection by odor analysis
US5787187A (en) Systems and methods for biometric identification using the acoustic properties of the ear canal
Ratha et al. Automated biometrics
US7708695B2 (en) Apparatus and method for detecting blood flow
US20080049987A1 (en) Fingerprint recognition system
WO2016099382A1 (fr) Authentification d'empreinte digitale à l'aide de données de capteur de toucher
Drahanský Liveness detection in biometrics
JP2005270672A (ja) 音響エネルギーを使用する誘導電流の生成および感知
Labati et al. Touchless fingerprint biometrics
Gaur et al. Biometric recognition techniques: a review
US20220300593A1 (en) System and method of biometric identification of a subject
WO2006036086A2 (fr) Procede d'identification biometrique
Drahansky et al. Liveness detection based on fine movements of the fingertip surface
Tiwari et al. A review of advancements in biometric systems
Iula et al. Multimodal biometric recognition based on 3D ultrasound palmprint-hand geometry fusion
Angle et al. Biometrics: A further echelon of security
KR100647088B1 (ko) 생체측정 정보 확인장치 및 그 방법
Pala et al. On the accuracy and robustness of deep triplet embedding for fingerprint liveness detection
RU2309672C2 (ru) Способ распознавания принадлежности отпечатка пальца живому или неживому человеку
Sadasivuni et al. Anti-spoofing device for biometric fingerprint scanners
Barotová Detector of Skin Diseases by Fingerprint Technology
Jain et al. A review on advancements in biometrics
Di Nardo Biometric technologies: functionality, emerging trends, and vulnerabilities
Modi Analysis of fingerprint sensor interoperability on system performance

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A2

Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BW BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE EG ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KM KP KR KZ LC LK LR LS LT LU LV LY MA MD MG MK MN MW MX MZ NA NG NI NO NZ OM PG PH PL PT RO SC SD SE SG SK SL SM SY TJ TM TN TR TT TZ UA UG US UZ VC VN YU ZA ZM ZW

AL Designated countries for regional patents

Kind code of ref document: A2

Designated state(s): GM KE LS MW MZ NA SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HU IE IS IT LT LU LV MC NL PL PT RO SE SI SK TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase