WO2017116331A1 - Stereo palm vein detection method and biometric identification system operating in compliance with said method - Google Patents
Stereo palm vein detection method and biometric identification system operating in compliance with said method Download PDFInfo
- Publication number
- WO2017116331A1 WO2017116331A1 PCT/TR2015/050304 TR2015050304W WO2017116331A1 WO 2017116331 A1 WO2017116331 A1 WO 2017116331A1 TR 2015050304 W TR2015050304 W TR 2015050304W WO 2017116331 A1 WO2017116331 A1 WO 2017116331A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vein
- stereo
- detection method
- palm
- images
- Prior art date
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
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- 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
- G06V40/14—Vascular patterns
Definitions
- the present invention is related to the mapping of a three dimensional vein structure from stereo matched palm vein images and to the usage of this information for biometric identification and for preventing forgery.
- Biometric identification systems have been thought of and developed as being exactly like the human brain and they are two staged systems formed of the recognition and verification stages. They function similarly with each other.
- the recognition stage the records are collected and these records are saved in the related system as a code.
- the verification stage the related person is compared immediately with the records that have been collected and a result is obtained.
- the opening and closing mechanism, locks or the door is connected to the locking unit and a door handle system that is held by the user in order to open the door is provided.
- a door handle system that is held by the user in order to open the door is provided.
- an image of the blood veins is taken from the back of the hand and a comparison of the pre identified blood vein patterns in the system is performed.
- the system controls the unit which carries out the locking and opening procedure in compliance with pattern identification.
- the aim of this invention is to capture the 3 dimension vein image of the veins that have become clear under infrared light, by means of a camera and two different mirrors using the stereo palm vein detection method and the biometric identification system which operates in compliance with said method.
- the aim of this invention is to provide a stereo palm vein detection method and a biometric identification system operating in compliance with this method wherein forgery is prevented and the matching precision of the system is increased by means of the perception of the vein depth by capturing a 3 dimension vein image.
- Figure-1 Is the flow diagram of the stereo palm detection method subject to the invention.
- Figure-2 Is the schematic view of the biometric identification system which operates in compliance with the stereo palm vein detection method subject to the invention.
- the Stereo palm vein detection method (1) subject to the invention comprises the following steps;
- the stereo palm vein detection method (1) and the biometric identification system (2) operating in compliance with said system subject to the invention comprises;
- Infrared led lighting (2.4) which maps out the structure of the veins by illuminating the hand structure via infrared led lamps (2.4),
- a built-in processor camera module (2.6) connected to the built-in processor (2.5), having an infrared filter (2.3) in front of the lens of said camera,
- the human vein structure is specific for each person and can be used for biometric identification.
- systems where security is increased by using a plurality of systems comprising combined biometric identification techniques have tried to be developed.
- the development of systems based on a palm print and palm vein system can be shown as examples. Palm vein tracking systems is a current subject that is frequently encountered in contemporary scientific studies. As it has not been developed into a stable system that has been accepted such as the iris code, this situation enables new studies to be carried out in this field.
- the stereo palm vein detection method (1) and the biometric identification system (2) operating in compliance with this method aims to determine biometric identification of a person from the 3 dimensional vein structures.
- a new method for palm vein recognition systems by means of the stereo palm vein detection method (1) and the biometric identification system (2) operating in compliance with this method and comparison performance is increased. By this means a more stable biometric identification system is provided.
- vein detection methods Two different vein detection methods have been tried which were adaptive threshold and regression based. As vein data which shall provide verification is not present in vein detection methods, the vein images obtained and the compatibility of the right and left camera veins shall be shown as a result.
- the binary result of certain parameters and gray color based images has been established.
- This structure that has been established converts the vein structures into single lines using morphological methods.
- Regression based vein detection algorithm uses the random forest method for classification.
- the values that have been obtained by 32x32 pixel filters are used as a part of a feature vector.
- a feature vector is established with 121 filters.
- Filters are automatic filters that have been established by the system that has been developed in order to find eye veins in center-line extraction algorithms. It has been noted that instead of deciding if a pixel is a vein or not in a system, finding the number of veins gave more successful results.
- the status of being a vein or not has been established according to the distance from the positive data for each pixel by means of the below mentioned formula.
- the constant number 7 has been used for neighborhood.
- the distance of the veins in the system for neighborhood shall be calculated according to the formula below. If we accept that C is the vein point, then Dc represents the distance that must be travelled. d(x) defines the coefficient it shall represent for regression.
- the stereo palm vein detection method (1) and the biometric identification system (2) operating in compliance with this method have been tested in three different ways. In all tests a 30 person set formed of 3 images each has been used. The images have been obtained by mirror A (2.7) and mirror B (2.8). 2 dimension person identification algorithm with an adaptive threshold has resulted with 71% performance. The stereo image result with adaptive threshold has been calculated as 86%. 96%) performance has been obtained by means of the regression based algorithm.
- the RANK table of the regression based stereo person identification algorithm and the maximum affinity histograms have been given in the below tables.
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)
- Image Input (AREA)
Abstract
The present invention is related to mapping the three dimensional vein structure from the palm vein images that have been stereo matched and to use this information in order to perform biometric identification. By means of the invention the veins are clarified under infrared led lighting (2.4), and the three dimensional vein images of the clarified veins are captured by means of a built-in processor camera module (2.6) and two different mirrors; mirror A (2.7) and mirror B (2.8); and as a result the stereo palm vein detection method (1) and biometric identification system (2) operating in compliance with this method is implemented. In conclusion, performance is increased and forgery is prevented.
Description
DESCRIPTION
STEREO PALM VEIN DETECTION METHOD AND BIOMETRIC IDENTIFICATION SYSTEM OPERATING IN COMPLIANCE WITH SAID METHOD
Technical Field
The present invention is related to the mapping of a three dimensional vein structure from stereo matched palm vein images and to the usage of this information for biometric identification and for preventing forgery.
Prior Art
Technology that is rapidly developing in every field nowadays is also forcing us to rapidly change our habits. Many procedures that were being carried out by using an identification card, credit card or passport information are nowadays being carried out using a password, a cipher and pin codes. However before long the disadvantages of such applications have been realized. The personal identification cards are forgotten to be brought along, they are lost, or used by other people, the cipher and passwords are found out by other people or forgotten by the users and this poses a threat in terms of the security of people and institutions. New technologic systems are developed in order to eliminate these problems. Biometric identification systems function with the principle of identification of physical or behavioral characteristics only owned by the person, which differentiate the person from others. Biometric identification systems have been thought of and developed as being exactly like the human brain and they are two staged systems formed of the recognition and verification stages. They function similarly with each other. At the recognition stage the records are collected and these records are saved in the related system as a code. At the verification stage,
the related person is compared immediately with the records that have been collected and a result is obtained.
Previously the systems that have been started to be developed for security purposes have become imperative beyond security for every institution that employs personnel. Said systems are being used for personnel and visitor tracking, and tracking of passage points inside the institution and even dining halls. This technology comprises systems that have the same operation principles but are different in form and as a result from each other, such as examination of fingerprints and hand geometry, comparison of facial characteristics, voice and speech analysis and iris and retina identification.
One of the most important problems relating to the techniques that have been developed is forgery. It is possible to mislead two dimensional approaches with biometric image copies. In order to overcome such problems, either a plurality of biometric information must be used or three dimension information must be used to make it difficult for copying. As vein technologies are limited in terms of visuality and in terms of being copied they stand out as prominent technology to be used against forgery.
In the "Increasing the reliability of Biometric Verification by using 3D face information and palm vein patterns (2010 IEEE Portugal signal workshop)" article of the state of the art that has been published, the usage of three dimensional face information and palm vein information for personal verification has been described. In the first step of this invention the supraorbital stereo image of the eye is obtained by means of fixed cameras.
By means of the images that have been obtained, first of all a canny edge detector and then a customized Hough circle algorithm is used to find the local maximum point. This point is accepted as the eye center and matching is made between stereo images. Identification of the person is carried out by means of feature extraction and hamming distance algorithm. The "Stereo palm vein detection method and the biometric identification system operating in compliance with this system" that is to be described in this document is different from the article "Increasing the reliability of Biometric Verification by using 3D face information and palm vein patterns (2010 IEEE Portugal signal workshop)".
In the Japanese Patent document numbered JP2007054623 A of the known state of the art, a digital imaging system and an algorithm for imaging of the palm blood vein is described. In this invention palm blood veins are shown as a three dimensional image. Images that belong to the blood vein are identified as voxel clusters. However while 3 dimensional blood vein technology described in the Japanese patent document numbered JP2007054623A is used for exact matching, the "stereo palm vein detection method and biometric identification system operating in compliance with said system" that is to be described in this document is different to the known state of the art in terms of the depth map of the connection points of stereo images and in terms of a method using a template matching method based algorithm.
In the International Patent document numbered WO2009154402 A2 a blood vein identification system used for opening and closing of doors is described. This invention makes use of a mechanism to open and close doors using the blood vein identification technique.
The opening and closing mechanism, locks or the door is connected to the locking unit and a door handle system that is held by the user in order to open the door is provided. When the user holds the door an image of the blood veins is taken from the back of the hand and a comparison of the pre identified blood vein patterns in
the system is performed. Following this the system controls the unit which carries out the locking and opening procedure in compliance with pattern identification.
The system described in the International Patent document numbered WO2009154402 A2 differs from the system of the invention when it is taken into consideration that the present system captures stereo image clusters obtained with a palm and double mirror.
Moreover it is understood that the identification algorithm that is to be described in this document is different from the document numbered WO2009154402A2.
Aims of the Invention
The aim of this invention is to capture the 3 dimension vein image of the veins that have become clear under infrared light, by means of a camera and two different mirrors using the stereo palm vein detection method and the biometric identification system which operates in compliance with said method.
The aim of this invention is to provide a stereo palm vein detection method and a biometric identification system operating in compliance with this method wherein forgery is prevented and the matching precision of the system is increased by means of the perception of the vein depth by capturing a 3 dimension vein image.
Detailed description of the Invention
The stereo palm detection method and the biometric identification system operating in compliance with said method developed in order to reach the aims of the invention has been illustrated in the attached figures.
According to the Figures; Figure-1 Is the flow diagram of the stereo palm detection method subject to the invention.
Figure-2 Is the schematic view of the biometric identification system which operates in compliance with the stereo palm vein detection method subject to the invention.
The parts in the figures have each been numbered as listed below;
1. Method
2. System
2.1 Monitor
2.2 Computer
2.3 Infrared filter
2.4 Infrared Led lighting
2.5 Built-in processor
2.6 Built-in processor camera module
2.7 Mirror A
2.8 Mirror B
The Stereo palm vein detection method (1) subject to the invention comprises the following steps;
To convert the images obtained by thresholding of the palm images using Mirror A (27) and Mirror B (2.8) into binary images (100), To obtain refined images by thinning the vein image by means of morphological procedures (110),
- To recognize the vein structure by a regression based algorithm together with HOG (Histogram of gradient) features of the small areas that have been chosen around the thinned image obtained and their distances to the vein center (120),
To carry out the regression based vein extraction process in order to compare the stereo images that have been obtained and recorded beforehand in the system (130),
To determine the separation points on the obtained vein images (140), To carry out depth comparison using these separation points (150), and To determine the response of the system by collecting weighted score data obtained by the comparisons made and by template matching (160).
The stereo palm vein detection method (1) and the biometric identification system (2) operating in compliance with said system subject to the invention comprises;
- A monitor used in order to view the vein images captured from the palm of the user (2.1),
- A computer (2.2) to which the images obtained by the built-in processor (2.5) is transferred to,
- An infrared filter (2.3) placed on the lens of the built-in processor camera module (2.6) in order to map the vein structure of the user,
- Infrared led lighting (2.4) which maps out the structure of the veins by illuminating the hand structure via infrared led lamps (2.4),
- A portable sized computer (2.2) to which the built-in processor camera module (2.6) is connected to and which can carry out image analysis by means of the software present therein,
- A built-in processor camera module (2.6) connected to the built-in processor (2.5), having an infrared filter (2.3) in front of the lens of said camera,
- Mirror A (2.7) and Mirror B (2.8) used to determine the vein depth by the stereo image captured by the built-in processor camera module (2.6).
Aim
The human vein structure is specific for each person and can be used for biometric identification.
In contemporary studies, systems where security is increased by using a plurality of systems comprising combined biometric identification techniques have tried to be developed. The development of systems based on a palm print and palm vein system can be shown as examples. Palm vein tracking systems is a current subject that is frequently encountered in contemporary scientific studies. As it has not been developed into a stable system that has been accepted such as the iris code, this situation enables new studies to be carried out in this field. The stereo palm vein detection method (1) and the biometric identification system (2) operating in compliance with this method aims to determine biometric identification of a person from the 3 dimensional vein structures. A study has been carried out within this scope, on the print out images that have been captured under infrared led lighting (2.4) and whose stereo matching has been carried out using a built-in processor (2.5). The system (2) performs palm vein analysis in order to carry out biometric identification. Infrared led lighting (2.4) is used due to the structure of the blood for vein identification. The veins are clarified by means of infrared led lighting (2.4). At the initial stage, the developed system shall transfer the depth information of the previously calibrated images that have been calibrated under infrared led lighting (2.4) to the system. The significant features shall be ascertained from the information obtained and a three dimension matching shall be carried out via comparison algorithms. Following this initial stage, standard biometric identification procedures are carried out.
A new method is provided for palm vein recognition systems by means of the stereo palm vein detection method (1) and the biometric identification system (2) operating in compliance with this method and comparison performance is increased. By this means a more stable biometric identification system is provided.
Vein Detection
Two different vein detection methods have been tried which were adaptive threshold and regression based. As vein data which shall provide verification is not present in vein detection methods, the vein images obtained and the compatibility of the right and left camera veins shall be shown as a result.
In the adaptive threshold algorithm, the binary result of certain parameters and gray color based images has been established. This structure that has been established, converts the vein structures into single lines using morphological methods.
Regression based vein detection algorithm uses the random forest method for classification. The values that have been obtained by 32x32 pixel filters are used as a part of a feature vector. A feature vector is established with 121 filters. Filters are automatic filters that have been established by the system that has been developed in order to find eye veins in center-line extraction algorithms. It has been noted that instead of deciding if a pixel is a vein or not in a system, finding the number of veins gave more successful results.
The status of being a vein or not has been established according to the distance from the positive data for each pixel by means of the below mentioned formula. The constant number 7 has been used for neighborhood.
( tr i\ \ — x 071 center line f J {,x, l)) - 0 otherwise,
The distance of the veins in the system for neighborhood shall be calculated according to the formula below. If we accept that C is the vein point, then Dc represents the distance that must be travelled. d(x) defines the coefficient it shall represent for regression.
As a result, all of these procedures are carried and the analysis of all pixels of a palm image is carried out to determine how much of the pixels are veins and how much aren't.
Identification
Three different tests have been used for identification. In all of the tests, the opencv library of intel ime template match algorithm is used. The algorithm has a structure such that it returns as normalization, the compatibility of the reference given with the questioned location as 0 to 1 and uses the intensity values of the pixels thereof. The most matching images above a 0.65 threshold value have been accepted to be correct in our tests.
Results
The stereo palm vein detection method (1) and the biometric identification system (2) operating in compliance with this method have been tested in three different ways. In all tests a 30 person set formed of 3 images each has been used. The images have been obtained by mirror A (2.7) and mirror B (2.8). 2 dimension person identification algorithm with an adaptive threshold has resulted with 71% performance. The stereo image result with adaptive threshold has been calculated as 86%. 96%) performance has been obtained by means of the regression based algorithm. The RANK table of the regression based stereo person identification algorithm and the maximum affinity histograms have been given in the below tables.
Maximum affinity histogram of regression based vein detection and person identification algorithm.
Claims
) A stereo palm vein detection method (1) characterized in that it comprises the step of thresholding the palm images by means of Mirror A (2.7) and Mirror B (2.8) and converting said images into binary images (100).
2. ) A stereo palm vein detection method (1) according to claim 1, characterized in that it comprises the step of obtaining a refined image (110) by thinning the vein image using morphological procedures.
3. ) A stereo palm vein detection method (1) according to claim 2, characterized in that it comprises the step of recognition of the vein structure (120) by a regression based algorithm together with the HOG (Histogram of gradient) features of small areas that have been chosen from around the thinned view obtained and their distances to the vein center.
4. ) A stereo palm vein detection method (1) according to claim 3 characterized in that it comprises the step of regression based vein extraction process (130) in order to compare the vein images that have been recorded beforehand with the stereo images obtained in the system.
5. ) A stereo palm vein detection method (1) according to claim 4, characterized in that it comprises the step of determining the separation points (140) on the vein images that have been obtained.
6. ) A stereo palm vein detection method (1) according to claim 5, characterized in that it comprises step of carrying out depth comparison (150) using the separation points.
7. ) A stereo vein detection method (1) according to claim 6, characterized in that it comprises the step of determining the response of the system (160)
by collecting the weighted score of the data obtained via the comparisons made and via template matching.
8.) A biometric identification system (2) operating in compliance with the stereo palm vein detection method (1) according to claim 7, comprising;
- A monitor used in order to view the vein images captured from the palm of the user (2.1),
- A computer (2.2) to which the images obtained by the built-in processor (2.5) is transferred to,
- An infrared filter (2.3) placed on the lens of the built-in processor camera module (2.6) in order to map the vein structure of the user,
- Infrared led lighting (2.4) which maps out the structure of the veins by illuminating the hand structure via infrared led lamps (2.4),
- A portable sized computer (2.2) to which the built-in processor camera module (2.6) is connected to and which can carry out image analysis by means of the software provided therein,
- A built-in processor camera module (2.6) connected to the built-in processor (2.5), having an infrared filter (2.3) in front of the lens of said camera,
Characterized in that it further comprises;
- Mirror A (2.7) and Mirror B (2.8) used to determine the vein depth by the stereo image captured by the built-in processor camera module (2.6).
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TR2015/17592 | 2015-12-30 | ||
TR2015/17592A TR201517592A2 (en) | 2015-12-30 | 2015-12-30 | STEREO PALM VASCULAR DETECTION METHOD AND A SUITABLE BIOMETRIC IDENTITY DETECTION SYSTEM |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2017116331A1 true WO2017116331A1 (en) | 2017-07-06 |
Family
ID=55411724
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/TR2015/050304 WO2017116331A1 (en) | 2015-12-30 | 2015-12-31 | Stereo palm vein detection method and biometric identification system operating in compliance with said method |
Country Status (2)
Country | Link |
---|---|
TR (1) | TR201517592A2 (en) |
WO (1) | WO2017116331A1 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107980140A (en) * | 2017-10-16 | 2018-05-01 | 厦门中控智慧信息技术有限公司 | A kind of recognition methods of vena metacarpea and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007054623A (en) | 2005-08-22 | 2007-03-08 | Siemens Ag | Identifying method for contrast intensified blood vessel in digital image data |
EP2003597A2 (en) * | 2007-06-13 | 2008-12-17 | NEC Corporation | Biometrical feature inputting system, image synthesizing apparatus, and image synthesizing method |
WO2009154402A2 (en) | 2008-06-20 | 2009-12-23 | (주)테크스피어 | Door opening-and-closing mechanism using blood vessel identification technique |
WO2015039102A1 (en) * | 2013-09-16 | 2015-03-19 | Eyeverify | Feature extraction and matching and template update for biometric authentication |
-
2015
- 2015-12-30 TR TR2015/17592A patent/TR201517592A2/en unknown
- 2015-12-31 WO PCT/TR2015/050304 patent/WO2017116331A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2007054623A (en) | 2005-08-22 | 2007-03-08 | Siemens Ag | Identifying method for contrast intensified blood vessel in digital image data |
EP2003597A2 (en) * | 2007-06-13 | 2008-12-17 | NEC Corporation | Biometrical feature inputting system, image synthesizing apparatus, and image synthesizing method |
WO2009154402A2 (en) | 2008-06-20 | 2009-12-23 | (주)테크스피어 | Door opening-and-closing mechanism using blood vessel identification technique |
WO2015039102A1 (en) * | 2013-09-16 | 2015-03-19 | Eyeverify | Feature extraction and matching and template update for biometric authentication |
Non-Patent Citations (5)
Title |
---|
"Increasing the reliability of Biometric Verification by using 3D face information and palm vein patterns", IEEE PORTUGAL SIGNAL WORKSHOP, 2010 |
HEESEUNG CHOI ET AL: "Mosaicing Touchless and Mirror-Reflected Fingerprint Images", IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY, IEEE, PISCATAWAY, NJ, US, vol. 5, no. 1, 1 March 2010 (2010-03-01), pages 52 - 61, XP011328949, ISSN: 1556-6013, DOI: 10.1109/TIFS.2009.2038758 * |
S.A. NENE ET AL: "Stereo with mirrors", SIXTH INTERNATIONAL CONFERENCE ON COMPUTER VISION (IEEE CAT. NO.98CH36271), 1 January 1998 (1998-01-01), pages 1087 - 1094, XP055297975, ISBN: 978-81-73-19221-0, DOI: 10.1109/ICCV.1998.710852 * |
SARAH BENZIANE ET AL: "ORIENTAL JOURNAL OF COMPUTER SCIENCE & TECHNOLOGY INTROdUCTION", PEER REVIEWED RESEARCH JOURNAL PUBLISHED BY, 2 December 2013 (2013-12-02), XP055298047, Retrieved from the Internet <URL:http://computerscijournal.org/dnload/SARAH-BENZIANE-and-ABDELKADER-BENYETTOU/OJCSV06I04P401-412.pdf> [retrieved on 20160826] * |
ZHANG QISHEN ET AL: "Personal authentication using hand vein and knuckle shape point cloud matching", 2013 IEEE SIXTH INTERNATIONAL CONFERENCE ON BIOMETRICS: THEORY, APPLICATIONS AND SYSTEMS (BTAS), IEEE, 29 September 2013 (2013-09-29), pages 1 - 6, XP032551058, DOI: 10.1109/BTAS.2013.6712702 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107980140A (en) * | 2017-10-16 | 2018-05-01 | 厦门中控智慧信息技术有限公司 | A kind of recognition methods of vena metacarpea and device |
CN107980140B (en) * | 2017-10-16 | 2021-09-14 | 厦门熵基科技有限公司 | Palm vein identification method and device |
Also Published As
Publication number | Publication date |
---|---|
TR201517592A2 (en) | 2017-01-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
Jee et al. | Liveness detection for embedded face recognition system | |
Verma et al. | Daughman’s algorithm method for iris recognition—a biometric approach | |
KR101017798B1 (en) | Method and apparatus for finger vein identification using mean curvature | |
CN107423703B (en) | Multi-mode recognition device and method based on face, fingerprint and finger vein features | |
CN104680128B (en) | Biological feature recognition method and system based on four-dimensional analysis | |
Zhao et al. | An automatic face recognition system in the near infrared spectrum | |
KR101724971B1 (en) | System for recognizing face using wide angle camera and method for recognizing face thereof | |
Fletcher et al. | Development of mobile-based hand vein biometrics for global health patient identification | |
Srivastava | Personal identification using iris recognition system, a review | |
Carney et al. | A multi-finger touchless fingerprinting system: Mobile fingerphoto and legacy database interoperability | |
Joy et al. | A Comparative Study on Recent Trends in Iris Recognition Techniques | |
Taha et al. | Iris features extraction and recognition based on the local binary pattern technique | |
Srinivas et al. | Human identification using automatic and semi‐automatically detected facial Marks | |
Ramsoful et al. | Feature extraction techniques for dorsal hand vein pattern | |
Taha et al. | Iris Features Extraction and Recognition based on the Scale Invariant Feature Transform (SIFT) | |
CN108875472B (en) | Image acquisition device and face identity verification method based on image acquisition device | |
WO2017116331A1 (en) | Stereo palm vein detection method and biometric identification system operating in compliance with said method | |
Singla et al. | Challenges at different stages of an iris based biometric system. | |
Patil et al. | Iris recognition using fuzzy system | |
Nestorovic et al. | Extracting unique personal identification number from iris | |
Rani et al. | An overview of biometric techniques | |
Roja et al. | Iris recognition using orthogonal transforms | |
Liu | Multi-modality quality assessment for unconstrained biometric samples | |
Kumar et al. | Performance of personal identification system technique using iris biometrics technology |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 15837217 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 15837217 Country of ref document: EP Kind code of ref document: A1 |