AU2021104662A4 - A multimodal biometric authentication system - Google Patents

A multimodal biometric authentication system Download PDF

Info

Publication number
AU2021104662A4
AU2021104662A4 AU2021104662A AU2021104662A AU2021104662A4 AU 2021104662 A4 AU2021104662 A4 AU 2021104662A4 AU 2021104662 A AU2021104662 A AU 2021104662A AU 2021104662 A AU2021104662 A AU 2021104662A AU 2021104662 A4 AU2021104662 A4 AU 2021104662A4
Authority
AU
Australia
Prior art keywords
biometric
iris
template
fingerprint
signature
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.)
Ceased
Application number
AU2021104662A
Inventor
Suvarna Joshi
Abhay Kumar
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.)
Individual
Original Assignee
Individual
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 Individual filed Critical Individual
Priority to AU2021104662A priority Critical patent/AU2021104662A4/en
Application granted granted Critical
Publication of AU2021104662A4 publication Critical patent/AU2021104662A4/en
Ceased legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
    • G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
    • G06V10/811—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data the classifiers operating on different input data, e.g. multi-modal 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
    • G06V40/1365—Matching; Classification
    • 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
    • G06V40/172—Classification, e.g. identification
    • 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
    • G06V40/18—Eye characteristics, e.g. of the iris
    • G06V40/197—Matching; Classification
    • 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
    • G06V40/30—Writer recognition; Reading and verifying signatures

Abstract

A MULTIMODAL BIOMETRIC AUTHENTICATION SYSTEM The present invention relates to a multimodal biometric authentication system. The object of the proposed invention is to provide robust identification system as it depends on four biometric traits. Proposed invention providesdecision level fusion based multimodal biometrics system which integrates decisions obtained from multiple biometric modalities of an individual. A decision level fusion is proposed for combining the face [100], iris [101], fingerprint [102] and signature [103]. The system is based on the uni modal decisions obtained by using distance classifier. Following invention is described in detail with the help of Figure 1 of sheet 1 showing basic diagram of proposed invention. 2/2 START inputface Input Input iris InputSignagure image from fingerprint image from image from face database image from iris database Signature t ddatabase Face Image Reprocessing Fingerprint Iris mage Signature Image and Feature Prere tossing and Preprocessing and exrcinFeatu re extraction Feature extraction Feature extraction Face feature Binary Fingerprint feature Iris feature Binary Signature feature Ter plate Binary Tempilate Template Binary Template Matching of face Matching of Matching of Iris Matching of template with fingerprint template template with stored Signature template stored database with stored database ternplate with stored template database template database template If faceiffrs score . .if >Tbrsho9=11= soreSignature Threhol oldh score >Thfshol< Di < Thresho + i f Id AND of result of all mnatchers ' No If result 1 Reject the person Yes Accept tepro Figure 2

Description

2/2
START
Input Input iris InputSignagure inputface fingerprint image from image from image from face database image from iris database Signature
ddatabase t Face Image Fingerprint Iris mage Signature Image Reprocessing and Feature Prere tossing and Preprocessing and exrcinFeatu re extraction Feature extraction Feature extraction
Face feature Binary Fingerprint feature Iris feature Binary Signature feature Ter plate Binary Tempilate Template Binary Template
Matching of face Matching of Matching of Iris Matching of template with fingerprint template template with stored Signature template stored database with stored database ternplate with stored template database template database template
If faceiffrs score . .if >Tbrsho9=11= soreSignature Threhol oldh score >Thfshol< Di < Thresho Id if +
AND of result of all mnatchers '
No If result 1
Reject the person Yes
Accept tepro
Figure 2
A MULTIMODAL BIOMETRIC AUTHENTICATION SYSTEM
Technical field of invention:
Present invention in general relates to a multimodal biometric authentication system for person recognition which precisely provide robust and reliable multimodal authentication.
Background of the invention:
[001] The background information herein below relates to the present disclosure but is not necessarily prior art.
[002] Biometrics are automated methods of recognizing a person based on a physiological or behavioral characteristic. Among the features measured are face, fingerprints, hand geometry, handwriting, iris, retinal, vein, and voice. Biometric technologies are becoming the foundation of an extensive array of highly secure identification and personal verification solutions. As the level of security breaches and transaction fraud increases, the need for highly secure identification and personal verification technologies is becoming '0 apparent.Utilizing biometrics for personal authentication is becoming convenient and considerably more accurate than current methods such as the utilization of passwords or PINs.
[003] The Unimodal biometric systems rely on the evidence of a single source of information for authentication (e.g., single fingerprint or face). These systems have to deal with a variety of problems includingnoise in sensed data, intra-class variations, inter-class similarities, non-universality, spoof attacks.
[004] Some of the limitations imposed by unimodal biometric systems can be overcome by including multiple sources of information for establishing identity.Such systems, known as multimodal biometric systems, are found more reliable due to the presence of multiple, (fairly) independent pieces of evidence. These systems are able to meet the stringent performance requirements imposed by various applications.
[005] Multimodal biometrics are a superior solution for every industry that demands higher accuracy as well as security. Overall, biometrics offer several advantages over unimodal systems.Biometric features are not exactly the same every time they are gathered. For instance, your signature is subject to change within the same day due to your emotional mode or health state. Fingerprint corresponding two fingers also have some variations. There may be degradation in fingerprint image quality due to various factors such as dry, oily, dirty finger, dirty sensor surface, scars and other factors or simply because the user has positioned his/her finger on the fingerprint sensor in a different position. Performance offace recognition system is limited due to the various problems such as wide variety of illumination, facial expression and pose variations, lightning conditions, ageing, disguises such as slight cut, glasses or makeup. Government of India is implementing a system to capture and store multiple biometric traits (face, fingerprints and iris) from its population of more than 1 billion individuals for the purpose of issuing them a unique identification number (UID).
[006] Although various attempts are made before, for providing variousbiometric system for person recognition system and few of them are such as- US10395097B2 discloses method and system for biometric recognition, US8135181B2 discloses method of multi-modal biometric recognition using handshape and palmprint, US10262123B2 discloses multimodal biometric authentication system and EP1533759A1 discloses biometric system.
[007] There exist many drawbacks in the existing unit. Therefore, there is need to introduce a novel and efficient biometric system. Hence the present invention develops amultimodal biometric authentication system.
Objective of the invention
[008] An objective of the present invention is to attempt to overcome the problems of the prior art and provide a multimodal biometric authentication system.
[009] In a preferred embodiment, the present invention provides robust and reliable multimodal authentication system.
[0010] These and other objects and characteristics of the present invention will become apparent from the further disclosure to be made in the detailed description given below.
Summary of the invention:
Accordingly following invention provides a multimodal biometric authentication system. The proposed invention provides a robust identification system as it depends on four biometric traits.The present invention relating to the integration of face [100], iris [101], and signature
[103] and fingerprint [102] features. Decision fusion framework is developed for selected biometrics. This multimodal system is based on the unimodal decisions obtained by using distance classifier. The system fuses the decisions of the individual face [100], iris [101], and fingerprint [102] and offline signature [103] biometrics. Each biometric decision is evaluated using hamming classifiers [108]. Decisions [109] obtained from hamming classifier [108]are then fused in order to generate the final decision. The individual decisions [109] from all the modalities are further combined with straightforward AND logic rule to obtain the final decision [111]. The AND logic is applied to ensure a satisfactory level of security, since a positive authentication is only accomplished in case if only all the biometrics traits produce positive authentication.
'0 Brief description of drawing:
[0011] This invention is described by way of example with reference to the following drawing where,
[0012] Figure 1 of sheet 1 illustrates basic diagram of proposed invention. Whereas, 100 denotes face image, 101 denotes iris, 102 denotes fingerprint, 103 denotes signature, 104 denotes face features, 105 denotes iris features, 106 denotes fingerprint features, 107 denotes signature features, 108 denotes hamming classifier,
109 denotes decision, 110 denotes AND rule based fusion, 111 denotes final decision.
[0013] Figure 2 of sheet 2 illustrates flow chart of proposed invention.
[0014] In order that the manner in which the above-cited and other advantages and objects of the invention are obtained, a more particular description of the invention briefly described above will be referred, which are illustrated in the appended drawing. Understanding that these drawing depict only typical embodiment of the invention and therefore not to be considered limiting on its scope, the invention will be described with additional specificity and details through the use of the accompanying drawing.
Detailed description of the invention:
[0015] The present invention relates to a multimodal biometric authentication system. More particularly the proposed invention provides robust and reliable multimodal authentication.
[0016] Present multimodal system integrates information from multiple biometric sources '0 like face [100], iris [101], fingerprint [102] and signature [103]to achieve a better performance. The system proposes decision level fusion based multimodal biometrics system which integrates decisions obtained from multiple biometric modalities of an individual. A decision level fusion is proposed forcombining the face [100], iris [101], fingerprint [102] and signature [103]. Present system is based on the unimodal decisions obtained by using distance classifier.
[0017] In accordance with figure 1 of sheet 1 which illustrates basic diagram of proposed invention. In the preferred embodiment, multimodal system integrates information from multiple biometric sources like face [100], iris [101], fingerprint [102] and signature [103]to achieve a better performance. The system is based on the unimodal decisions obtaining by using distance classifier. Each biometric decision is evaluated using hamming classifiers
[108]. Decisions [109] obtaining from hamming classifier [108]are then fused in order to generate the final decision [111]. The individual decisions from all modalities are further combined with straightforward the AND logic rule to obtain the final decision [111]. The
AND logic is applied to ensure a satisfactory level of security, since a positive authentication is only accomplished in case if only all the biometrics traits produce positive authentication. Decision level based multimodal authentication systemoutperforms unimodal biometrics system in terms of different error rates and GAR.
[0018] In the present system distinct and significant features of all biometric modalities are extracting using the discrete wavelet transform based technique. For face [100], iris [101] and signature [103] modalities proposed adaptive configuration uses detail coefficients obtaining from wavelet decomposition. Approximation coefficients obtained from wavelet decomposition is used for fingerprint [102] modality. Decisions [109] obtained from individual matchers is combined using simple AND rule. The obtained results show that the proposed decision level fusion technique carries out an enhanced system showing interesting results in terms of FAR and FRR indexes.
[0019] Present invention related to robust of decision level fusion based multimodal recognition system for combining the face [100], iris [101], fingerprint [102] and signature
[103]. The invention provides a robust identification system as it depends on four biometric traits.Selection of face [100], iris [101], fingerprint [102] and signature [103] as biometric features for building a multimodal biometric system stems from their potential involvement '0 in real-time large-scale biometrics applications. These multimodal biometrics system uses biometrics information originated four biometric traits of an individual. This invention is based on the unimodal biometric decisions obtained by using distance classifier.
[0020] The individual decisions [109] from all four modalities are further combinewith the AND logic rule to obtain the final decision [111]. The AND logic is applied to ensure a satisfactory level of security, since a positive authentication is only accomplished in case if only all the fusion levels approaches produce positive authentication.
[0021] Further present automatic multimodal biometric system has a very high potential for to be employed in various government and consumer security critical applications as well as for commercialization. The invention provides robust and efficient multimodal biometrics system to overcome limitation of unimodal biometrics system. However, unimodal biometrics has limited usage since no single biometric is sufficiently robust and accurate in real-world applications.
[0022] The many features and advantages of the invention are apparent from the detailed specification, and thus, it is intended by the appended claims to cover all such features and advantages of the invention which fall within the true spirit and scope of the invention. Further, since numerous modifications and variations will readily occur to those skilled in the art, it is not desired to limit the invention to the exact construction and operation illustrated and described, and accordingly, all suitable modifications and equivalents may be resorted to, falling within the scope of the invention.

Claims (5)

THE CLAIMS DEFINING THE INVENTION ARE AS FOLLOWS
1. A multimodal biometric authentication system wherein
multimodal system integrates information from multiple biometric sources like face [100], iris [101], fingerprint [102] and signature [103]to achieve a better performance; said system is based on the unimodal decisions obtaining by using distance classifier; each biometric decision is evaluated using hamming classifiers [108];
decisions [109] obtaining from hamming classifier [108]are then fused in order to generate the final decision [111]; the individual decisions from all modalities are further combined with straightforward the AND logic rule to obtain the final decision [111].
2. The system as claimed in claim 1 wherein the AND logic is applied to ensure a satisfactory level of security, since a positive authentication is only accomplished in case if only all the biometrics traits produce positive authentication.
3. The system as claimed in claim 1 wherein the distinct and significant features of all biometric modalities are extracting using the discrete wavelet transform based technique; for face [100], iris [101] and signature [103] modalities proposed adaptive configuration uses detail coefficients obtaining from wavelet decomposition and approximation coefficients obtained from wavelet decomposition is used for fingerprint [102] modality; decisions [109] obtained from individual matchers is combined using simple AND rule. the obtained results show that the proposed decision level fusion technique carries out an enhanced system showing interesting results in terms of FAR and FRR indexes.
4. The system as claimed in claim 1 wherein said system depends on four biometric traits; Selection of face [100], iris [101], fingerprint [102] and signature [103] as biometric features for building a multimodal biometric system stems from their potential involvement in real-time large-scale biometrics applications; these multimodal biometrics system uses biometrics information originated four biometric traits of an individual.
5. The system as claimed in claim 1 wherein the individual decisions [109] from all four modalities are further combine with the AND logic rule to obtain the final decision [111]; the AND logic is applied to ensure a satisfactory level of security, since a positive authentication is only accomplished in case if only all the fusion levels approaches produce positive authentication.
AU2021104662A 2021-07-28 2021-07-28 A multimodal biometric authentication system Ceased AU2021104662A4 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
AU2021104662A AU2021104662A4 (en) 2021-07-28 2021-07-28 A multimodal biometric authentication system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
AU2021104662A AU2021104662A4 (en) 2021-07-28 2021-07-28 A multimodal biometric authentication system

Publications (1)

Publication Number Publication Date
AU2021104662A4 true AU2021104662A4 (en) 2021-10-07

Family

ID=77922875

Family Applications (1)

Application Number Title Priority Date Filing Date
AU2021104662A Ceased AU2021104662A4 (en) 2021-07-28 2021-07-28 A multimodal biometric authentication system

Country Status (1)

Country Link
AU (1) AU2021104662A4 (en)

Similar Documents

Publication Publication Date Title
Sahoo et al. Multimodal biometric person authentication: A review
Ross et al. Human recognition using biometrics: an overview.
Hemalatha A systematic review on Fingerprint based Biometric Authentication System
Charity et al. A bimodal biometrie student attendance system
Shyam et al. Identifying individuals using multimodal face recognition techniques
Meraoumia et al. An automated ear identification system using Gabor filter responses
Ribaric et al. A biometric verification system based on the fusion of palmprint and face features
Selwal et al. A scheme for template security at feature fusion level in multimodal biometric system
Akulwar et al. Secured multi modal biometric system: a review
Ross et al. Multimodal human recognition systems
Geethanjali et al. Feature level fusion of multimodal biometrics and two tier security in ATM system
AU2021104662A4 (en) A multimodal biometric authentication system
Badrinath et al. An efficient multi-algorithmic fusion system based on palmprint for personnel identification
Devi et al. A multimodal biometric system using partition based dwt and rank level fusion
Kaur Multimodal biometrics feature level fusion for iris and hand geometry using chaos-based encryption technique
Jadhav et al. Review on Multimodal Biometric Recognition System Using Machine Learning
Kumar et al. Fingerprint image enhancement and minutia matching
Sharma et al. Human recognition methods based on biometric technologies
Manivannan et al. Fingerprint biometric for identity management
Sharma et al. Multimodal biometric system fusion using fingerprint and face with fuzzy logic
Gupta Advances in multi modal biometric systems: a brief review
Herbadji et al. Multimodal Biometric Verification using the Iris and Major Finger Knuckles
Rahman et al. Distinguishing a person by face and iris using fusion approach
Ayodele et al. Current practices in information fusion for multimodal biometrics
Sharma et al. Fingerprint matching Using Minutiae Extraction Techniques

Legal Events

Date Code Title Description
FGI Letters patent sealed or granted (innovation patent)
MK22 Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry