The Center for Unified Biometrics and Sensors (CUBS) at the University at Buffalo, SUNY is developing biometrics identification systems for civilian, law enforcement and homeland security applications. The center is involved in traditional research developing matching algorithms for several biometric modalities (e.g., fingerprint, signature, face) and in identifying exploratory areas of research that will address problems anticipated in widescale deployment of biometrics. In this paper we describe some of our recent research in fingerprint verification. In particular, we will describe a new non-stationary fingerprint enhancement algorithm based on Fourier domain analysis and a partial fingerprint matching algorithm that uses novel approaches from graph and optimization theory. We will also present new score computation algorithm that treats fingerprint verification as a classification problem. Finally, we will describe a novel technique for protecting the privacy and security of fingerprint templates that is based on symmetric hash functions. INTRODUCTION In an increasingly digital world, reliable personal authentication is an important human computer interface activity. National security, e-commerce, and access to computer networks are some examples where establishing a person's identity is vital. Existing security measures rely on knowledge-based approaches like passwords or token-based approaches such as swipe cards and passports to control access to physical and virtual spaces. Though ubiquitous, such methods are not very secure. Tokens such as badges and access cards may be shared or stolen. Passwords and PIN numbers may be stolen electronically. Further, they cannot differentiate between authorized user and a person having access to the tokens or knowledge. Biometrics such as fingerprint, face and voice print offers means of reliable personal authentication that can address these problems and is gaining citizen and government acceptance. Biometrics is the science of verifying the identity of an individual through physiological measurements or behavioral traits. Since biometric identifiers are associated permanently with the user they are more reliable that token or knowledge based authentication methods. Figure 1: (a)Various biometric modalities: Fingerprint, Voice, Signature, Face recognition, Hand Geometry and chemical biometrics (b) General architecture of a biometric authentication system Depending on the application, biometrics can be used for identification or for verification. In verification, the biometrics is used to validate the claim made by the individual. The biometric of the user is compared with the biometrics of the claimed individual in the databases. The claim is rejected or accepted based on the match. (In essence, the system tries to answer the question, “Am I whom I claim to be?”). In identification, the system recognizes an individual by comparing his biometrics with every record in the database. (In essence, the system tries to answer the question, “Who am I?”). In this paper, we will be dealing solely with the problem of verification using fingerprints. In general, biometric verification consists of two stages (Figure 1b) (i) Enrollment and (ii) Authentication. During enrollment, the biometrics of the user is captured and the extracted features (template) are stored in the database. During authentication, the biometrics of the user is captured again and the extracted features are compared with the ones already existing in the database to determine a match. The specific record to fetch from the database is determined by using the claimed identity of the user. Furthermore, the database itself may be central or distributed with each user carrying his template on a smart card. Biometrics offers several advantages over traditional security measures. These include (i) Non-repudiation: With token and password based approaches, the perpetrator can always deny committing the crime pleading his/her password or ID was stolen or compromised in some fashion. Therefore a user can repudiate or deny the use of a service even when an electronic record exists. However, biometrics is indefinitely associated with a user and hence it cannot be lent or stolen making repudiation infeasible. (ii) Accuracy and Security: Password based systems are prone to dictionary and brute force attacks. Furthermore, the system is as vulnerable as its weakest password. Biometric authentication requires the physical presence of the user and therefore cannot be circumvented through a dictionary or brute force style attack. Biometrics have also been shown to possess a higher bit strength compared to password based systems (Jea, Chavan et al. 2004) and are therefore inherently secure (iii) Screening : In screening applications, we are interested in preventing the users from assuming multiple identities (e.g. a terrorist using multiple passports to enter a foreign country). This requires we ensure that a person has not already enrolled under another assumed identity before enrolling his new record into the database. Such screening is not possible using traditional authentication mechanisms and biometrics provides the only available solution. Fingerprints were one of the first biometrics to be adopted and have currently become synonymous with reliable personal identification. Fingerprints were accepted formally as valid personal identifier in the early twentieth century and have since then become a de-facto authentication technique in law-enforcement agencies world wide. The FBI currently maintains more than 200 million fingerprint records on file. Fingerprints have several advantages over other biometrics, such as the following: (i) High universality: A large majority of the human population has legible fingerprints and can therefore be easily authenticated. This exceeds the extent of the population who possess passports, ID cards or any other form of tokens. (ii) High distinctiveness: Even identical twins who share the same DNA have been shown to have different fingerprints, since the ridge structure on the finger is not encoded in the genes of an individual. Thus, fingerprints represent a stronger authentication mechanism than DNA. Furthermore, there has been no evidence of identical fingerprints in more than a century of forensic practice. There are also mathematical models (Pankanti, Prabhakar et al. 2002) that justify the high distinctiveness of fingerprint patterns. (iii) High permanence: The ridge patterns on the surface of the finger are formed in the womb and remain invariant until death except in the case of severe burns or deep physical injuries. (iv) Easy collectability : The process of collecting fingerprints has become very easy with the advent of online sensors. These sensors are capable of capturing high resolution images of the finger surface within a matter of seconds(Maio, Maltoni et al. 2003). This process requires minimal or no user training and can be collected easily from co-operative or non cooperative users. In contrast, other accurate modalities like iris recognition require very cooperative users and have considerable learning curve in using the identification system. (v) High performance: Fingerprints remain one of the most accurate biometric modalities available to date with jointly optimal FAR (false accept rate) and FRR (false reject rate). Forensic systems are currently capable of achieving FAR of less than 10(NIST). (vi) Wide acceptability: While a minority of the user population is reluctant to give their fingerprints due to the association with criminal and forensic fingerprint databases, it is by far the most widely used modality for biometric authentication. The fingerprint surface is made up of a system of ridges and valleys that serve as friction surface when we are gripping the objects. The surface exhibits very rich structural information when examined as an image. The fingerprint images can be represented by both global as well as local features (Figure 2). The global features include the ridge orientation, ridge spacing and singular points such as core and delta. The singular points are very useful from the classification perspective. However, verification usually relies exclusively on minutiae features. Minutiae are local features marked by ridge discontinuities. There are about 18 distinct types of minutiae features that include ridge endings, bifurcations, crossovers and islands. Among these, ridge endings and bifurcation are the commonly used features. A ridge ending occurs when the ridge flow abruptly terminates and a ridge bifurcation is marked by a fork in the ridge flow. Most matching algorithms do not even differentiate between these two types since they can easily get exchanged under different pressures during acquisition. Global features do not have sufficient discriminative power on their own and are therefore used for binning and during intermediate steps before the extraction of the local minutiae features. Figure 2: (a) Fingerprint image showing various type of ridge features (b) Core (c) Delta (d) Lake (e) Island (f) Ridge ending (g) Ridge bifurcation The various stages of a typical fingerprint recognition system is shown in Figure 3. The fingerprint image is acquired using off-line methods such as creating an inked impression on paper or through a live capture device consisting of an optical, capacitive, ultrasound or thermal sensor (Maio, Maltoni et al. 2003). The first stage consists of standard image processing algorithms such as noise removal and smoothening. However, it is to be noted that unlike regular images, the fingerprint image represents a system of oriented texture and has very rich structural information within the image. Furthermore, the definition of noise and unwanted artifacts are also specific to fingerprints. The fingerprint image enhancement algorithms are specifically designed to exploit the periodic and directional nature of the ridges. Fina
[1]
Anil K. Jain,et al.
Adaptive flow orientation-based feature extraction in fingerprint images
,
1995,
Pattern Recognit..
[2]
Zsolt Miklós Kovács-Vajna,et al.
A Fingerprint Verification System Based on Triangular Matching and Dynamic Time Warping
,
2000,
IEEE Trans. Pattern Anal. Mach. Intell..
[3]
B. V. K. Vijaya Kumar,et al.
Fingerprint Verification Using Correlation Filters
,
2003,
AVBPA.
[4]
MaioDario,et al.
Direct Gray-Scale Minutiae Detection In Fingerprints
,
1997
.
[5]
Xudong Jiang,et al.
Fingerprint minutiae matching based on the local and global structures
,
2000,
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.
[6]
Sabih H. Gerez,et al.
Fingerprint matching by thin-plate spline modelling of elastic deformations
,
2003,
Pattern Recognit..
[7]
D.C.D. Hung,et al.
Enhancement and feature purification of fingerprint images
,
1993,
Pattern Recognit..
[8]
Qinghan Xiao,et al.
Combining Statistical and Structural Information for Fingerprint Image Processing, Classification and identification
,
1991,
Pattern Recognition.
[9]
Anil K. Jain,et al.
Audio- and Video-based Biometric Person Authentication
,
1997,
Lecture Notes in Computer Science.
[10]
Craig I. Watson,et al.
Comparison of FFT Fingerprint Filtering Methods for Neural Network Classification | NIST
,
1994
.
[11]
Sharath Pankanti,et al.
Filterbank-based fingerprint matching
,
2000,
IEEE Trans. Image Process..
[12]
S. H. Gerez,et al.
A correlation-based fingerprint verification system
,
2000
.
[13]
Venu Govindaraju,et al.
A minutia-based partial fingerprint recognition system
,
2005,
Pattern Recognit..
[14]
Akio Tojo,et al.
Fingerprint pattern classification
,
1984,
Pattern Recognit..
[15]
Anil K. Jain,et al.
FVC2000: Fingerprint Verification Competition
,
2002,
IEEE Trans. Pattern Anal. Mach. Intell..
[16]
Danny Roberge,et al.
High-Speed Fingerprint Verification Using an Optical Correlator
,
1998
.
[17]
B. Sherlock,et al.
Fingerprint enhancement by directional Fourier filtering
,
1994
.
[18]
Anil K. Jain,et al.
Handbook of Fingerprint Recognition
,
2005,
Springer Professional Computing.
[19]
Yair Frankel,et al.
On enabling secure applications through off-line biometric identification
,
1998,
Proceedings. 1998 IEEE Symposium on Security and Privacy (Cat. No.98CB36186).
[20]
Anil K. Jain,et al.
Fingerprint Image Enhancement: Algorithm and Performance Evaluation
,
1998,
IEEE Trans. Pattern Anal. Mach. Intell..
[21]
Venu Govindaraju,et al.
Security and matching of partial fingerprint recognition systems
,
2004,
SPIE Defense + Commercial Sensing.
[22]
Lawrence O'Gorman,et al.
An approach to fingerprint filter design
,
1989,
Pattern Recognit..
[23]
Sharath Pankanti,et al.
On the individuality fingerprints
,
2001,
Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.
[24]
Sharath Pankanti,et al.
Minutia verification and classification for fingerprint matching
,
2000,
Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.