Elevating Fingerprint Verification System
Chander Kant, Rajender Nath
Department of Computer Science and applications
Kurukshetra University, Kurukshetra, Haryana, INDIA
,
Abstract
This paper is concerned with increasing the performance of fingerprint verification system. Verification is 1:1 matching process, establishing the validity of a claimed identity by comparing a verification template to an enrollment template. Verification requires that an identity be claimed, after which the individual’s enrollment template is located and compared with the verification template.
This paper presents an approach that improves existing conventional fingerprint verification system. The approach is useful when fingerprint verifications are made at large scale level. In the proposed method, first the dimensions of Finger/ Thumb are matched while scanning the fingerprint for verification. The minute points are calculated and matched further only when the dimensions are matched. This technique improves FAR (False Accept Rate) and Total Response Time of conventional fingerprint verification systems. The approach presented here is based on hand/ finger geometry verification systems as the geometry-based systems have very fast response time.
Keywords: Biometrics; Multimodal; Fingerprints; Face; Hand geometry; identification; Verification
1. Introduction
Need for reliable user authentication techniques have increased in the wake of heightened concerns about security and rapid advancements in networking, communication and mobility. Questions like “Is he really, who he claims to be? “Is this person authorized to use this facility?” or “Is he in the watchlist posted by the government?” are routinely being posed in a variety of scenarios ranging from issuing a driver’s license to gaining entry into a country. Biometrics, described as the science of recognizing an individual based on her physiological or behavioral traits. Biometric systems have now been deployed in various commercial, civilian and forensic applications as a means of establishing identity. These systems rely on the evidence of fingerprints, hand geometry, iris, retina, face, hand vein, facial thermogram, signature, voice, etc. to either validate or determine an identity [1]. A generic biometric system has four important modules: (a) sensor module; it acquires the raw biometric data of an individual; (b) feature extraction module; it processes the acquired data to extract a feature set that represents the biometric trait; (c) matching module; it compare the extracted feature set against the templates residing in the database through the generation of matching scores; (d) decision-making module; in which the matching scores are used to either validate the user’s claimed identity (verification) or determine her identity (identification). The template feature set is typically generated during enrollment when a user first interacts with the system and is refreshed or updated over a period of time in order to account for intra-class variations [2]. Ideally, the feature set extracted from the raw data is expected to be an invariant representation of a person’s biometric.
2. Problem Formulation
Idea for improving the response time hit from “Can multibiometrics improve performance?” [4]. If in multibiometrics one can improve the performance, then why should not in normal fingerprint verification?
In conventional Fingerprint verification system, minute points are extracted and compare with existing template in the database. Feature extractor finds the ridge endings and ridge bifurcations from the input fingerprint images. If ridges can be perfectly located in an input fingerprint image, then minutiae extraction is just a trivial task of extracting singular points in a thinned ridge map [3]. However, in practice, it is not always possible to obtain a perfect ridge map. The performance of currently available minutiae extraction algorithms depends heavily on the quality of the input fingerprint images [5]. Due to a number of factors (aberrant formations of epidermal ridges of fingerprints, postnatal marks, occupational marks, problems with acquisition devices, etc.), fingerprint images may not always have well-defined ridge structures. A reliable minutiae extraction algorithm is critical to the performance of an automatic identity authentication system using fingerprints. The overall flowchart of a typical algorithm is depicted in Figure below. It mainly consists of five components [6]:
The process shown above increases the complexity and response time of the system. To overcome these problems it is presided to take help of hand geometry system. Hand geometry system has faster response time compared to any other system due to its minimum data size per record as discussed in section 2.1.
2.1 Data Size Per Record
In order to divide the biometric data into partitions, the per-record size of the biometric data must be considered. In general, the larger the per-record data size of the biometric, the easier it is to assign the biometric record to a particular partition within the database. Also, the database can be divided into a greater number of partitions as the per-record data size of the biometric grows larger, but it increases the system complexity and thereby the response time.
Biometrics Areas
/ Data Size Per Record (bytes)Retinal Scan / 35
Iris Scan / 256
Fingerprints / 512 - 1000
Hand Geometry/ Finger Geometry / 9
Table 1 adopted from [7] shows that, the per-record data size for Hand Geometry is 9 bytes vs. 35 to 1000 bytes for the other biometrics listed.
3. Proposed Scheme
As it has been discussed in section 3.1 that geometry verification/ identification system has faster response time as compare with fingerprint verification/identification system. The proposed approach is based on geometry verification system.
Proposed scheme works at two levels (as shown in figure 2); at first level we compare and match the geometry of finger and at next level we compare the minutiae points extracted. Level-II is traversed only if Level-I is passed. Finger or fingerprints are discarded at the first level (while measuring its dimensions), if Level-I is not matched, system avoids for calculating and matching minutiae points further at level-II. This technique is also a better approach over multimodal Biometrics [8], as in multimodal, we employee two or more biometrics (e.g face, fingerprint, retina etc.) causing size, cost and complexity of the system to increase whereas in proposed scheme two techniques are applied on single biometric.
There are number of advantages of proposed approach over the conventional system, as discussed below: (i) the minute points are being calculated if and only if the dimensions are matched improves FAR (False Accept Rate); (ii) Total Response time will increases as compared to normal fingerprint verification system.
Let us illustrate the improvement in Total Response Time with the help of an example. Suppose, there are 10,000 templates to be compared and matched and out of these 10,000 templates there are only 100 templates which are supposed to be matched against the input templates.
Let time taken by Fingerprint verification system = T
Let time taken by Geometry verification system = t (where T>t say T=5*t)
In conventional Fingerprint verification system, Total Response Time (Tc) = 10,000*T.
In Proposed system (Tp) = 9900*t + 100 *(T + t).
(Since 9900 templates are discarded at Level-I. Only 100 templates are need verified at both of levels).
If ratio of T: t is 5: 1 then
Tc = 10,000*5=50,000 and
Tp = 9900*1 + 100(5+1)= 9900+600=10500.
Ratio R= Tc / Tp = 50,000/10,500= 4.7 times.
Total response time of proposed system increase 4.7 times of conventional system. Further this ratio becomes more when more templates are taken at input side.
4. Conclusion
This paper presents a simple and effective method of fingerprint verification scheme based on geometry identification/verification system. The scheme works in two phases. At first phase first works on the basis of hand geometry (Level-I) and then goes to detailed analysis (Level-II). The scheme allows us to completely controlled and automated fingerprint verification with efficient response time and FAR (False Accept Rate). The proposed scheme is not free from all drawbacks. One of the drawbacks of proposed scheme is that it needs extra storage space to store the templates of finger dimensions as compared to other conventional schemes.
REFERENCES
[1] S. Prabhakar, S. Pankanti, and A. K. Jain, “Biometric recognition: Security and privacy concerns,” IEEE Security Privacy Mag., vol. 1, no. 2,pp. 33–42, 2003.
[2] D. Maltoni, D. Maio, A. K. Jain, and S. Prabhakar, Handbook of Fingerprint Recognition. New York: Springer-Verlag, 2003.
[3] Biometric Sensor Interoperability: A Case Study In Fingerprints Arun Ross and Anil Jain Appeared in Proc. of International ECCV Workshop on Biometric Authentication (BioAW), May 2004
[4] L. Hong, A. K. Jain, and S. Pankanti, “Can multibiometrics improve performance?,” in Proc. AutoID’99, Summit, NJ, Oct. 1999, pp. 59–64.
[5] S. Prabhakar and A. K. Jain, “Decision-level fusion in fingerprint verification,” Pattern Recognit., vol. 35, no. 4, pp. 861–874, 2002.
[6] D. Maio, D. Maltoni, R. Cappelli, J. L. Wayman, and A. K. Jain, “FVC2002: Fingerprint verification competition,” in Proc. Int. Conf. Pattern Recognition (ICPR), Quebec City, QC, Canada, Aug. 2002, pp. 744–747.
[7] Comparison Of Biometric Techniques Prepared By Thomas Ruggles.
[8] L. Hong and A. K. Jain, “Integrating faces and fingerprints for personal identification,” IEEE Trans. Pattern Anal. Machine Intell, vol. 20, pp. 1295–1307, Dec. 1998.