Performance Improvement by Classification Approach for Fingerprint Identification System
Meghna B. Patel1, Ashok R. Patel2

1Asst. Prof. Meghna B. Patel, Department of MCA , U. V. Patel College of Engineering, Ganpat University, Kherva (Gujarat), India.
2Dr. Ashok R. Patel, Department of Computer Application and Information Technology, HNGU, Patan (Gujarat), India.

Manuscript received on 21 May 2013 | Revised Manuscript received on 28 May 2013 | Manuscript published on 30 May 2013 | PP: 200-203 | Volume-2 Issue-2, May 2013 | Retrieval Number: B0635052213/2013©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: In the world of Information Technology, Information Security is an important factor. For Information Security, authentication plays a vital role. And for Secure Authentication now a days biometric based authentication (‘who you are’, e.g. Fingerprint) replace the Knowledge Based (‘what you know’, e.g. Password) and Object Based Authentication (‘what you have’, e.g. Token). Biometric authentication is the method which identifies or verifies the person based on his/her physiological or behavioral characteristics. The fingerprint is most widely used in biometric world. In Fingerprint Authentication different three levels (The Global or Galton level, The Local Level, The Very Fine Level) of Feature extraction techniques are used at the time of Fingerprint Identification and Verification. In Global or Galton Level identify the flow of ridges and valleys and also extract delta and core point features which classify the fingerprint in different pattern group like arch, tented arch, whorl, left loop and right loop. In tradition biometric recognition approach, the fingerprint template is match with all the template of the database. So, it will take long time for the individual’s authentication. In this paper present an approach which speed up the matching process by classifying the fingerprint template database on various fingerprint pattern group. So, instead of matching process done on whole database it will be done on specific fingerprint pattern group and reduce the no. of matches and improve the performance 3 time faster than the traditional approach.
Keywords: Biometrics, Classification, Identification, Verification, Minutiae points, Singular Points.

Scope of the Article: Classification