Haar Wavelet Approach of Iris Texture Extraction for Personal Recognition
S. M. Rajbhoj1, P. B. Mane2

1S. M. Rajbhoj, Ph.D. Research Scholar, Bharati Vidyapeeth University College of Engineering, Bharati Vidyapeeth University, Pune (Maharashtra), India.
2Dr. P. B. Mane, Principal, AISSMS, Institute of Information Technology, Pune (Maharashtra), India.
Manuscript received on 10 July 2013 | Revised Manuscript received on 18 July 2013 | Manuscript Published on 30 July 2013 | PP: 22-25 | Volume-3 Issue-2, July 2013 | Retrieval Number: B0985073213/13©BEIESP
Open Access | Editorial and Publishing 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 (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Iris recognition is one of the fast, accurate, reliable and secure biometric techniques for human identification. As the iris texture pattern is very unique and has no links with the genetic structure of an individual it is used as feature in iris recognition system. Poor quality images, high failure to accept rates (FTE) and high false reject rates (FRR) undermines the performance of iris recognition systems. The selection of subset of feature, its extraction and classification is a crucial step in this system. In this paper a method for iris recognition based on Haar wavelet approach of Iris texture extraction is proposed. Iris recognition system consists of iris localization, normalization, features extraction and matching modules. The feature extraction algorithm extracts haar wavelet packet energies of the normalized iris image (local features) to generate a unique code by quantizing these energies into one bit according to an adapted threshold. Hamming distance measure is used in order to find similarity between the iris images. Results are presented that demonstrate significant improvements in iris recognition accuracy when feature extracted using higher wavelet decomposition through the use of the public iris database CASIA.V4.
Keywords: Biometrics, Iris Recognition, Feature Extraction, Wavelet Transform.

Scope of the Article: Pattern Recognition