Biometric Iris Recognition System using Multiscale Feature Extraction Method
K. Harini1, G. Yamuna2, V. Santhiya3

1K. Harini, P.G., Department of Engineering (Communication Systems) Annamalai University, Tamil Nadu, India.
2Dr. G. Yamuna, Professor and Head, Department of Electronics and Communication Engineering, Annamalai University, Tamil Nadu, India.
3V. Santhiya, P.G., Department of Engineering (Communication Systems) Annamalai University, Tamil Nadu, India.
Manuscript received on March 16, 2020. | Revised Manuscript received on March 24, 2020. | Manuscript published on March 30, 2020. | PP: 2298-2303 | Volume-8 Issue-6, March 2020. | Retrieval Number: F8016038620/2020©BEIESP | DOI: 10.35940/ijrte.F8016.038620

Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: By an growing demand for security systems, identification of individuals based on biometric techniques has been a major role of research and education. Biometric recognition examines unique behavioral characteristics, such as an iris, face, retina, voice, fingerprint, hand geometry etc. The iris is one of the highly consistent methods that used to identify individuals because it is fixed and does not change throughout life. This features have led to increasing importance in its use for biometric recognition. In this study, we proposed a system combining Discrete Wavelet Transformation and Principal Component Analysis for feature extraction process of an iris. The idea of using DWT behind PCA is to decrease the resolution of the iris pattern. The Discrete Wavelet Transform (DWT) is depend on sub-band coding which reduces the computation time and resources required. PCA is used for further extraction. Our experimental calculation supports the efficient performance of the proposed system.
Keywords: Biometrics, Iris Recognition, PCA, Daugman’s Rubber Sheet Model, DWT, Hough Transform, Hamming Distance.
Scope of the Article: Probabilistic Models and Methods.