Iris recognition system using block based approach with DWT and DCT
Ameya Deshpande, Sumitkumar Dubey, Hrushikesh Shaligram, Aditya Potnis, Satishkumar Chavan · 2014
Advancement in electronics industry and revolution in information technology sector has lead authentication and recognition to be the important aspect in today's life. Authentication and recognition can be achieved using biometric cues which provide secure and reliable alternative to traditional methods of human identification. Human iris is most reliable biometric because of its uniqueness, stability and non-invasive nature. The paper presents an efficient iris recognition system for authentication of a person using block based approach with Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) for feature extraction and standard deviation method for feature comparison. The proposed system is evaluated for its performance i.e. identification of person on 500 images of iris of 100 persons (5 images of each person) of UBIRIS v2 database. The experimental results prove the efficiency of block based approach with DWT is superior to traditional approach of DWT and DCT. The false acceptance rate (FAR) and false rejection rate (FRR) is minimum for block based DWT.