Comparative study of color iris recognition: DCT vs. vector quantization approaches in rgb and hsv color spaces

Security is obligatory for digital world. It requires robust and reliable security mechanisms which comprises irreplaceable identification of individual. Biometrics plays an important role in recognizing individual uniquely, furthermore iris based security is more impenetrable as compared to fingerprint based security. Also, human iris doesn't change with ageing and can be easily captured. Generic iris recognition process includes lots of preprocessing such as iris localization, hence become time intensive; further, if preprocessing is not done properly, lead to poor accuracy because of noisy image. In this paper, an iris reorganization system is proposed that provides good accuracy even after eliminating iris localization step which is considered as one of the mandatory step in literature. It evaluates an impact on accuracy for different color spaces namely, Hue Saturation Value (HSV) and Red Green Blue (RGB); better performance is observed using HSV color space. This work also evaluates accuracy of feature extraction techniques, Discrete Cosine Transform (DCT) and Vector quantization (VQ) algorithms such as Linde Buzo Gray (LBG) and Kekre's Fast Codebook Generation (KFCG) in both RBG and HSV color spaces. It is observed that a Vector quantization algorithm performs better in HSV color space.