Biometric Watermarking and Recognition Using IRIS

Abstract

A watermark is a form, image or text that is impressed onto paper, which provides evidence of its authenticity. Digital watermarking is an extension of the same concept. There are two types of watermarks: visible watermark and invisible watermark. In this project we have concentrated on implementing watermark in image. The main consideration for any watermarking scheme is its robustness to various attacks. Watermarking dependency on the original image increases its robustness but at the same time we need to make sure that the watermark is imperceptible. In this project an invisible watermarking technique is implemented. Biometric Watermarking pertains to the integration of biometrics with watermarking. We present a novel technique of watermarking using iris of the person to which the work belongs, as biometric. In this project, we propose to use the combination of Zernike moments for feature extraction along with Lifting Wavelet Transform (LWT) and Singular value decomposition (SVD) for watermark embedding. The extracted iris image obtained by inverse of LWT and SVD is subjected to the procedure of extraction of features for template matching. K-means clustering is used to match the recovered watermark image with the set of all centred images in the training database