%0 Journal Article
%T Biometric Template Protection With Robust Semi ¨C Blind Watermarking Using Image Intrinsic Local Property
%A Mita C. Paunwala
%A Suparva Patnaik
%J International Journal of Biometric and Bioinformatics
%D 2011
%I Computer Science Journals
%X This paper addresses a biometric watermarking technology sturdy towards image manipulations,like JPEG compression, image filtering, and additive noise. Application scenarios includeinformation transmission between client and server, maintaining e-database and management ofsignatures through insecure distribution channels. Steps involved in this work are, a) generationof binary signature code for biometric, b) embedding of the binary signature to the host imageusing intrinsic local property, that ensures signature protection, c) host image is then madeexposed to various attacks and d) signature is extracted and matched based on an empiricalthreshold to verify the robustness of proposed embedding method. Embedding relies on binarysignature manipulating the lower order AC coefficients of Discrete Cosine Transformed subblocksof host image. In the prediction phase, DC values of the nearest neighbor DCT blocks isutilized to predict the AC coefficients of centre block. Surrounding DC values of a DCT blocks areadaptively weighed for AC coefficients prediction. Linear programming is used to calculate theweights with respect to the image content. Multiple times embedding of watermark ensuresrobustness against common signal processing operations (filtering, enhancement, rescaling etc.)and various attacks. The proposed algorithm is tested for 50 different types of host images andpublic data collection, DB3, FVC2002. FAR and FRR are compared with other methods to showthe improvement.
%K Biometric Watermarking
%K Image Manipulation
%K Edge Block Analysis
%K Fingerprint Matching
%K Security System.
%U http://cscjournals.org/csc/manuscript/Journals/IJBB/volume5/Issue2/IJBB-111.pdf