Mar. 25, 2009 to Mar. 27, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/UKSIM.2009.63
This paper explains algorithm of digital imagewatermarking using DWT for copyright protection.The detail coefficients of second level host image aftertaking DWT is used as a watermark key for thewatermark logo insertion and extraction process. Awatermark image recognition system has beendeveloped that uses new class of local image features.These local features of image are invariant to rotation,scaling and are shown to provide robust matchingacross a substantial range of affine distortion, changein 3D viewpoint, addition of noise, and change inillumination. The recognition proceeds by matchingindividual features to a database of features fromknown watermark images using a fast nearestneighboralgorithm, followed by Hough transform toidentify clusters belonging to a single object. Theeffectiveness of local scale invariant feature is testedon original watermark logo, extracted watermarklogo. We were able to design a prototype system,which provides user authentication.
Correlation Coefficient, Discrete Wavelet Transform, Mean Square Error, Peak Signal to Noise Ratio, Scale Invariant Feature Transform
Amol R. Madane, "Watermark Image Recognition from Local Scale-Invariant Feature", UKSIM, 2009, Computer Modeling and Simulation, International Conference on, Computer Modeling and Simulation, International Conference on 2009, pp. 258-263, doi:10.1109/UKSIM.2009.63