A Self Adaptability based Stereo Correspondence of Face Images using Wavelets

This paper proposes a discrete wavelet-based stereo matching technique. A discrete wavelet transform is first applied to a pair of stereo images to decorrelate the images into a number of approximations. Information in the basebands is less sensitive to shift variability of the wavelet transform. A self-adapting dissimilarity measure is employed to generate a disparity map of the stereo pairs. Results show that the proposed technique produces smoother disparity maps with less computation cost