Variable window Gabor filters and their use in focus and correspondence

More and more low level vision algorithms are being carried out in the spatial frequency domain, using Gabor lters. There are two basic problems concerned with Gabor lterings we will address in this paper. One is the window size problem, in which we will adopt a set of 2D variable window Gabor lters, and compare its performance with those of xed window lters. We will show that the variable window scheme is more adaptive to image contents, while xed window schemes may suffer either large errors or instabilities when image contents are changed. The other problem we will address is the stability of amplitude and phase information resulting from convolving the lters with images. We will extend Fleet's 1D phase stability analysis to 2D phase and amplitude stability analysis based upon the assumption of local resemblance of lter outputs to a single sinusoid. Applications on focus quality measurement and 2D correspondence are described, and the results demonstrate improvements of performance by detecting unstable information using the criterion developed. K eywords: Computer vision, Low-level processing, Gabor lter, Depth from defocus, Depth from stereo, 2D correspondence. iv