Image matching using the windowed Fourier phase

摘要

A theoretical framework is presented in which windowed Fourier phase (WFP) is introduced as the primary matching primitive. Zero-crossings and peaks correspond to special values of the phase. The WFP is quasi-linear and dense; and its spatial period and slope are controlled by the scale. This framework has the following important characteristics: 1) matching primitives are available almost everywhere to convey dense disparity information in every channel, either coarse or fine; 2) the false-target problem is significantly mitigated; 3) the matching is easier, uniform, and can be performed by a network suitable for parallel computer architecture; 4) the matching is fast since very few iterations are needed. In fact, the WFP is so informative that the original signal can be uniquely determined up to a multiplicative constant by the WFP in any channel. The use of phase as matching primitive is also supported by some existing psychophysical and neurophysiological studies. An implementation of the proposed theory has shown good results from synthesized and natural images.