Cepstral Filtering on a Columnar Image Architecture: A Fast Algorithm for Binocular Stereo Segmentation
Issue No. 07 - July (1989 vol. 11)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.192471
<p>Many primate visual cortex architectures have a prominent feature responsible for the mixing of left and right eye visual data: ocular dominance columns represent thin (about 5-10 minutes of arc) strips of alternating left and right eye input to the brain. It is shown that such an architecture, when operated upon with a cepstral filter, provides a strong cue for binocular stereopsis. Specifically, the vector of binocular disparity may be easily identified in the output of the (columnar based) cepstral filter. This algorithm is illustrated with application to a random dot stereogram and to natural images. The authors suggest that this provides a fast algorithm for stereo segmentation, in a machine vision context. In a biological context, it may provide a computational rationale for the existence of columnar systems with regard to both ocular mixing and other visual modalities that have a columnar architecture.</p>
pattern recognition; computer vision; columnar image architecture; binocular stereo segmentation; primate visual cortex architectures; ocular dominance columns; brain; cepstral filter; binocular stereopsis; binocular disparity; random dot stereogram; natural images; stereo segmentation; machine vision; computer vision; filtering and prediction theory; pattern recognition; visual perception
Y. Yeshurun and E. Schwartz, "Cepstral Filtering on a Columnar Image Architecture: A Fast Algorithm for Binocular Stereo Segmentation," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 11, no. , pp. 759-767, 1989.