Structural analysis of stereograms for CNN depth detection

The usefulness of combining stereogram techniques with cellular neural netw ork (CNN) analogic procedures in stereo depth extraction has been demonstra ted before. Due to the local processing philosophy in the CNN paradigm, the detailed and well-established knowledge of local stereogram properties is of high importance. The paper gives an algorithmic definition for synthetic stereograms; a means for structural analysis of different types of random stereograms. In order to confine the generally propagating effect of three- dimensional (3-D) surface features into a restricted neighborhood in a ster eogram, the concept of difference stereograms and the related difference su rface is introduced for coding local surface variations into stereograms, T he difference stereogram, with its local structure, is especially suitable for CNN processing, and it is closely connected to the pattern projection t echnique of depth extraction.