An adaptive neural net approach to the segmentation of mixed gray-level and binary pictures
Troudet, Tabatabai · 1988
An adaptive neural network architecture is proposed to perform segmentation in real time for mixed gray-level and binary pictures. In this approach the composite picture is divided into binary and image blocks based on a dichotomy measure computed by an adaptive neural net. A VLSI implementation of such a net in 2- mu m CMOS technology is described and simulated for a maximum block size of 256 pixels.>