A neural net based architecture for the segmentation of mixed gray-level and binary pictures

A neural-net-based 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 16×16 pixel blocks, which are identified as character blocks or image blocks on the basis of a dichotomy measure computed by an adaptive 16×16 neural net. For compression purposes, each image block is further divided into 4×4 subblocks and, similar to the classical block truncation coding (BTC) scheme, a one-bit nonparametric quantizer is used to encode 16×16 character and 4×4 image blocks. In this case, however, the binary map and quantizer levels are obtained through a neural net segmentor over each block. The efficiency of the neural segmentation in terms of computational speed, data compression, and quality of the compressed picture is demonstrated. The effect of weight quantization is also discussed. VLSI implementations of such adaptive neural nets in CMOS technology are described and simulated in real time for a maximum block size of 256 pixels