Image-processing algorithms realized by discrete-time cellular neural networks and their circuit implementations

Abstract In this study, eight image tasks: connected component detection (CCD) with down, right, +45° and −45° directions, edge detection, shadow projection with left and right directions and point removal are analyzed. These tasks are solved using the binary input and binary output discrete-time cellular neural networks (DTCNNs) associated with suitable templates. Furthermore, the behavior of the DTCNNs can be realized using Boolean functions, and the corresponding equivalent logic circuits are derived. An 8 × 8 DTCNNs-based image-processing chip is implemented by the FPGA technology. A simulation of the chip developed for the CCD task is also presented.