Cellular neural network design for solving specific image‐processing problems
Krzysztof Śalot · International Journal of Circuit Theory and Applications · 1992
Abstract This paper is concerned with determining simple CNN‐paradigm‐based circuits for solving specific binary image‐processing problems. Single‐layer CNN templates for performing specified shape extraction, extraction of shapes which contain a desired feature and modified feature detection are derived using a formulated design strategy. the concept of CNNs composed of modified cells is developed and circuits designed for realizing simultaneous detection of distinct features and for extracting horizontal line midpoints are presented.