Fuzzy reasoning for the design of CNN-based image processing systems
Marco Balsi, Francesco Voci · 2002
Fuzzy reasoning in image processing has been proved to be a very effective way to formalize complex inference techniques based on heuristics or experience, taking perceptual quality criteria into account. In this paper, we discuss implementation of fuzzy reasoning image processing on the standard cellular neural network universal machine. In this way, it is possible to employ such powerful massively parallel chips to speed up use of known algorithms, and to systematize design of new perceptual-quality driven CNN applications.