Straightforward design of robust cellular neural networks for image processing

The analytical design of cellular neural network (CNN) templates for image processing often goes through the resolution of pixel level analytical rule-based task descriptions involving ideal CNN models. Due to nonideal analog implementations of CNN, recent issues have addressed the template robustness in order to achieve fault-tolerant processing. However, besides their efficiency and usefulness for the definition of coupled operators, rule-based approaches can make CNN templates design appear to be an intricate art reserved for initiated CNN specialists rather than for image processing scientists. An alternative straightforward analytical design method for uncoupled CNNs, which is until now the only unified approach to the design of both gray and binary output operators, has already been presented, and is now extended to the design of robust binary operators.