A new kind of shadow detector based on CNN-UBN

In this paper, a new kind of two-dimensional cellular automata (CA) is studied. Several algorithmic rules are discovered that can be used to design new cellular neural networks (CNNs) that can implement a shadow detector for character recognition. The Boolean expressions and learning algorithms are introduced in detail. The results of computer simulation confirm that this new approach is simpler and more effective than that given in the literature. Furthermore, these results also confirm that we can design a new cellular neural network with CA rules and find a novel method to design CNNs.