Automatic CNN multi-template tree generation

We deal with the cellular neural network (CNN) research in the development of analogic algorithms that combine single templates to perform complex image processing. The results can be very useful for pattern recognition in industrial and robotic applications. This work presents a general methodology for the automatic generation of analogic algorithms by means of a genetic search. A genetic algorithm for generating multi-template trees, a concept derived from the AI field, is applied to the automatic generation of analogic algorithms based on both the genetic-evolutionary search and heuristic approaches.

[1]  R. Caponetto,et al.  Cellular neural network simulator for image processing applications , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[2]  Tamás Szirányi,et al.  Texture Classification and Segmentation by Cellular Neural Networks Using Genetic Learning , 1998, Comput. Vis. Image Underst..

[3]  Ángel Rodríguez-Vázquez,et al.  A VLSI-oriented continuous-time CNN model , 1996 .

[4]  Lin-Bao Yang,et al.  Cellular neural networks: theory , 1988 .

[5]  George S. Moschytz,et al.  Stochastic and hybrid approaches toward robust templates , 1998, 1998 Fifth IEEE International Workshop on Cellular Neural Networks and their Applications. Proceedings (Cat. No.98TH8359).

[6]  P. Szolgay,et al.  An experimental system for optical detection of layout errors of printed circuit boards using learned CNN templates , 1992, CNNA '92 Proceedings Second International Workshop on Cellular Neural Networks and Their Applications.

[7]  Leon O. Chua,et al.  Analogic CNN algorithms for some image compression and restoration tasks , 1995 .