2000 6th IEEE international workshop on cellular neural networks and their applications proceedings

摘要

A fruitful field into the CNN research is being the development of analogic algorithms utilizing combinations of single templates to perform complex image processing tasks dedicated to industrial applications, vision problems in robotics, pattern analysis, etc. In this work a software implementation for the automatic generation of analogic algorithms by mean of a genetic search is presented. First, we ore going to shortly present an improved automatic templates generation, task already solved in before works. Next, an algorithm for generating templates in cascade will be showed like the natural and original extension of the already known tool. Lastly, the multi-template tree concept derived from the AI field is applied in the automatic generation of analog algorithms, and its solution based in both genetic-evolutionory search and heuristic methods are exposed.