Classification of bidimensional images using artificial intelligence techniques

Abstract

This article presents the structure of an "intelligent classifier" composed of three modules: 1) the preprocessor, responsible for the transformation of the raw image; 2) the characteristics extractor, implemented by a genetic algorithm, which is responsible for the selection of the most relevant coefficients; and 3) the classifier, implemented by a neural network. Generic algorithms have been used as a search technique for large sets of data and neural networks, due to their ability to extract information from complex sets of data, have been largely applied in computer vision for pattern classification. The complete image classification system is invariant to translation rotation and sizing of the analysed object.