Modeling multiple object scenarios for feature recognition and classification using cellular neural networks
Malumedzha, Tendani Calven
Cellular neural networks (CNNs) have been adopted in the spatio-temporal processing research field as a paradigm of complexity. This is due to the ease of designs for complex spatio-temporal tasks introduced by these networks. This has led to an increase in the adoption of CNNs for on-chip VLSI implementations. This dissertation proposes the use of a Cellular Neural Network to model, detect and classify objects appearing in multiple object scenes. The algorithm proposed is based on image scene enhancement through anisotropic diffusion; object detection and extraction through binary edge detection and boundary tracing; and object classification through genetically optimised associative networks and texture histograms. The first classification method is based on optimizing the space-invariant feedback template of the zero-input network through genetic operators, while the second method is based on computing diffusion filtered and modified histograms for object classes to generate decision boundaries that can be used to classify the objects. The primary goal is to design analogic algorithms that can be used to perform these tasks. While the use of genetically optimized associative networks for object learning yield an efficiency of over 95%, the use texture histograms has been found very accurate though there is a need to develop a better technique for histogram comparisons. The results found using these analogic algorithms affirm CNNs as well-suited for image processing tasks.