Full text
| |
| Author(s): |
Estevão Esmi
Total Authors: 1
|
| Document type: | Master's Dissertation |
| Press: | Campinas, SP. |
| Institution: | Universidade Estadual de Campinas (UNICAMP). Instituto de Matemática, Estatística e Computação Científica |
| Defense date: | 2010-04-26 |
| Examining board members: |
Peter Sussner;
Alvaro Rodolfo De Pierro;
Marcos Eduardo Ribeiro do Valle Mesquita;
Fernando José Von Zuben
|
| Advisor: | Peter Sussner |
| Abstract | |
Morphological neural networks (MNN) are artificial neural networks whose hidden neurons perform elementary operations of mathematical morphology (MM). Several particular models of MNNs have been proposed in recent years, including morphological perceptrons (MPs), morphological perceptrons with dendrites, (fuzzy) morphological associative memories, modular morphological neural networks as well as morphological shared-weight and regularization neural networks. Applications of MNNs include pattern recognition, time series prediction, target detection, self-location, and hyper-spectral image processing. In this thesis, we present two new models of morphological neural networks. The first one consists of a fuzzy associative memory called KS-FAM. The second one represents a novel version of the morphological perceptron for classification problems with multiple classes called morphological perceptron with competitive learning(MP/CL). For both KS-FAM and MP/CL models, we investigated and showed several properties. In particular, we characterized the conditions for perfect recall using the KS-FAM as well as the outputs produced upon presentation of an arbitrary input patern. In addition, we proved that the learning algorithm of the MP/CL converges in a finite number of steps and that the results produced after the conclusion of the training phase do not depend on the order in which the training patterns are presented to the network. Moreover, the MP/CL is guaranteed to perfectly classify all training data without generating any regions of indecision. Finaly, we compared the performances of our new models and a range of competing models in terms of a series of experiments in gray-scale image recognition (in case of the KS-FAM) and classification using several well-known datasets that are available on the internet (in case of the MP/CL) (AU) | |
| FAPESP's process: | 06/05868-5 - Modified models of morphological neural networks |
| Grantee: | Estevão Esmi Laureano |
| Support Opportunities: | Scholarships in Brazil - Master |