A neural network for handwritten pattern recognition

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 1996

Autores

santos, nmp (Autor) Outra; oliveira, ed (Autor) FEUP

Ata de Conferência Internacional

Título: MELECON '96 - 8TH MEDITERRANEAN ELECTROTECHNICAL CONFERENCE, PROCEEDINGS, VOLS I-III: INDUSTRIAL APPLICATIONS IN POWER SYSTEMS, COMPUTER SCIENCE AND TELECOMMUNICATIONS

Páginas: 665-668

8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications (Melecon 96)

BARI, ITALY, MAY 13-16, 1996

Indexação

ISI Web of Knowledge - 0 Citações

Scopus - 0 Citações

Classificação Científica

FOS: Ciências da engenharia e tecnologias > Engenharia electrotécnica, electrónica e informática

Outras Informações

ID Authenticus: P-001-FEM

Abstract (EN): Neuroscientists are mainly interested in the study of the behavior of an all set of cells, while AI researchers study how to extract, freeze and analyze the process, by means of models, and learn the specificity of each kind of neuron's behavior. Our aim is to describe a neural network based system, inspired by the optical structure of human cortex area and its application to pattern recognition. We adopted an unsupervised learning algorithm that is applied to each presented pattern. The system's most relevant feature is its insensibility to spatial shift variance. The system's behavior is based on the identification and decomposition of the relevant input image characteristics, that will be used to achieve classification. Finally, we briefly describe a case study followed by some conclusion.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 4