Reconhecimento de caracteres numéricos manuscritos com autômatos celulares, através da noção de protótipos espectrais

Página do item simplificado
dc.contributor.advisorOliveira, Pedro Paulo Balbi dept_BR
dc.contributor.advisor1Latteshttp://lattes.cnpq.br/9556738277476279por
dc.contributor.authorOliveira Junior, Carlos Candido dept_BR
dc.creator.Latteshttp://lattes.cnpq.br/5529110835412390por
dc.date.accessioned2016-03-15T19:38:06Z
dc.date.accessioned2020-05-28T18:08:41Z
dc.date.available2007-12-06pt_BR
dc.date.available2020-05-28T18:08:41Z
dc.date.issued2006-03-07pt_BR
dc.description.abstractThe computational ability of cellular automata (CAs) has been investigated in many research initiatives in the literature. Among them, one possibility is their use as spatial pattern recognizers. Here, we attempt to use CAs to recognize handwritten numerical characters, by looking for CA rules which, running on different initial configurations that represent the same handwritten digit, would lead the temporal evolution to equivalent final configurations (defining the same spectral fixed point. The work uses a metric that allows the comparison between images based on their spectral similarity, drawn from a previous work, as well as a proposal therein on the way elementary CA rules are applied (in a crossed fashion) so as to allow the reduction in the size of the rule space involved. Conceptual structures are defined to support the recognition experiments, namely, the notions of spectral fixed point, spectral prototype, and a measure of a rule potential to perform well in the recognition task. The latter entailed from various studies on the attributes a good rule should account for, and, once defined, made it possible an evolutionary search in that space. Here we show some rules that yielded positive results in the recognition of the image used for training (i.e., those used in the definition of the recognition prototypes), and further results on the attempt to carry out real recognition experiments, with images not used for training, whose results are not yet satisfactory.eng
dc.description.sponsorshipWolfram Research, Inc.pt_BR
dc.formatapplication/pdfpor
dc.identifier.citationOLIVEIRA JUNIOR, Carlos Candido de. Reconhecimento de caracteres numéricos manuscritos com autômatos celulares, através da noção de protótipos espectrais. 2006. 144 f. Dissertação (Mestrado em Engenharia Elétrica) - Universidade Presbiteriana Mackenzie, São Paulo, 2006.por
dc.identifier.urihttp://dspace.mackenzie.br/handle/10899/24393
dc.languageporpor
dc.publisherUniversidade Presbiteriana Mackenziepor
dc.rightsAcesso Abertopor
dc.subjectautômatos celularespor
dc.subjectalgoritmos genéticospor
dc.subjectprotótipo espectralpor
dc.subjectautomata cellulareng
dc.subjectgenetic algorithmseng
dc.subjectspectral prototypeeng
dc.subject.cnpqCNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAOpor
dc.thumbnail.urlhttp://tede.mackenzie.br/jspui/retrieve/3565/Carlos%20Candido%20de%20Oliveira%20Junior.pdf.jpg*
dc.titleReconhecimento de caracteres numéricos manuscritos com autômatos celulares, através da noção de protótipos espectraispor
dc.typeDissertaçãopor
local.contributor.board1Marengoni, Mauríciopt_BR
local.contributor.board1Latteshttp://lattes.cnpq.br/1974791787566027por
local.contributor.board2Macau, Elbert Einstein Nehrerpt_BR
local.contributor.board2Latteshttp://lattes.cnpq.br/0793627832164040por
local.publisher.countryBRpor
local.publisher.departmentEngenharia Elétricapor
local.publisher.initialsUPMpor
local.publisher.programEngenharia Elétricapor
Arquivos
Pacote Original
Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
Carlos Candido de Oliveira Junior.pdf
Tamanho:
2.44 MB
Formato:
Adobe Portable Document Format
Descrição:
Baixar
Coleções
Engenharia Elétrica e Computação - Dissertações - EE Higienópolis