Registro Completo |
Biblioteca(s): |
Embrapa Agricultura Digital. |
Data corrente: |
08/08/1996 |
Data da última atualização: |
03/08/2007 |
Autoria: |
ALVES, A. H. H.; MASCARENHAS, N. de A. |
Título: |
Probabilistic and dictionary-based relaxation techniques applied to a statistical method of edge detection. |
Ano de publicação: |
1993 |
Fonte/Imprenta: |
In: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO GRÁFICA E PROCESSAMENTO DE IMAGENS, 6., 1993, Recife. Anais... Recife: SBC: UFPe, 1993. |
Páginas: |
p.81-87. |
Idioma: |
Inglês |
Notas: |
Evento conhecido como SIBGRAPI. Editado por Luiz H. de Figueiredo e Jonas de Miranda Gomes. |
Conteúdo: |
Two relaxation schemes, a probabilistic and a dictionary-based one, applied to edge detection, are described. The problem of edge detection is defined using a statistical approach. The problem of edge detection is defined using a statistical approach. The solution, in terms of statitical decision theory, leads to a test among hypotheses of configurations of sets of four pixels (quadriples). The relaxation schemes are also developed using the quadriplets as labeling objects. The initial probabilities for the label set of each object are sinthesized from the values obtained in the statistical tests. The interaction neighbourhood adopted for the two methods is the 4-neighbourdhood. The iterative label probaability updating is performed using a classical heuristic procedure in the two schemes. Tests using noisy synthetic and real images are presented. An experimental analysis of convergence to a consistent and non-ambiguous blabelling and speed of convergence is performed for the two schemes and the results are compared. A change in the dictionary according to a modification in the definition of consistency is proposed and the resulting scheme is tested and compared with the two other ones. |
Categoria do assunto: |
-- |
Marc: |
LEADER 01838naa a2200157 a 4500 001 1003182 005 2007-08-03 008 1993 bl uuuu u00u1 u #d 100 1 $aALVES, A. H. H. 245 $aProbabilistic and dictionary-based relaxation techniques applied to a statistical method of edge detection. 260 $c1993 300 $ap.81-87. 500 $aEvento conhecido como SIBGRAPI. Editado por Luiz H. de Figueiredo e Jonas de Miranda Gomes. 520 $aTwo relaxation schemes, a probabilistic and a dictionary-based one, applied to edge detection, are described. The problem of edge detection is defined using a statistical approach. The problem of edge detection is defined using a statistical approach. The solution, in terms of statitical decision theory, leads to a test among hypotheses of configurations of sets of four pixels (quadriples). The relaxation schemes are also developed using the quadriplets as labeling objects. The initial probabilities for the label set of each object are sinthesized from the values obtained in the statistical tests. The interaction neighbourhood adopted for the two methods is the 4-neighbourdhood. The iterative label probaability updating is performed using a classical heuristic procedure in the two schemes. Tests using noisy synthetic and real images are presented. An experimental analysis of convergence to a consistent and non-ambiguous blabelling and speed of convergence is performed for the two schemes and the results are compared. A change in the dictionary according to a modification in the definition of consistency is proposed and the resulting scheme is tested and compared with the two other ones. 700 1 $aMASCARENHAS, N. de A. 773 $tIn: SIMPÓSIO BRASILEIRO DE COMPUTAÇÃO GRÁFICA E PROCESSAMENTO DE IMAGENS, 6., 1993, Recife. Anais... Recife: SBC: UFPe, 1993.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Agricultura Digital (CNPTIA) |
|