Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Weight adaptation and oscillatory correlation for image segmentation
Autore:
Chen, K; Wang, DL; Liu, XW;
Indirizzi:
Peking Univ, Natl Lab Machine Percept, Beijing 100871, Peoples R China Peking Univ Beijing Peoples R China 100871 ijing 100871, Peoples R China Peking Univ, Ctr Informat Sci, Beijing 100871, Peoples R China Peking Univ Beijing Peoples R China 100871 ijing 100871, Peoples R China Ohio State Univ, Dept Comp & Informat Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 nformat Sci, Columbus, OH 43210 USA Ohio State Univ, Ctr Cognit Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 Cognit Sci, Columbus, OH 43210 USA
Titolo Testata:
IEEE TRANSACTIONS ON NEURAL NETWORKS
fascicolo: 5, volume: 11, anno: 2000,
pagine: 1106 - 1123
SICI:
1045-9227(200009)11:5<1106:WAAOCF>2.0.ZU;2-J
Fonte:
ISI
Lingua:
ENG
Soggetto:
PERCEPTUAL ORGANIZATION; EDGE-DETECTION; ANISOTROPIC DIFFUSION; NEURAL OSCILLATORS; REGION; INFORMATION; COMPETITION; ALGORITHM; NETWORKS;
Keywords:
desynchronization; image segmentation; LEGION; nonlinear smoothing; oscillatory correlation; synchronization; weight adaptation;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
45
Recensione:
Indirizzi per estratti:
Indirizzo: Chen, K Peking Univ, Natl Lab Machine Percept, Beijing 100871, Peoples R China Peking Univ Beijing Peoples R China 100871 0871, Peoples R China
Citazione:
K. Chen et al., "Weight adaptation and oscillatory correlation for image segmentation", IEEE NEURAL, 11(5), 2000, pp. 1106-1123

Abstract

We propose a method for image segmentation based on a neural oscillator network, Unlike previous methods, weight adaptation is adopted during segmentation to remove noise and preserve significant discontinuities in an image. Moreover, a logarithmic grouping rule is proposed to facilitate grouping of oscillators representing pixels with coherent properties. We show that weight adaptation plays the roles of noise removal and feature preservation. In particular, our weight adaptation scheme is insensitive to termination time and the resulting dynamic weights in a wide range of iterations lead tothe same segmentation results. A computer algorithm derived from oscillatory dynamics is applied to synthetic and real images and simulation results show that the algorithm yields favorable segmentation results in comparisonwith other recent algorithms. In addition, the weight adaptation scheme can be directly transformed to a novel feature-preserving smoothing procedure: We also demonstrate that our nonlinear smoothing algorithm achieves good results for various kinds of images.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 28/03/20 alle ore 14:07:49