Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Object selection based on oscillatory correlation
Autore:
Wang, DL;
Indirizzi:
Ohio State Univ, Dept Informat & Comp Sci, Columbus, OH 43210 USA Ohio State Univ Columbus OH USA 43210 & Comp 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:
NEURAL NETWORKS
fascicolo: 4-5, volume: 12, anno: 1999,
pagine: 579 - 592
SICI:
0893-6080(199906)12:4-5<579:OSBOOC>2.0.ZU;2-9
Fonte:
ISI
Lingua:
ENG
Soggetto:
FIGURE-GROUND SEPARATION; NEURAL OSCILLATORS; VISUAL-ATTENTION; CORTICAL DYNAMICS; NETWORK; VISION; MODEL; SYNCHRONIZATION; PERCEPTION; NEURONS;
Keywords:
object selection; oscillatory correlation; local cooperation; global competition; selective attention; LEGION; WTA;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Engineering, Computing & Technology
Citazioni:
41
Recensione:
Indirizzi per estratti:
Indirizzo: Wang, DL Ohio0State Univ, Dept Informat & Comp Sci, 2015 Neil Ave, Columbus, OH 4321 Ohio State Univ 2015 Neil Ave Columbus OH USA 43210 mbus, OH 4321
Citazione:
D.L. Wang, "Object selection based on oscillatory correlation", NEURAL NETW, 12(4-5), 1999, pp. 579-592

Abstract

One of the classical topics in neural networks is winner-take-all (WTA), which has been widely used in unsupervised (competitive) learning, conical processing, and attentional control. Owing to global connectivity, WTA networks, however, do not encode spatial relations in dhe input. and thus cannotsupport sensory and perceptual processing where spatial relations are important. We propose a new architecture that maintains spatial relations between input features. This selection network builds on Locally Excitatory Globally Inhibitory Oscillator Networks (LEGION) dynamics and slow inhibition. In an input scene with many objects (patterns), the network selects the largest object. This system can be easily adjusted to select several largest objects, which then alternate in time. We analyze the speed of selection, and further show that a two-stage selection network gains efficiency by combining selection with parallel removal of noisy regions. The network is applied to select the most salient object in gray-level images. As a special case, the selection network without local excitation gives rise to a new form of oscillatory WTA. (C) 1999 Elsevier Science Ltd. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 07/08/20 alle ore 00:37:36