UNIGE document Chapitre d'actes
previous document  unige:47732  next document
add to browser collection
Title

Figure-ground separation: evidence for asynchronous processing in visual perception?

Author
Published in H. Kaiser, R. Bach & H. Bunke. Third Annual Meeting of the Swiss Group for Artificial Intelligence and Cognitive Science. Biel-Bienne (Switzerland) - October 10-11, 1991 - Bern: Universität Bern. 1992, p. 36-48
Abstract The performance of the human visual system in extracting noisy figures from a noisy background is astonishingly good. Even in situations of very poor contrast, boundaries emerge clearly. Conversely, typical edge detectors fail to give good results for such images. In an attempt to explain the discrepancies in these performances we have developed a neural network model relying on two assumptions, both of which are based on neurophysiological findings. Firstly, the processing of visual information is considered ta be asynchronous: stimuli are delayed accordingly to their intensity. Secondly, emergent boundaries have the property of producing coherent responses corresponding to the (near)-simultaneous responses of cells in the cortical orientation columns. Results show that such neural network can indeed benefit from the asynchrony when treating images with ratio signal-to-noise particularly low.
Keywords asynchronous visual processingedge detectorneurophysiological model
Full text
Proceedings chapter (Published version) (1000 Kb) - public document Free access
Structures
Citation
(ISO format)
BURGI, Pierre-Yves. Figure-ground separation: evidence for asynchronous processing in visual perception?. In: H. Kaiser, R. Bach & H. Bunke (Ed.). Third Annual Meeting of the Swiss Group for Artificial Intelligence and Cognitive Science. Biel-Bienne (Switzerland). Bern : Universität Bern, 1992. p. 36-48. https://archive-ouverte.unige.ch/unige:47732

197 hits

67 downloads

Update

Deposited on : 2015-03-06

Export document
Format :
Citation style :