DocumentCode :
3782659
Title :
Modelling perception of occluded Craik-O´Brien-Cornsweet Effect
Author :
Z. Nedic;P. Lozo;L.C. Jain
Author_Institution :
Univ. of South Australia, Adelaide, SA, Australia
fYear :
1999
Firstpage :
435
Lastpage :
438
Abstract :
Modern neural networks based on emulation of biological systems are successfully applied for solving many problems in visual signal processing. Among other applications, Form-And-Color-And-DEpth (FACADE) theory (S. Grossberg and D. Todorovic, 1987) was successfully implemented for processing the Craik-O´Brien-Cornsweet Effect (COCE) in 1D. But our further investigation of the proposed boundary contour system/feature-contour-system (BCS/FCS) model failed to give correct results in the case when a strip of different brightness is occluding one side of the classic form of COCE. We argue that this is the consequence of one BCS/FCS interaction proposed by the FACADE theory and therefore is not valid.
Keywords :
"Machine vision","Brightness","Humans","Australia","Artificial neural networks","Biological system modeling","Image processing","Biological neural networks","Psychology","Lakes"
Publisher :
ieee
Conference_Titel :
Knowledge-Based Intelligent Information Engineering Systems, 1999. Third International Conference
Print_ISBN :
0-7803-5578-4
Type :
conf
DOI :
10.1109/KES.1999.820216
Filename :
820216
Link To Document :
بازگشت