Title :
A network mechanism for the determination of apparent orientation
Author_Institution :
Inst. of Inf. Sci. & Electron., Tsukuba Univ., Ibaraki, Japan
Abstract :
Proposes a network mechanism for the determination of apparent tilt based on human psychophysics and physiology. The network model is capable of determining the apparent orientation of bars, including those in various types of tilt illusion. The model extracts local orientation information by VI-cell-like units with a Gabor-like receptive field. The activities of the units are grouped together based on collinear synchronization observed in a VI superficial layer. The model shows good quantitative agreement with human responses in the determination of the apparent orientations of bars in a variety of bar junctions
Keywords :
image segmentation; neural nets; physiological models; visual perception; Gabor-like receptive field; VI superficial layer; VI-cell-like units; apparent orientation; apparent tilt; collinear synchronization; local orientation information; network mechanism; tilt illusion; Bars; Brain modeling; Computer networks; Computer vision; Data mining; Humans; Mechanical factors; Painting; Physiology; Psychology;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.903703