Title :
A Markov random field model of subjective contour perception
Author :
Cooper, Paul R. ; Hyun, Seungseok ; Yuen, Patrick
Author_Institution :
Intelligent Perception & Action Lab., Northwestern Univ., Evanston, IL, USA
Abstract :
We describe a model of subjective contour perception that sees the triangle: top-down feedback from the perception of an occluding object causes the perception of illusory contrast along the object´s boundary. Unlike other approaches, the model explicitly incorporates a representational hierarchy of visual elements at multiple levels of abstraction, for example, both local contrast edges and triangles. The model is a connectionist network implemented within the formal framework of Markov random fields, which provides for bidirectional information flow over connections. Simulation results show how feedforward activation yields the perception of the occluding triangle at a high-level of abstraction, and how feedback activates the units that represent the illusory contrast
Keywords :
Markov processes; edge detection; feedback; feedforward; neural nets; physiological models; visual perception; Markov random field model; bidirectional information flow; connectionist network; feedforward activation; illusory contrast; local contrast edges; occluding object; subjective contour perception; top-down feedback; triangles; Biological neural networks; Biological system modeling; Computational modeling; Feedback; Focusing; Image segmentation; Markov random fields; Neurofeedback; Psychology;
Conference_Titel :
Pattern Recognition, 1996., Proceedings of the 13th International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-8186-7282-X
DOI :
10.1109/ICPR.1996.547242