TY - GEN
T1 - Saliency and segregation without feature gradient
T2 - 2006 Conference on Computer Vision and Pattern Recognition Workshops
AU - Ben-Shahar, Ohad
PY - 2006/1/1
Y1 - 2006/1/1
N2 - The analysis of texture patterns, and texture segregation in particular, are at the heart of perceptual organization. In this paper we question the widely accepted view that the detection (both perceptual and computational) of salient perceptual singularities between perceptually coherent texture regions is tightly dependent upon feature gradients. Specifically, we study smooth orientation-defined textures (ODTs) and show that they exhibit striking perceptual singularities even without any outstanding gradients in their defining feature, namely orientation. We further show how these generic singularities are not only unpredictable from the orientation gradient, but that they also defy popular segmentation algorithms and neural models. We then examine smooth ODTs from a (differential) geometric point of view and develop a theory that fully predicts their perceptual singularities from two ODT curvatures. The computational results exhibit striking correspondence to segregation performed by human subjects and provide a conclusive evidence for the role of curvature in texture segregation. Extensions and implications of our results are developed for various aspects of visual processing.
AB - The analysis of texture patterns, and texture segregation in particular, are at the heart of perceptual organization. In this paper we question the widely accepted view that the detection (both perceptual and computational) of salient perceptual singularities between perceptually coherent texture regions is tightly dependent upon feature gradients. Specifically, we study smooth orientation-defined textures (ODTs) and show that they exhibit striking perceptual singularities even without any outstanding gradients in their defining feature, namely orientation. We further show how these generic singularities are not only unpredictable from the orientation gradient, but that they also defy popular segmentation algorithms and neural models. We then examine smooth ODTs from a (differential) geometric point of view and develop a theory that fully predicts their perceptual singularities from two ODT curvatures. The computational results exhibit striking correspondence to segregation performed by human subjects and provide a conclusive evidence for the role of curvature in texture segregation. Extensions and implications of our results are developed for various aspects of visual processing.
UR - http://www.scopus.com/inward/record.url?scp=33845537754&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2006.182
DO - 10.1109/CVPRW.2006.182
M3 - Conference contribution
AN - SCOPUS:33845537754
SN - 0769526462
SN - 9780769526461
T3 - 2006 Conference on Computer Vision and Pattern Recognition Workshops
SP - 175
EP - 182
BT - 2006 Conference on Computer Vision and Pattern Recognition Workshop
PB - Institute of Electrical and Electronics Engineers
Y2 - 17 June 2006 through 22 June 2006
ER -