TY - GEN
T1 - Good continuation in layers
T2 - 2006 Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2006
AU - Ben-Shahar, Ohad
AU - Glaser, Andreas
AU - Zucker, Steven W.
PY - 2006/1/1
Y1 - 2006/1/1
N2 - We extend the concept of good continuation in a uniform fashion from boundaries to shading, hue, and texture. Each has the property that heal measurements yield an orientation, which we explicitly establish for hue using geometric harmonic techniques. Good continuation arises in a geometric sense, because these orientations all vary smoothly in an appropriate sense. Thus they correspond to flows. Taken together they define a layered set of flows, in the sense the "horizontal" computations within each flow provide global consistency while "vertical" computations across flows enable the identification of shading and shadowing and different types of edges. Evidence is reviewed that primate visual systems enjoy such an organization.1
AB - We extend the concept of good continuation in a uniform fashion from boundaries to shading, hue, and texture. Each has the property that heal measurements yield an orientation, which we explicitly establish for hue using geometric harmonic techniques. Good continuation arises in a geometric sense, because these orientations all vary smoothly in an appropriate sense. Thus they correspond to flows. Taken together they define a layered set of flows, in the sense the "horizontal" computations within each flow provide global consistency while "vertical" computations across flows enable the identification of shading and shadowing and different types of edges. Evidence is reviewed that primate visual systems enjoy such an organization.1
UR - https://www.scopus.com/pages/publications/33845527693
U2 - 10.1109/CVPRW.2006.91
DO - 10.1109/CVPRW.2006.91
M3 - Conference contribution
AN - SCOPUS:33845527693
SN - 0769526462
SN - 9780769526461
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
BT - 2006 Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2006
Y2 - 17 June 2006 through 22 June 2006
ER -