TY - GEN
T1 - Global active contour-based image segmentation via probability alignment
AU - Myronenko, Andriy
AU - Song, Xubo
PY - 2009
Y1 - 2009
N2 - Active contours is a popular technique for image segmentation. However, active contour tend to converge to the closest local minimum of its energy function and often requires a close boundary initialization. We introduce a new approach that overcomes the close boundary initialization problem by reformulating the external energy term. We treat the active contour as a mean curve of the probability density function p(x). It moves to minimize the Kullback-Leibler (KL) divergence between p(x) and the probability density function derived from the image. KL divergence forces p(x) to .cover all image areas. and the uncovered areas are heavily penalized, which allows the active contour to go over the edges. Also we use deterministic annealing on the width of p(x) to implement a coarse-to-fine search strategy. In the limit, when the width of p(x) goes to zero, the KL divergence function converges to the conventional external energy term (which can be seen a special case) of active contours. Our method produces robust segmentation results from arbitrary initialization positions.
AB - Active contours is a popular technique for image segmentation. However, active contour tend to converge to the closest local minimum of its energy function and often requires a close boundary initialization. We introduce a new approach that overcomes the close boundary initialization problem by reformulating the external energy term. We treat the active contour as a mean curve of the probability density function p(x). It moves to minimize the Kullback-Leibler (KL) divergence between p(x) and the probability density function derived from the image. KL divergence forces p(x) to .cover all image areas. and the uncovered areas are heavily penalized, which allows the active contour to go over the edges. Also we use deterministic annealing on the width of p(x) to implement a coarse-to-fine search strategy. In the limit, when the width of p(x) goes to zero, the KL divergence function converges to the conventional external energy term (which can be seen a special case) of active contours. Our method produces robust segmentation results from arbitrary initialization positions.
UR - http://www.scopus.com/inward/record.url?scp=70450159370&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70450159370&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2009.5206552
DO - 10.1109/CVPRW.2009.5206552
M3 - Conference contribution
AN - SCOPUS:70450159370
SN - 9781424439935
T3 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
SP - 2798
EP - 2804
BT - 2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
PB - IEEE Computer Society
T2 - 2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Y2 - 20 June 2009 through 25 June 2009
ER -