Prior-based segmentation by projective registration and level sets

Object detection and segmentation can be facilitated by the availability of a reference object. However, accounting for possible transformations between the different object views, as part of the segmentation process, remains a challenge. Recent works address this problem by using comprehensive training data. Other approaches are applicable only to limited object classes or can only accommodate similarity transformations. We suggest a novel variational approach to prior-based segmentation, which accounts for planar projective transformation, using a single reference object. The prior shape is registered concurrently with the segmentation process, without point correspondence. The algorithm detects the object of interest and correctly extracts its boundaries. The homography between the two object views is accurately recovered as well. Extending the Chan-Vese level set framework, we propose a region-based segmentation functional that includes explicit representation of the projective homography between the prior shape and the shape to segment. The formulation is derived from two-view geometry. Segmentation of a variety of objects is demonstrated and the recovered transformation is verified.

[1]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[2]  Daniel Cremers,et al.  Shape statistics in kernel space for variational image segmentation , 2003, Pattern Recognit..

[3]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .

[4]  C. E. Springer,et al.  Geometry and Analysis of Projective Spaces , 1967 .

[5]  Michal Irani,et al.  All About Direct Methods , 1999 .

[6]  Dimitris N. Metaxas,et al.  Learning Coupled Prior Shape and Appearance Models for Segmentation , 2004, MICCAI.

[7]  Stefano Soatto,et al.  Region Matching with Missing Parts , 2002, ECCV.

[8]  Daniel Cremers,et al.  Multiphase Dynamic Labeling for Variational Recognition-Driven Image Segmentation , 2004, ECCV.

[9]  O. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2002, 5th IEEE EMBS International Summer School on Biomedical Imaging, 2002..

[10]  Pierre Kornprobst,et al.  Mathematical problems in image processing - partial differential equations and the calculus of variations , 2010, Applied mathematical sciences.

[11]  Nahum Kiryati,et al.  Unlevel-Sets: Geometry and Prior-Based Segmentation , 2004, ECCV.

[12]  S. Osher,et al.  Algorithms Based on Hamilton-Jacobi Formulations , 1988 .

[13]  Nikos Paragios,et al.  Shape Priors for Level Set Representations , 2002, ECCV.

[14]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[15]  S. Shankar Sastry,et al.  An Invitation to 3-D Vision , 2004 .

[16]  O. Faugeras,et al.  The Geometry of Multiple Images , 1999 .

[17]  Yunmei Chen,et al.  Using Prior Shapes in Geometric Active Contours in a Variational Framework , 2002, International Journal of Computer Vision.

[18]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[19]  W. Eric L. Grimson,et al.  A shape-based approach to the segmentation of medical imagery using level sets , 2003, IEEE Transactions on Medical Imaging.