Interactive Image Segmentation Based on Hierarchical Graph-Cut Optimization with Generic Shape Prior

A new algorithm for interactive image segmentation is proposed. Besides the traditional appearance and gradient information, a new Generic Shape Prior (GSP) knowledge which implies the location and the shape information of the object is combined into the framework. The GSP can be further categorized into the Regional and the Contour GSP to fit the interactive application, where a hierarchical graph-cut based optimization procedure is established, for its global optimization using the regional GSP to obtain good global segmentation results, and the local one using the Contour GSP to refine boundaries of global results. Moreover, the global optimization is based on superpixels which significantly reduce the computational complexity but preserve necessary image structures; the local one only considers a subset pixels around a contour segment, they both speed up the system. Results show our method performs better on both speed and accuracy.

[1]  Jian Sun,et al.  Lazy snapping , 2004, SIGGRAPH 2004.

[2]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Stan Z. Li,et al.  Markov Random Field Modeling in Image Analysis , 2001, Computer Science Workbench.

[4]  Pushmeet Kohli,et al.  Dynamic Graph Cuts for Efficient Inference in Markov Random Fields , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Stan Z. Li.  Markov Random Field Modeling in Image Analysis , 2009, Advances in Pattern Recognition.

[6]  Tao Zhang,et al.  Interactive graph cut based segmentation with shape priors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[7]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[8]  Olga Veksler,et al.  Star Shape Prior for Graph-Cut Image Segmentation , 2008, ECCV.

[9]  Richard Szeliski,et al.  A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Andrew J. Davison,et al.  Active Matching , 2008, ECCV.

[11]  Vladimir Kolmogorov,et al.  "GrabCut": interactive foreground extraction using iterated graph cuts , 2004, ACM Trans. Graph..

[12]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[13]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[14]  Pushmeet Kohli,et al.  Simultaneous Segmentation and Pose Estimation of Humans Using Dynamic Graph Cuts , 2008, International Journal of Computer Vision.

[15]  Andrew Blake,et al.  Image Segmentation by Branch-and-Mincut , 2008, ECCV.

[16]  Andrew Zisserman,et al.  OBJ CUT , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Vladimir Kolmogorov,et al.  Graph cut based image segmentation with connectivity priors , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.