Distancecut: Interactive Real-Time Segmentation and Matting of Images and Videos (PREPRINT)

Abstract : An interactive algorithm for soft segmentation and matting of natural images and videos is presented in this paper. The technique follows and extends [11], where the user first roughly scribbles/labels different regions of interest, and from them the whole data is automatically segmented. The segmentation and alpha matte are obtained from the fast, linear complexity, computation of weighted distances to the user-provided scribbles. These weighted distances assign probabilities to each labelled class for every pixel. The weights are derived from models of the image regions obtained from the user provided scribbles via kernel density estimation. The matting results follow from combining this density and the computed weighted distances. We present the underlying framework and examples showing the capability of the algorithm to segment and compute alpha mattes in interactive real time, for difficult natural data.

[1]  Matthew P. Wand,et al.  Kernel Smoothing , 1995 .

[2]  Larry S. Davis,et al.  Improved fast gauss transform and efficient kernel density estimation , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[3]  William A. Barrett,et al.  Intelligent scissors for image composition , 1995, SIGGRAPH.

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

[5]  David Salesin,et al.  Keyframe-based tracking for rotoscoping and animation , 2004, ACM Trans. Graph..

[6]  Guillermo Sapiro,et al.  Interactive Image Segmentation via Adaptive Weighted Distances , 2007, IEEE Transactions on Image Processing.

[7]  Dani Lischinski,et al.  Colorization using optimization , 2004, ACM Trans. Graph..

[8]  Gareth Funka-Lea,et al.  Multi-label Image Segmentation for Medical Applications Based on Graph-Theoretic Electrical Potentials , 2004, ECCV Workshops CVAMIA and MMBIA.

[9]  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.

[10]  Laurent D. Cohen,et al.  Global Minimum for Active Contour Models: A Minimal Path Approach , 1997, International Journal of Computer Vision.

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

[12]  Michael F. Cohen,et al.  An iterative optimization approach for unified image segmentation and matting , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[13]  Hugues Talbot,et al.  Globally minimal surfaces by continuous maximal flows , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Guillermo Sapiro,et al.  An energy-based three-dimensional segmentation approach for the quantitative interpretation of electron tomograms , 2005, IEEE Transactions on Image Processing.

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

[16]  Guillermo Sapiro,et al.  O(N) implementation of the fast marching algorithm , 2006, Journal of Computational Physics.

[17]  Helen C. Shen,et al.  Semi-Supervised Classification Using Linear Neighborhood Propagation , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[18]  Guillermo Sapiro,et al.  Fast image and video colorization using chrominance blending , 2006, IEEE Transactions on Image Processing.

[19]  David Salesin,et al.  Video matting of complex scenes , 2002, SIGGRAPH.