Toward Perception-Based Shape Decomposition

The aim of this work is to decompose shapes into parts which are consistent to human perception. We propose a novel shape decomposition method which utilizes the three perception rules suggested by psychological study: the Minima rule, the Short-cut rule and the Convexity rule. Unlike the previous work, we focus on improving the convexity of the decomposed parts while minimizing the cut length as much as possible. The problem is formulated as a combinatorial optimization problem and solved by a quadratic programming method. In addition, we consider the curved branches which introduce "false" concavity. To solve this problem, we straighten the curved branches before shape decomposition which makes the results more consistent with human perception. We test our approach on the MPEG-7 shape dataset, and the comparison results to previous work show that the proposed method can improve the part convexity while keeping the cuts short, and the decomposition is more consistent with human perception.

[1]  Antonio Torralba,et al.  Part and appearance sharing: Recursive Compositional Models for multi-view , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Thomas Deselaers,et al.  ClassCut for Unsupervised Class Segmentation , 2010, ECCV.

[4]  Johan Löfberg,et al.  YALMIP : a toolbox for modeling and optimization in MATLAB , 2004 .

[5]  Walter Gerbino,et al.  Convexity and Symmetry in Figure-Ground Organization , 1976 .

[6]  Ulrich Eckhardt,et al.  Shape descriptors for non-rigid shapes with a single closed contour , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[7]  Donald D. Hoffman,et al.  Parsing silhouettes: The short-cut rule , 1999, Perception & psychophysics.

[8]  Paul L. Rosin.  Shape Partitioning by Convexity , 1999, BMVC.

[9]  Rama Chellappa,et al.  Articulation-Invariant Representation of Non-planar Shapes , 2010, ECCV.

[10]  Xiaofeng Mi,et al.  Separating Parts from 2D Shapes using Relatability , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[11]  Mary Henle,et al.  Vision and artifact , 1977 .

[12]  Robert B. Fisher,et al.  Model-driven grouping and recognition of generic object parts from single images , 1997, Robotics Auton. Syst..

[13]  Donald D. Hoffman,et al.  Parts of recognition , 1984, Cognition.

[14]  Junsong Yuan,et al.  Minimum near-convex decomposition for robust shape representation , 2011, 2011 International Conference on Computer Vision.

[15]  Hongyuan Wang,et al.  Skeleton growing and pruning with bending potential ratio , 2011, Pattern Recognit..

[16]  Haibin Ling,et al.  Shape Classification Using the Inner-Distance , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Longin Jan Latecki,et al.  Convexity Rule for Shape Decomposition Based on Discrete Contour Evolution , 1999, Comput. Vis. Image Underst..

[18]  Kaleem Siddiqi,et al.  Parts of visual form: computational aspects , 1993, Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[19]  Jitendra Malik,et al.  Can convexity explain how humans segment objects into parts , 2010 .

[20]  Song Wang,et al.  Two perceptually motivated strategies for shape classification , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[21]  Wenyu Liu,et al.  Convex shape decomposition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.