The Tractability of Segmentation and Scene Analysis

One of the fundamental problems in computer vision is the segmentation of an image into semantically meaningful regions, based only on image characteristics. A single segmentation can be determined using a linear number of evaluations of a uniformity predicate. However, minimising the number of regions is shown to be an NP-complete problem. We also show that the variational approach to segmentation, based on minimising a criterion combining the overall variance of regions and the number of regions, also gives rise to an NP-complete problem.When a library of object models is available, segmenting the image becomes a problem of scene analysis. A sufficient condition for the reconstruction of a 3D scene from a 2D image to be solvable in polynomial time is that the scene contains no cycles of mutually occluding objects and that no range information can be deduced from the image. It is known that relaxing the no cycles condition renders the problem NP-complete. We show that relaxing the no range information condition also produces an NP-complete problem.

[1]  Alfred V. Aho,et al.  The Design and Analysis of Computer Algorithms , 1974 .

[2]  Theodosios Pavlidis,et al.  Structural pattern recognition , 1977 .

[3]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[4]  M. Garey.  Johnson: computers and intractability: a guide to the theory of np- completeness (freeman , 1979 .

[5]  Michael L. Baird,et al.  Structural Pattern Recognition , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  David Lichtenstein,et al.  Planar Formulae and Their Uses , 1982, SIAM J. Comput..

[7]  Christos H. Papadimitriou,et al.  The complexity of recognizing polyhedral scenes , 1985, 26th Annual Symposium on Foundations of Computer Science (sfcs 1985).

[8]  K. Sugihara.  Machine interpretation of line drawings , 1986, MIT Press series in artificial intelligence.

[9]  Olivier D. Faugeras,et al.  HYPER: A New Approach for the Recognition and Positioning of Two-Dimensional Objects , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Charles R. Dyer,et al.  Two-dimensional object recognition using multiresolution models , 1986, Comput. Vis. Graph. Image Process..

[11]  Yehezkel Lamdan,et al.  Object recognition by affine invariant matching , 2011, Proceedings CVPR '88: The Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Martin C. Cooper.  Efficient systematic analysis of occlusion , 1988, Pattern Recognit. Lett..

[13]  Morris Goldberg,et al.  Hierarchy in Picture Segmentation: A Stepwise Optimization Approach , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Edward J. Delp,et al.  Partial shape recognition: a landmark-based approach , 1989, Conference Proceedings., IEEE International Conference on Systems, Man and Cybernetics.

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

[16]  S. Sutherland.  Seeing things , 1989, Nature.

[17]  Sang Uk Lee,et al.  On the color image segmentation algorithm based on the thresholding and the fuzzy c-means techniques , 1990, Pattern Recognit..

[18]  John K. Tsotsos.  Analyzing vision at the complexity level , 1990, Behavioral and Brain Sciences.

[19]  Lalit Gupta,et al.  Robust partial shape classification using invariant breakpoints and dynamic alignment , 1990, Pattern Recognit..

[20]  Edward J. Delp,et al.  Partial Shape Recognition: A Landmark-Based Approach , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Lefteris M. Kirousis.  Effectively Labeling Planar Projections of Polyhedra , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  P. Kube.  Unbounded visual search is not both biologically plausible and NP - Complete , 1991, Behavioral and Brain Sciences.

[23]  Todd A. Cass,et al.  Polynomial-Time Object Recognition in the Presence of Clutter, Occlusion, and Uncertainty , 1992, ECCV.

[24]  Martin C. Cooper.  Visual occlusion and the interpretation of ambiguous pictures , 1992 .

[25]  Julian R. Ullmann.  Analysis of 2-D Occlusion by Subtracting Out , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[26]  Lefteris M. Kirousis,et al.  Fast Parallel Constraint Satisfaction , 1993, Artif. Intell..

[27]  Peter Eades,et al.  The complexity of computing minimum separating polygons , 1993, Pattern Recognit. Lett..

[28]  David Mumford,et al.  Filtering, Segmentation and Depth , 1993, Lecture Notes in Computer Science.

[29]  Sankar K. Pal,et al.  A review on image segmentation techniques , 1993, Pattern Recognit..

[30]  Vincent Torre,et al.  On the Complexity of Labeling Perspective Projections of Polyhedral Scenes , 1994, Artif. Intell..

[31]  Martin C. Cooper,et al.  Characterising Tractable Constraints , 1994, Artif. Intell..

[32]  Martin C. Cooper.  Interpreting line drawings of curved objects with tangential edges and surfaces , 1997, Image Vis. Comput..

[33]  Xie Yuan-dan,et al.  Survey on Image Segmentation , 2002 .

[34]  Nick D. Dendris,et al.  An efficient parallel algorithm for geometrically characterising drawings of a class of 3-D objects , 1992, Journal of Mathematical Imaging and Vision.