Matching shapes with self-intersections:application to leaf classification

We address the problem of two-dimensional (2-D) shape representation and matching in presence of self-intersection for large image databases. This may occur when part of an object is hidden behind another part and results in a darker section in the gray level image of the object. The boundary contour of the object must include the boundary of this part which is entirely inside the outline of the object. The curvature scale space (CSS) image of a shape is a multiscale organization of its inflection points as it is smoothed. The CSS-based shape representation method has been selected for MPEG-7 standardization. We study the effects of contour self-intersection on the curvature scale space image. When there is no self-intersection, the CSS image contains several arch shape contours, each related to a concavity or a convexity of the shape. Self intersections create contours with minima as well as maxima in the CSS image. An efficient shape representation method has been introduced in this paper which describes a shape using the maxima as well as the minima of its CSS contours. This is a natural generalization of the conventional method which only includes the maxima of the CSS image contours. The conventional matching algorithm has also been modified to accommodate the new information about the minima. The method has been successfully used in a real world application to find, for an unknown leaf, similar classes from a database of classified leaf images representing different varieties of chrysanthemum. For many classes of leaves, self-intersection is inevitable during the scanning of the image. Therefore the original contributions of this paper is the generalization of the curvature scale space representation to the class of 2-D contours with self-intersection, and its application to the classification of Chrysanthemum leaves.

[1]  Jan J. Koenderink,et al.  Solid shape , 1990 .

[2]  Wesley E. Snyder,et al.  Application of Affine-Invariant Fourier Descriptors to Recognition of 3-D Objects , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Farzin Mokhtarian,et al.  A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Rajiv Mehrotra,et al.  Feature-based retrieval of similar shapes , 1993, Proceedings of IEEE 9th International Conference on Data Engineering.

[5]  Christos Faloutsos,et al.  QBIC project: querying images by content, using color, texture, and shape , 1993, Electronic Imaging.

[6]  Jan Flusser,et al.  Pattern recognition by affine moment invariants , 1993, Pattern Recognit..

[7]  Peter Eggleston.  Constraint-based feature indexing and retrieval for image databases , 1993, Other Conferences.

[8]  Du-Ming Tsai,et al.  Curve fitting approach for tangent angle and curvature measurements , 1994, Pattern Recognit..

[9]  Zhaohui Huang,et al.  Affine-invariant B-spline moments for curve matching , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Michael Lindenbaum,et al.  Curve Segmentation Under Partial Occlusion , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Alex Pentland,et al.  Modal Matching for Correspondence and Recognition , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Borko Furht,et al.  Video and Image Processing in Multimedia Systems , 1995 .

[13]  Wayne Niblack,et al.  A pseudo-distance measure for 2D shapes based on turning angle , 1995, Proceedings., International Conference on Image Processing.

[14]  Chi-Wang Shu,et al.  Geometric shock-capturing ENO schemes for subpixel interpolation, computation, and curve evolution , 1995, Proceedings of International Symposium on Computer Vision - ISCV.

[15]  James A. Sethian,et al.  A unified approach to noise removal, image enhancement, and shape recovery , 1996, IEEE Trans. Image Process..

[16]  Alberto Del Bimbo,et al.  Image retrieval by elastic matching of shapes and image patterns , 1996, Proceedings of the Third IEEE International Conference on Multimedia Computing and Systems.

[17]  James A. Sethian,et al.  Level set and fast marching methods in image processing and computer vision , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[18]  A. Murat Tekalp,et al.  Image query-by-example using region-based shape matching , 1996, Electronic Imaging.

[19]  Josef Kittler,et al.  Reliable Classification of Chrysanthemum Leaves through Curvature Scale Space , 1997, Scale-Space.

[20]  Jie Chen,et al.  Affine curve moment invariants for shape recognition , 1997, Pattern Recognit..

[21]  Stan Sclaroff,et al.  Deformable prototypes for encoding shape categories in image databases , 1995, Pattern Recognit..

[22]  James A. Sethian,et al.  A real-time algorithm for medical shape recovery , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[23]  Kaleem Siddiqi,et al.  Shapes, shocks and wiggles , 1999, Image Vis. Comput..

[24]  Henri H. Arsenault,et al.  Fourier-Mellin descriptor and interpolated feature space trajectories for three-dimensional object recognition , 2000 .

[25]  Georg S. Ruppert,et al.  FFT-descriptors for shape recognition of military vehicles , 2000, Defense, Security, and Sensing.

[26]  Guangyi Chen,et al.  An Orthonormal-Shell-Fourier Descriptor for Rapid Matching of Patterns in Image Database , 2001, Int. J. Pattern Recognit. Artif. Intell..

[27]  Sadegh Abbasi,et al.  Affine-similar shape retrieval: application to multiview 3-D object recognition , 2001, IEEE Trans. Image Process..

[28]  Sadegh Abbasi,et al.  Shape similarity retrieval under affine transforms , 2002, Pattern Recognit..

[29]  Guillermo Sapiro,et al.  Affine invariant scale-space , 1993, International Journal of Computer Vision.