A Comparison of Some Contour Based Shape Descriptors After Applying Bezier Curve Approximation with Application to Brachiopods Classification

The goal of shape descriptors is to uniquely depict the object shape in a large database. In this paper, we present a comparative study between some of contour based shape descriptors after applying a Bezier curve approximation to the contours. Especially, we studied Curvature, Fourier descriptors, Wavelet descriptors, Radial function and Fourier of Radial function. By applying Bezier curve approximation we can reduce the number of points in the contours and gives a smooth curve. We used this technique for fossils classification, Specifically Brachiopods. The five shape descriptors are compared using the City block distance and the recognition rate.

[1]  Wageeh Boles,et al.  Recognition of 2D object contours using the wavelet transform zero-crossing representation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Faouzi Ghorbel.  Stability of invariant Fourier descriptors and its inference in the shape classification , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol. III. Conference C: Image, Speech and Signal Analysis,.

[3]  Faouzi Ghorbel,et al.  Brachiopods classification based on fusion of global and local complete and stable descriptors , 2015, 2015 IEEE/ACS 12th International Conference of Computer Systems and Applications (AICCSA).

[4]  Kimcheng Kith,et al.  The Normalized Wavelet Descriptor for Shape Retrieval , 2008, Int. J. Wavelets Multiresolution Inf. Process..

[5]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[6]  King-Sun Fu,et al.  Shape Discrimination Using Fourier Descriptors , 1977, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  James S. Crampton,et al.  Elliptic Fourier shape analysis of fossil bivalves: some practical considerations , 1995 .

[8]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

[9]  Guojun Lu,et al.  Study and evaluation of different Fourier methods for image retrieval , 2005, Image Vis. Comput..

[10]  Fernando Pereira,et al.  Spatial shape error concealment for object-based image and video coding , 2004, IEEE Transactions on Image Processing.

[11]  Luigi Cinque,et al.  Shape description using cubic polynomial Bezier curves , 1998, Pattern Recognit. Lett..

[12]  Cristina Urdiales,et al.  Non-parametric planar shape representation based on adaptive curvature functions , 2002, Pattern Recognit..

[13]  Kidiyo Kpalma,et al.  Multiscale contour description for pattern recognition , 2006, Pattern Recognit. Lett..

[14]  Describing Ammonite shape using Fourier analysis , 2004 .

[15]  Mandyam D. Srinath,et al.  Orthogonal Moment Features for Use With Parametric and Non-Parametric Classifiers , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  Farzin Mokhtarian,et al.  Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Steffen Goebbels,et al.  Fourier descriptors for broken shapes , 2013, EURASIP Journal on Advances in Signal Processing.

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

[19]  Matti Pietikäinen,et al.  An Experimental Comparison of Autoregressive and Fourier-Based Descriptors in 2D Shape Classification , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[21]  Sang Uk Lee,et al.  Recognition of 2D Object Contours Using Starting-Point-Independent Wavelet Coefficient Matching , 1998, J. Vis. Commun. Image Represent..

[22]  N. Alaa,et al.  A new method for classification of Brachiopods based on the radon transformation , 2011 .