Piecewise linear skeletonization using principal curves

We propose an algorithm to find piecewise linear skeletons of handwritten characters by using principal curves. The development of the method was inspired by the apparent similarity between the definitions of principal curves (smooth curves which pass through the "middle" of a cloud of points) and the medial axis (smooth curves that go equidistantly from the contours of a character image). The algorithm is an extension of the polygonal line algorithm, originally designed to find principal curves of data sets, to compute the principal graph of a data set. Test results indicate that the proposed algorithm substantially improves the pixelwise skeleton obtained by traditional thinning methods.

[1]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[2]  Michael E. Tipping,et al.  Probabilistic Principal Component Analysis , 1999 .

[3]  Nabil Jean Naccache,et al.  SPTA: A proposed algorithm for thinning binary patterns , 1984, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  Sam T. Roweis,et al.  EM Algorithms for PCA and SPCA , 1997, NIPS.

[5]  Roger J. Green,et al.  Skeletonization of Arabic characters using clustering based skeletonization algorithm (CBSA) , 1991, Pattern Recognit..

[6]  Amitava Datta,et al.  Skeletons from dot patterns: A neural network approach , 1997, Pattern Recognit. Lett..

[7]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[8]  Stephen P. Luttrell,et al.  Derivation of a class of training algorithms , 1990, IEEE Trans. Neural Networks.

[9]  T. Pavlidis.  A thinning algorithm for discrete binary images , 1980 .

[10]  A. Raftery,et al.  Ice Floe Identification in Satellite Images Using Mathematical Morphology and Clustering about Principal Curves , 1992 .

[11]  Teuvo Kohonen,et al.  The self-organizing map , 1990, Neurocomputing.

[12]  Ching Y. Suen,et al.  A Systematic Evaluation of Skeletonization Algorithms , 1993, Int. J. Pattern Recognit. Artif. Intell..

[13]  Song-Chun Zhu,et al.  Stochastic Jump-Diffusion Process for Computing Medial Axes in Markov Random Fields , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  B. Kégl,et al.  Principal curves: learning, design, and applications , 2000 .

[15]  R. A. Kirsch,et al.  Experiments in processing pictorial information with a digital computer , 1899, IRE-ACM-AIEE '57 (Eastern).

[16]  Ching Y. Suen,et al.  Veinerization: A New Shape Description for Flexible Skeletonization , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[17]  T. Hastie.  Principal Curves and Surfaces , 1984 .

[18]  Adam Krzyzak,et al.  Learning and Design of Principal Curves , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  HARRY BLUM,et al.  Shape description using weighted symmetric axis features , 1978, Pattern Recognit..

[20]  Godfried T. Toussaint,et al.  On Approximating Polygonal Curves in Two and Three Dimensions , 1994, CVGIP Graph. Model. Image Process..

[21]  Nikolaos Papanikolopoulos,et al.  Self-organizing maps for the skeletonization of sparse shapes , 2000, IEEE Trans. Neural Networks Learn. Syst..

[22]  James C. Bezdek,et al.  Optimal Fuzzy Partitions: A Heuristic for Estimating the Parameters in a Mixture of Normal Distributions , 1975, IEEE Transactions on Computers.

[23]  G. P. Dinneen.  Programming pattern recognition , 1955, AFIPS '55 (Western).