A novel stroke extraction method for Chinese characters using Gabor filters

A robust stroke extraction method for Chinese characters is essential to off-line character recognition systems, which depend on stroke structure analysis to function. This study presents a novel stroke extraction method based on a directional filtering technique for extracting reliable and undistorted stroke segments. First, a set of Gabor filters is used to break down an image of a character into different directional features. Next, a new iterative thresholding technique that minimizes the reconstruction error is proposed to recover stroke shape. Finally, a refinement process based on measuring the degree of stroke overlap is used to remove redundant stroke pieces. Experimental results show that the proposed method cannot only provide immunity against the junction-distortion and spurious-branch problems associated with a thinning-based process, but is also insensitive to shape deformation and noise.

[1]  Linda G. Shapiro,et al.  Computer and Robot Vision , 1991 .

[2]  H. Joel Trussell,et al.  Comments on "Picture Thresholding Using an Iterative Selection Method" , 1979, IEEE Trans. Syst. Man Cybern..

[3]  Michael W. Carter,et al.  The indefinite zero-one quadratic problem , 1984, Discret. Appl. Math..

[4]  Chang-Fuu Chen,et al.  Stroke extraction for chinese characters using a trend-followed transcribing technique , 1996, Pattern Recognit..

[5]  Rafael C. González,et al.  Local Determination of a Moving Contrast Edge , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Kuo-Chin Fan,et al.  A run-length coding based approach to stroke extraction of Chinese characters , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[7]  Jim R. Parker,et al.  Algorithms for image processing and computer vision , 1996 .

[8]  Oscar Nestares,et al.  Efficient spatial-domain implementation of a multiscale image representation based on Gabor functions , 1998, J. Electronic Imaging.

[9]  T. W. Ridler,et al.  Picture thresholding using an iterative selection method. , 1978 .

[10]  Chungnan Lee,et al.  A Chinese-character-stroke-extraction algorithm based on contour information , 1998, Pattern Recognit..

[11]  Richard Buse,et al.  Using gabor filters to measure the physical parameters of lines , 1996, Pattern Recognit..

[12]  Yung-Sheng Chen.  Segmentation and association among lines and junctions for a line image , 1994, Pattern Recognit..

[13]  Kuo-Chin Fan,et al.  A run-length-coding-based approach to stroke extraction of Chinese characters , 2000, Pattern Recognit..

[14]  Din-Chang Tseng,et al.  A novel stroke-based feature extraction for handwritten Chinese character recognition , 1999, Pattern Recognit..

[15]  Theo Pavlidis,et al.  A vectorizer and feature extractor for document recognition , 1986 .

[16]  Kuo-Chin Fan,et al.  Recognition of handwritten Chinese characters by modified relaxation methods , 1994, Image Vis. Comput..

[17]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[18]  Ching Y. Suen,et al.  Identification of Fork Points on the Skeletons of Handwritten Chinese Characters , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Ching Y. Suen,et al.  A fast parallel algorithm for thinning digital patterns , 1984, CACM.