A simple iterative thinning algorithm for text and shape binary images

Thinning or skeletonization is become a curial step in many document image analysis and recognition application as a pre-process stage. These applications such as optical character recognition OCR, optical script recognition OSR, and optical font recognition OFR widely adopt many exist methods, some thinning challenging defect the performance of these applications. However, further enhancement for thinning technique is indeed. A simple iterative thinning algorithm is proposed for binary images domain. Thereafter, a benchmark dataset is designed for thinning algorithm evaluation is used. Finally, The evaluation experiments result are compared with some other major thinning methods to proof the proposed method efficiency. The proposed algorithm visual experiments shows outperform for many thinning challenges such as one pixel width, topology preserving, rotation tolerance, and tail occurrences.

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

[2]  Siti Norul Huda Sheikh Abdullah,et al.  Off-line Arabic Character-Based Writer Identification – a Survey , 2011 .

[3]  P. Ahmed,et al.  A neural network based dedicated thinning method , 1995, Pattern Recognit. Lett..

[4]  Lawrence O'Gorman,et al.  Document Image Analysis , 1996 .

[5]  Gaurav Harit,et al.  An improved contour-based thinning method for character images , 2011, Pattern Recognit. Lett..

[6]  Mohamed A. Ali.  AN EFFICIENT THINNING ALGORITHM FOR ARABIC OCR SYSTEMS , 2012 .

[7]  Wahyu Kusuma,et al.  Journal of Theoretical and Applied Information Technology , 2012 .

[8]  Ching Y. Suen,et al.  Thinning Methodologies - A Comprehensive Survey , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

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

[10]  Simone Marinai,et al.  Introduction to Document Analysis and Recognition , 2008, Machine Learning in Document Analysis and Recognition.

[11]  Patrick Shen-Pei Wang,et al.  A parallel thinning algorithm with two-subiteration that generates one-pixel-wide skeletons , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[12]  Wei Chen,et al.  Improved Zhang-Suen thinning algorithm in binary line drawing applications , 2012, 2012 International Conference on Systems and Informatics (ICSAI2012).

[13]  Ronald H. Perrott,et al.  An improved parallel thinning algorithm , 1987, CACM.

[14]  Kenji Shimada,et al.  Skeleton-based computational method for the generation of a 3D finite element mesh sizing function , 2004, Engineering with Computers.

[15]  Yuan Yan Tang,et al.  Wavelet-Based Approach to Character Skeleton , 2007, IEEE Transactions on Image Processing.

[16]  Yung-Sheng Chen,et al.  Systematic approach for designing 2-subcycle and pseudo 1-subcycle parallel thinning algorithms , 1989, Pattern Recognit..

[17]  Rabab Kreidieh Ward,et al.  A Rotation Invariant Rule-Based Thinning Algorithm for Character Recognition , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Khairuddin Omar,et al.  A comparative study of Voronoi algorithm construction in thinning , 2011, Proceedings of the 2011 International Conference on Electrical Engineering and Informatics.

[19]  Khairuddin Omar,et al.  A Novel Baseline Detection Method of Handwritten Arabic-Script Documents Based on Sub-Words , 2013, M-CAIT.

[20]  Venu Govindaraju,et al.  Document image analysis: A primer , 2002 .

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

[22]  Theodosios Pavlidis,et al.  An asynchronous thinning algorithm , 1982, Comput. Graph. Image Process..

[23]  Peter Rockett.  An improved rotation-invariant thinning algorithm , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Dinesh U Acharya,et al.  Script Identification from Multilingual Indian Documents using Structural Features , 2010 .

[25]  Khairuddin Omar,et al.  An adaptive local binarization method for document images based on a novel thresholding method and dynamic windows , 2011, Pattern Recognit. Lett..

[26]  Kálmán Palágyi,et al.  Topology preserving parallel thinning algorithms , 2011, Int. J. Imaging Syst. Technol..

[27]  Fei Xie,et al.  Human body and posture recognition system based on an improved thinning algorithm , 2011 .

[28]  Zicheng Guo,et al.  Fast fully parallel thinning algorithms , 1991, CVGIP Image Underst..