Thinning is a very important preprocessing step for the analysis and recognition of different types of images. Thinning is the process of minimizing the width of a line, in an image, from many pixels wide to just one pixel (Lam et al., 1992) [3]. Thus Correct and Reliable thinning of character patterns are essential to a variety of applications in the field of document analysis and recognition systems like pattern recognition; finger print recognition etc. Iterative parallel thinning algorithms which generate one-pixel-wide skeletons generally have difficulty in preserving the connectivity of an image. In present paper, four iterative parallel thinning algorithms namely the Fast Parallel Thinning Algorithm (FPTA), Guo & Hall’s parallel thinning Algorithm (GHPTA), Robust Parallel Thinning Algorithm for binary images (RPTA), and Preprocessing Thinning Algorithms for Handwritten Character Recognition (PPTA) have been implemented in C Language and evaluated. A comparison among these was made on the basis of following factors: quality of skeleton, convergence to unit width and data reduction rate. This study may help to compare or to select the best algorithm. The comparative results are included to support our findings.
[1]
P. K. Rhee,et al.
An efficient fully parallel thinning algorithm
,
1997,
Proceedings of the Fourth International Conference on Document Analysis and Recognition.
[2]
Zicheng Guo,et al.
Parallel thinning with two-subiteration algorithms
,
1989,
Commun. ACM.
[3]
Amitava Datta,et al.
A robust parallel thinning algorithm for binary images
,
1994,
Pattern Recognit..
[4]
Ching Y. Suen,et al.
Thinning Methodologies - A Comprehensive Survey
,
1992,
IEEE Trans. Pattern Anal. Mach. Intell..
[5]
Waleed H. Abdulla,et al.
A preprocessing algorithm for hand-written character recognition
,
1988,
Pattern Recognit. Lett..
[6]
Ching Y. Suen,et al.
A fast parallel algorithm for thinning digital patterns
,
1984,
CACM.
[7]
Anil K. Jain.
Fundamentals of Digital Image Processing
,
2018,
Control of Color Imaging Systems.
[8]
Lawrence O'Gorman,et al.
Document Image Analysis
,
1996
.