Title :
An enhanced thinning algorithm using parallel processing
Author :
Kwon, Jun-Sik ; Gi, Jun-Woong ; Kang, Eung-Kwan
Author_Institution :
Dept. of Electr. Eng, Se-Myung Univ., Chechon, South Korea
fDate :
6/23/1905 12:00:00 AM
Abstract :
A thinning algorithm is a very important factor in recognizing the characters, figures and drawings. Until comparatively lately, various methods have been proposed for the thinning algorithm. We ascertain the point at issue of ZS, LW and WHF algorithms that are parallel thinning algorithms. The parallel thinning algorithm means that the first processing does not have to influence the second processing. the ZS algorithm has a problem that loses pixels in slanting lines and the LW algorithm does not have one pixel width in slanting lines. We propose an enhanced parallel thinning algorithm that connects the pixels to each other and preserves the end point
Keywords :
character recognition; image recognition; image thinning; parallel algorithms; LW algorithm; WHF algorithm; ZS algorithm; character recognition; drawing recognition; enhanced thinning algorithm; figure recognition; parallel processing; slanting lines; Character recognition; Image recognition; Parallel processing;
Conference_Titel :
Image Processing, 2001. Proceedings. 2001 International Conference on
Conference_Location :
Thessaloniki
Print_ISBN :
0-7803-6725-1
DOI :
10.1109/ICIP.2001.958228