DocumentCode
2431462
Title
A fully parallel thinning algorithm using a weighted template
Author
Park, Se Hyun ; Kim, Sang Kyoon ; Kim, Hang Joon
Author_Institution
Dept. of Comput. Eng., Kyungpook Nat. Univ., Taegu, South Korea
Volume
1
fYear
1996
fDate
26-29 Nov 1996
Firstpage
300
Abstract
A new fully parallel thinning algorithm using a weighted template with eight pixel supports is presented. The algorithm does not have any substeps and preserves the connectivity of an input image. Experimental results show that our algorithm has performed better, in terms of skeleton of curves, than both Zhang-Suen´s (1984) and Lu-Wang´s (1986) algorithms
Keywords
character recognition; edge detection; image recognition; parallel algorithms; connectivity; eight pixel supports; fully parallel thinning algorithm; handwritten character recognition; input image; skeleton of curves; weighted template; Algorithm design and analysis; Character recognition; Concurrent computing; Fingerprint recognition; Image processing; Parallel algorithms; Partitioning algorithms; Pixel; Shape; Skeleton;
fLanguage
English
Publisher
ieee
Conference_Titel
TENCON '96. Proceedings., 1996 IEEE TENCON. Digital Signal Processing Applications
Conference_Location
Perth, WA
Print_ISBN
0-7803-3679-8
Type
conf
DOI
10.1109/TENCON.1996.608826
Filename
608826
Link To Document