DocumentCode
1580014
Title
Building skeletal graphs for structural feature extraction on handwriting images
Author
Xue, Hanhong ; Govindaraju, Venu
Author_Institution
CEDAR, State Univ. of New York, Buffalo, NY, USA
fYear
2001
fDate
6/23/1905 12:00:00 AM
Firstpage
96
Lastpage
100
Abstract
Presents a method of building skeletal graphs for handwriting images, aiming at extraction of high-level structural features such as loops, turns, ends, and junctions. Block adjacency graphs are used as the base representation and transformed at locations where deformation occurs to obtain satisfactory skeletal graphs. Then the identification and ordering of structural features are considered based on skeletal graphs
Keywords
directed graphs; feature extraction; handwritten character recognition; block adjacency graphs; deformation; ends; handwriting images; junctions; loops; skeletal graphs; structural feature extraction; turns; Buildings; Clustering algorithms; Feature extraction; Image analysis; Image coding; Image converters; Pattern recognition; Pixel; Skeleton; Venus;
fLanguage
English
Publisher
ieee
Conference_Titel
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location
Seattle, WA
Print_ISBN
0-7695-1263-1
Type
conf
DOI
10.1109/ICDAR.2001.953762
Filename
953762
Link To Document