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
fDate :
6/23/1905 12:00:00 AM
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;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953762
