DocumentCode
2220843
Title
Continuous approach to segmentation of handwritten text
Author
Mestetskii, L.M. ; Reyer, I.A. ; Sederberg, T.W.
Author_Institution
Tver State Univ., Russia
fYear
2002
fDate
2002
Firstpage
440
Lastpage
445
Abstract
A new approach to the segmentation of handwritten text is presented that is based on approximating a binary raster image with a set of polygons and building a continuous skeleton of those polygons. Polygons and skeletons are then used in extraction of lines, removing of spots and artifacts, extraction of words from lines and extraction of strokes from words.
Keywords
computational geometry; feature extraction; handwritten character recognition; artifacts; binary raster image; continuous approach; continuous skeleton; handwritten text segmentation; lines extraction; polygons; strokes extraction; Buildings; Handwriting recognition; Image analysis; Image segmentation; Joints; Mathematical model; Mathematics; Pixel; Skeleton; Topology;
fLanguage
English
Publisher
ieee
Conference_Titel
Frontiers in Handwriting Recognition, 2002. Proceedings. Eighth International Workshop on
Print_ISBN
0-7695-1692-0
Type
conf
DOI
10.1109/IWFHR.2002.1030950
Filename
1030950
Link To Document