Title :
Handwritten character segmentation using transformation-based learning
Author :
Kavallieratou, E. ; Stamatatos, E. ; Fakotakis, N. ; Kokkinakis, G.
Author_Institution :
Dept. of Electr. & Comput. Eng., Patras Univ., Greece
Abstract :
Presents a character segmentation algorithm for unconstrained cursive handwritten text. The transformation-based learning method and a simplified variation of it are used in order to extract automatically rules that detect the segment boundaries. Comparative experimental results are given for a collection of multiwriter handwritten words. The achieved accuracy in detecting segment boundaries exceeds 82%. Moreover limited training data can provide very satisfactory results
Keywords :
handwritten character recognition; image segmentation; learning (artificial intelligence); optical character recognition; handwritten character segmentation; multiwriter handwritten words; segment boundaries; transformation-based learning; unconstrained cursive handwritten text; Character recognition; Data mining; Handwriting recognition; Histograms; Image segmentation; Learning systems; Optical character recognition software; Text recognition; Training data; Vocabulary;
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
Print_ISBN :
0-7695-0750-6
DOI :
10.1109/ICPR.2000.906155
