Title :
Generation of synthetic training data for an HMM-based handwriting recognition system
Author :
Varga, Tamás ; Bunke, Horst
Author_Institution :
Inst. fur Informatik und angewandte Math., Univ. Bern, Switzerland
Abstract :
A perturbation model for generating synthetic text lines from existing cursively handwritten lines of text produced by human writers is presented. Our purpose is to improve the performance of an HMM-based off-line cursive handwriting recognition system by providing it with additional synthetic training data. Two kinds of perturbations are applied, geometrical transformations and thinning/thickening operations. The proposed perturbation model is evaluated under different experimental conditions.
Keywords :
handwriting recognition; hidden Markov models; image thinning; HMM-based off-line cursive handwriting recognition system; cursively handwritten lines; geometrical transformations; pattern recognition; perturbation model; synthetic text line generation; synthetic training data generation; thickening operation; thinning operation; Character recognition; Classification algorithms; Handwriting recognition; Hidden Markov models; Humans; Image recognition; Nonlinear distortion; Pattern recognition; Text recognition; Training data;
Conference_Titel :
Document Analysis and Recognition, 2003. Proceedings. Seventh International Conference on
Print_ISBN :
0-7695-1960-1
DOI :
10.1109/ICDAR.2003.1227736
