Title :
Robust text-line and word segmentation for handwritten documents images
Author :
Stafylakis, Themos ; Papavassiliou, Vassilis ; Katsouros, Vassilis ; Carayannis, George
Author_Institution :
Res. & Innovation Center in Inf., Inst. for Language & Speech Process. of Athena, Athens
fDate :
March 31 2008-April 4 2008
Abstract :
This paper addresses the problem of automatic text-line and word segmentation in handwritten document images. Two novel approaches are presented, one for each task. In text-line segmentation a Viterbi algorithm is proposed while an SVM-based metric is adopted to locate words in each text-line. The overall algorithm was tested in the ICDAR2007 handwriting segmentation contest and showed highly promising results.
Keywords :
document image processing; image segmentation; maximum likelihood estimation; support vector machines; SVM-based metric; Viterbi algorithm; handwritten documents images; text-line segmentation; word segmentation; Carbon capture and storage; Clustering algorithms; Handwriting recognition; Image segmentation; Natural languages; Probability; Robustness; Speech processing; Statistics; Viterbi algorithm; Document image processing; Viterbi estimation; handwriting recognition; image segmentation; support vector machines;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2008.4518379
