Connected and degraded text recognition using planar hidden Markov models

Authors:
Oscar E. Agazzi;Shyh-shiaw Kuo;Esther Levin;Roberto Pieraccini
Affiliations:
Signal Processing Research Department, AT&T Bell Laboratories, Murray Hill, NJ;Signal Processing Research Department, AT&T Bell Laboratories, Murray Hill, NJ;Speech Research Department, AT&T Bell Laboratories, Murray Hill, NJ;Speech Research Department, AT&T Bell Laboratories, Murray Hill, NJ
Venue:
ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: image and multidimensional signal processing - Volume V
Year:
1993

Citing 0
Cited 2

Machine vision for keyword spotting using pseudo 2D hidden Markov models

ICASSP'93 Proceedings of the 1993 IEEE international conference on Acoustics, speech, and signal processing: image and multidimensional signal processing - Volume V
Semantic image segmentation with a multidimensional hidden markov model

MMM'07 Proceedings of the 13th international conference on Multimedia Modeling - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present an algorithm for connected text recognition using enhanced Planar Hidden Markov Models (PHMMs). The algorithm we propose automatically segments text into characters (even if they are highly blurred and touching) as an integral part of the recognition process, thus jointly optimizing segmentation and recognition. Performance is enhanced by the use of state length models, transition probabilities among characters (bigrams), and grammars. Experiments are presented using: 1) A simulated database of over 24,000 highly degraded images of city names; 2) A database of 6,000 images rejected by a high performance commercial OCR machine with 99.5% accuracy. Measured performance on the first database is 99.65% for the most degraded images when a grammar is used, and 98.76% in the second database. Traditional OCR algorithms would fail drastically on these images.