Paper
30 March 1995 Word recognition using a lexicon constrained by first/last character decisions
Sheila X. Zhao, Sargur N. Srihari
Author Affiliations +
Proceedings Volume 2422, Document Recognition II; (1995) https://doi.org/10.1117/12.205812
Event: IS&T/SPIE's Symposium on Electronic Imaging: Science and Technology, 1995, San Jose, CA, United States
Abstract
In lexicon based recognition of machine-printed word images, the size of the lexicon can be quite extensive. The recognition performance is closely related to the size of the lexicon. Recognition performance drops quickly when lexicon size increases. Here, we present an algorithm to improve the word recognition performance by reducing the size of the given lexicon. The algorithm utilizes the information provided by the first and last characters of a word to reduce the size of the given lexicon. Given a word image and a lexicon that contains the word in the image, the first and last characters are segmented and then recognized by a character classifier. The possible candidates based on the results given by the classifier are selected, which give us the sub-lexicon. Then a word shape analysis algorithm is applied to produce the final ranking of the given lexicon. The algorithm was tested on a set of machine- printed gray-scale word images which includes a wide range of print types and qualities.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Sheila X. Zhao and Sargur N. Srihari "Word recognition using a lexicon constrained by first/last character decisions", Proc. SPIE 2422, Document Recognition II, (30 March 1995); https://doi.org/10.1117/12.205812
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Image segmentation

Detection and tracking algorithms

Image processing algorithms and systems

Image quality

Visualization

Image classification

Information visualization

RELATED CONTENT

Image segmentation evaluation for very-large datasets
Proceedings of SPIE (March 24 2016)
Unified approach toward text recognition
Proceedings of SPIE (March 07 1996)
Word recognition using ideal word patterns
Proceedings of SPIE (March 23 1994)
Font identification using visual global context
Proceedings of SPIE (March 23 1994)

Back to Top