An Omnifont Open-Vocabulary OCR System for English and Arabic
IEEE Transactions on Pattern Analysis and Machine Intelligence
Top-Down Likelihood Word Image Generation Model for Holistic Word Recognition
DAS '02 Proceedings of the 5th International Workshop on Document Analysis Systems V
Recognition of off-line printed Arabic text using Hidden Markov Models
Signal Processing
WAV'09 Proceedings of the 3rd WSEAS international symposium on Wavelets theory and applications in applied mathematics, signal processing & modern science
The use of radon transform in handwritten Arabic (Indian) numerals recognition
WSEAS Transactions on Computers
Recognition of Arabic (Indian) bank check digits using log-gabor filters
Applied Intelligence
Offline arabic handwritten text recognition: A Survey
ACM Computing Surveys (CSUR)
HMM-based script identification for OCR
Proceedings of the 4th International Workshop on Multilingual OCR
| Hi-index | 0.00 |
on We present a set of techniques for omnifont, unlimited-vocabulary OCR, within the context of a system based on Hidden Markov Models (HMM). First, we address the issue of how to perform OCR on omnifont and multi-style data, such as plain and italic, without the need to have a separate model for each style. The amount of training data from each style, which is used to train a single model, becomes an important issue in the face of the conditional independence assumption inherent in the use of HMMs. We demonstrate mathematically and empirically how to allocate training data among the different styles to alleviate this problem. Second, we show how to use a word-based HMM system to perform character recognition with unlimited vocabulary. The method includes the use of a trigram language model on character sequences. Using all these techniques, we have achieved character error rates of 1.1% on data from the University of Washington English Document Image Database and 3.3% on data from the DARPA Arabic OCR Corpus.