An Insight into the Entropy and Redundancy of the English Dictionary
IEEE Transactions on Pattern Analysis and Machine Intelligence
Prototype Extraction and Adaptive OCR
IEEE Transactions on Pattern Analysis and Machine Intelligence
On-Line Handwriting Recognition Based on Bigram Co-Occurrences
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Visual inter-word relations and their use in OCR postprocessing
ICDAR '95 Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1
Word Discrimination Based on Bigram Co-Occurrences
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Solving multiclass learning problems via error-correcting output codes
Journal of Artificial Intelligence Research
Comparison of Feature Reduction Methods in the Text Recognition Task
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Application of bidirectional probabilistic character language model in handwritten words recognition
IDEAL'06 Proceedings of the 7th international conference on Intelligent Data Engineering and Automated Learning
| Hi-index | 0.00 |
We propose further improvement of a handwritingrecognition method that avoids segmentation while ableto recognize words that were never seen before inhandwritten form. This method is based on the fact thatfew pairs of English words share exactly the same set ofletter bigrams and even fewer share longer n-grams. Thelexical n-gram matches between every word in a lexiconand a set of reference words can be precomputed. Aposition-based match function then detects the matchesbetween the handwritten signal of a query word and eachreference word. We show that with a reasonable set ofreference words, the recognition of lexicon words exceeds90%.