Improving optical character recognition through efficient multiple system alignment
Proceedings of the 9th ACM/IEEE-CS joint conference on Digital libraries
Analysis of whole-book recognition
DAS '10 Proceedings of the 9th IAPR International Workshop on Document Analysis Systems
Improving handwriting recognition by the use of semantic information
DAS '10 Proceedings of the 9th IAPR International Workshop on Document Analysis Systems
From handwriting recognition to ontologie-based information extraction of handwritten notes
KES'11 Proceedings of the 15th international conference on Knowledge-based and intelligent information and engineering systems - Volume Part IV
Bridging the gap between handwriting recognition and knowledge management
Pattern Recognition Letters
Hi-index | 0.00 |
We describe experimental results for unsupervised recognition of the textual contents of book-images using fully automatic mutual-entropy-based model adaptation. Each experiment starts with approximate {\it iconic} and{\it linguistic} models---derived from (generally errorful) OCR results and (generally incomplete) dictionaries---and then runs a fully automatic adaptation algorithm which, guided entirely by evidence internal to the test set, attempts to correct the models for improved accuracy. The iconic model describes image formation and determines the behavior of a character-image classifier. The linguistic model describes word-occurrence probabilities. Our adaptation algorithm detects disagreements between the models by analyzing mutual entropy between (1) the {\em a posteriori} probability distribution of character classes (the recognition results from image classification alone), and (2) the {\em a posteriori} probability distribution of word classes (the recognition results from image classification combined with linguistic constraints). Disagreements identify candidates for automatic model corrections. We report experiments on 40 textlines in which word error rates fall monotonicaly with passage lengths. We also report experiments on an enhanced algorithm which can cope with character-segmentation errors (a single split, or a single merge, per word). In order to scale up experiments, soon, to whole book images, we have revised data structures and implemented speed enhancements. For this algorithm, we report results on three increasingly long passage lengths: (a) one full page, (b) five pages, and (b) ten pages. We observe that error rates on long words fall monotonically with passage lengths.