Word-Based Adaptive OCR for Historical Books Export

@inproceedings{citeulike:5470151, abstract = {The aim of this work is to propose a new approach to the recognition of historical texts by providing an adaptive mechanism that automatically tunes itself to a specific book. The system is based on clustering together all the similar words in a book/text and simultaneously handling entire class. The paper describes the architecture of such a system and new algorithms that have been developed for robust word image comparison (including registration, optical flow based distortion compensation, and adaptive binarization). Results for a large dataset are presented as well. Over 23\% recognition improvement is demonstrated.}, author = {Kluzner, Vladimir and Tzadok, Asaf and Antonacopoulos, Apostolos and Shimony, Yuval and Walach, Eugene}, booktitle = {10th International Conference on Document Analysis and Recognition}, citeulike-article-id = {5470151}, citeulike-linkout-0 = {http://www.cvc.uab.es/icdar2009/papers/3725a501.pdf}, keywords = {books, digital\_libraries--historical, document-recognition--historical, ocr}, posted-at = {2009-08-18 20:56:01}, priority = {3}, title = {Word-Based Adaptive OCR for Historical Books}, url = {http://www.cvc.uab.es/icdar2009/papers/3725a501.pdf}, year = {2009} }

TY - CONF ID - citeulike:5470151 L3 - citeulike-article-id:5470151 N2 - The aim of this work is to propose a new approach to the recognition of historical texts by providing an adaptive mechanism that automatically tunes itself to a specific book. The system is based on clustering together all the similar words in a book/text and simultaneously handling entire class. The paper describes the architecture of such a system and new algorithms that have been developed for robust word image comparison (including registration, optical flow based distortion compensation, and adaptive binarization). Results for a large dataset are presented as well. Over 23% recognition improvement is demonstrated. TI - Word-Based Adaptive OCR for Historical Books T2 - 10th International Conference on Document Analysis and Recognition KW - books KW - digital_libraries--historical KW - document-recognition--historical KW - ocr AU - Kluzner, Vladimir AU - Tzadok, Asaf AU - Antonacopoulos, Apostolos AU - Shimony, Yuval AU - Walach, Eugene PY - 2009/// UR - http://www.cvc.uab.es/icdar2009/papers/3725a501.pdf ER -