TY - GEN
T1 - Improving OCR for an under-resourced script using unsupervised word-spotting
AU - Silberpfennig, Adi
AU - Wolf, Lior
AU - Dershowitz, Nachum
AU - Bhagesh, Seraogi
AU - Chaudhuri, Bidyut B.
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/11/20
Y1 - 2015/11/20
N2 - Optical character recognition (OCR) quality, especially for under-resourced scripts like Bangla, as well as for documents printed in old typefaces, is a major concern. An efficient and effective pipeline for OCR betterment is proposed here. The method is unsupervised. It employs a baseline OCR engine as a black box plus a dataset of unlabeled document images. That engine is applied to the images, followed by a visual encoding designed to support efficient word spotting. Given a new document to be analyzed, the black-box recognition engine is first applied. Then, for each result, word spotting is carried out within the dataset. The unreliable OCR outputs of the retrieved word spotting results are then considered. The word that is the centroid of the set of OCR words, measured by edit distance, is deemed a candidate reading.
AB - Optical character recognition (OCR) quality, especially for under-resourced scripts like Bangla, as well as for documents printed in old typefaces, is a major concern. An efficient and effective pipeline for OCR betterment is proposed here. The method is unsupervised. It employs a baseline OCR engine as a black box plus a dataset of unlabeled document images. That engine is applied to the images, followed by a visual encoding designed to support efficient word spotting. Given a new document to be analyzed, the black-box recognition engine is first applied. Then, for each result, word spotting is carried out within the dataset. The unreliable OCR outputs of the retrieved word spotting results are then considered. The word that is the centroid of the set of OCR words, measured by edit distance, is deemed a candidate reading.
UR - http://www.scopus.com/inward/record.url?scp=84962505792&partnerID=8YFLogxK
U2 - 10.1109/ICDAR.2015.7333853
DO - 10.1109/ICDAR.2015.7333853
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:84962505792
T3 - Proceedings of the International Conference on Document Analysis and Recognition, ICDAR
SP - 706
EP - 710
BT - 13th IAPR International Conference on Document Analysis and Recognition, ICDAR 2015 - Conference Proceedings
PB - IEEE Computer Society
T2 - 13th International Conference on Document Analysis and Recognition, ICDAR 2015
Y2 - 23 August 2015 through 26 August 2015
ER -