@inproceedings{dbef993760b74fe2ac5c345594180c26,
title = "OCR Error Correction Using Character Correction and Feature-Based Word Classification",
abstract = "This paper explores the use of a learned classifier for post-OCR text correction. Experiments with the Arabic language show that this approach, which integrates a weighted confusion matrix and a shallow language model, improves the vast majority of segmentation and recognition errors, the most frequent types of error on our dataset.",
keywords = "Classifier, OCR, information retrieval, spelling correction",
author = "Ido Kissos and Nachum Dershowitz",
note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 12th IAPR International Workshop on Document Analysis Systems, DAS 2016 ; Conference date: 11-04-2016 Through 14-04-2016",
year = "2016",
month = jun,
day = "10",
doi = "10.1109/DAS.2016.44",
language = "אנגלית",
series = "Proceedings - 12th IAPR International Workshop on Document Analysis Systems, DAS 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "198--203",
booktitle = "Proceedings - 12th IAPR International Workshop on Document Analysis Systems, DAS 2016",
address = "ארצות הברית",
}