Historical Documents, Optical Character Recognition, OCR Error Correction, Ensemble Methods
As the digitization of historical documents, such as newspapers, becomes more common, the need of the archive patron for accurate digital text from those documents increases. Building on our earlier work, the contributions of this paper are: 1. in demonstrating the applicability of novel methods for correcting optical character recognition (OCR) on disparate data sets, including a new synthetic training set, 2. enhancing the correction algorithm with novel features, and 3. assessing the data requirements of the correction learning method. First, we correct errors using conditional random fields (CRF) trained on synthetic training data sets in order to demonstrate the applicability of the methodology to unrelated test sets. Second, we show the strength of lexical features from the training sets on two unrelated test sets, yielding a relative reduction in word error rate on the test sets of 6.52%. New features capture the recurrence of hypothesis tokens and yield an additional relative reduction in WER of 2.30%. Further, we show that only 2.0% of the full training corpus of over 500,000 feature cases is needed to achieve correction results comparable to those using the entire training corpus, effectively reducing both the complexity of the training process and the learned correction model.
Original Publication Citation
Lund, W., Ringger, E. K., & Walker, D. W. (2014) How Well Does Multiple OCR Error Correction Generalize? In Proceedings of The 20th Document Recognition and Retrieval (DRR 2014). San Francisco, Calif.
BYU ScholarsArchive Citation
Lund, William B.; Ringger, Eric K.; and Walker, Daniel D., "How Well Does Multiple OCR Error Correction Generalize?" (2014). All Faculty Publications. 1647.
Society of Photo-Optical Instrumentation Engineers
Harold B. Lee Library
Copyright 2014 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited. doi: 10.1117/12.2042502
Copyright Use Information