Improving OCR Accuracy on Early Printed Books by utilizing Cross Fold Training and Voting
This addresses OCR accuracy issues for historical document digitization, representing a strong incremental improvement.
The paper tackles the problem of high character error rates in OCR text from early printed books by introducing a method combining cross-fold training and confidence-based voting, achieving error reductions of up to 50% or more in experiments on seven books.
In this paper we introduce a method that significantly reduces the character error rates for OCR text obtained from OCRopus models trained on early printed books. The method uses a combination of cross fold training and confidence based voting. After allocating the available ground truth in different subsets several training processes are performed, each resulting in a specific OCR model. The OCR text generated by these models then gets voted to determine the final output by taking the recognized characters, their alternatives, and the confidence values assigned to each character into consideration. Experiments on seven early printed books show that the proposed method outperforms the standard approach considerably by reducing the amount of errors by up to 50% and more.