![]() ![]() Finally, we perform post-correction on the new OCR results and perform error analysis. ![]() Furthermore, we revisit the effect of confidence voting on the OCR results with different model combinations. First, we find an optimal DNN for our data and, with additional training data, successfully train high-quality mixed-language models. In this paper, we explore the training of a variety of OCR models with deep neural networks (DNN). The difficulty lies in the fact that the corpus is printed in the two main languages of Finland (Finnish and Swedish) and in two font families (Blackletter and Antiqua). There have been earlier attempts to train high-quality OCR models with open-source software, like Ocropy ( ) and Tesseract ( ), but so far, none of the methods have managed to successfully train a mixed model that recognizes all of the data in the corpus, which would be essential for an efficient re-OCRing of the corpus. ![]() The estimated character error rate (CER) of the corpus, achieved with commercial software, is between 8 and 13%. The optical character recognition (OCR) quality of the historical part of the Finnish newspaper and journal corpus is rather low for reliable search and scientific research on the OCRed data.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |