title: Building and Improving an OCR Classifier for Republican Chinese Newspaper Text
creator: Henke, Konstantin
description: This work presents methods and results of an initial step towards full text extraction from a Republican Chinese newspaper. My basis is a small fraction of the image corpus for which text ground truth exists. I introduce a character segmentation method which produces over 90,000 labeled images of single characters. Then I pre-train a GoogLeNet classifier as an OCR model on character images extracted from font files and randomly augmented on the fly, whereafter I fine-tune it on the previously segmented character images. I show that the pre-training step is able to increase OCR accuracy from 95.49% to 96.95% on the test set and finally, how post-processing using a masked language model corrects up to 16% of remaining errors, increasing accuracy on the test set to 97.44%.
date: 2021
type: Bachelor thesis
type: info:eu-repo/semantics/bachelorThesis
type: NonPeerReviewed
format: application/pdf
identifier: https://archiv.ub.uni-heidelberg.de/volltextserverhttps://archiv.ub.uni-heidelberg.de/volltextserver/30845/1/Bachelor_Thesis.pdf
identifier: DOI:10.11588/heidok.00030845
identifier: urn:nbn:de:bsz:16-heidok-308453
identifier:   Henke, Konstantin  (2021) Building and Improving an OCR Classifier for Republican Chinese Newspaper Text.  [Bachelor thesis]     
relation: https://archiv.ub.uni-heidelberg.de/volltextserver/30845/
rights: info:eu-repo/semantics/openAccess
rights: Please see front page of the work (Sorry, Dublin Core plugin does not recognise license id)
language: eng