Software module for automatic enhancement of digitized documents

OCR, document, quality enhancement, Generative Adversarial Networks, Convolutional Networks

Tool for text-guided textual document scan quality enhancement. The method works on lines of text that can be input through a PAGE XML or detected automatically by a built-in OCR. By using text input along with the image, the results can be correctly readable even with parts of the original text missing or severely degraded in the source image. The tool includes functionality for cropping the text lines, processing them with our provided models for either text enhancement and inpainting, and for blending the enhanced text lines back into the source document image. We currently provide models for OCR and enhancement of czech newspapers optimized for low-quality scans from micro-films. This package can be used as a standalone command line tool to process document pages in bulk. Alternatively, the package provides a python class that can be integrated in third-party software.

github.com/DCGM/pero-enhance