DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement

Abstract

Documents often exhibit various forms of degradation, which make it hard to be read and substantially deteriorate the performance of an OCR system. In this paper, we propose an effective end-to-end framework named Document Enhancement Generative Adversarial Networks (DE-GAN) that uses the conditional GANs (cGANs) to restore severely degraded document images. To the best of our knowledge, this practice has not been studied within the context of generative adversarial deep networks. We demonstrate that, in different tasks (document clean up, binarization, deblurring and watermark removal), DE-GAN can produce an enhanced version of the degraded document with a high quality. In addition, our approach provides consistent improvements compared to state-of-the-art methods over the widely used DIBCO 2013, DIBCO 2017 and H-DIBCO 2018 datasets, proving its ability to restore a degraded document image to its ideal condition. The obtained results on a wide variety of degradation reveal the flexibility of the proposed model to be exploited in other document enhancement problems.

Accepted in IEEE TPAMI

References in corpus (5)

• Auto-Encoding Variational Bayes
• Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections
• Semantic Segmentation using Adversarial Networks
• A selectional auto-encoder approach for document image binarization
• Language Independent Single Document Image Super-Resolution using CNN for improved recognition

Cited by in corpus (8)

• Enhance to Read Better: A Multi-Task Adversarial Network for Handwritten Document Image Enhancement
• Digitizing Historical Balance Sheet Data: A Practitioner's Guide
• Three-stage binarization of color document images based on discrete wavelet transform and generative adversarial networks
• Systematic Literature Review of Machine Learning Models and Applications for Text Recognition
• Npix2Cpix: A GAN-Based Image-to-Image Translation Network With Retrieval- Classification Integration for Watermark Retrieval From Historical Document Images
• A Fair Evaluation of Various Deep Learning-Based Document Image Binarization Approaches
• FP-THD: Full page transcription of historical documents
• SauvolaNet: Learning Adaptive Sauvola Network for Degraded Document Binarization