Docentr: An end-to-end document image enhancement transformer
MA Souibgui, S Biswas, SK Jemni… - 2022 26th …, 2022 - ieeexplore.ieee.org
Document images can be affected by many degradation scenarios, which cause recognition
and processing difficulties. In this age of digitization, it is important to denoise them for …
and processing difficulties. In this age of digitization, it is important to denoise them for …
Enhance to read better: a multi-task adversarial network for handwritten document image enhancement
Handwritten document images can be highly affected by degradation for different reasons:
Paper ageing, daily-life scenarios (wrinkles, dust, etc.), bad scanning process and so on …
Paper ageing, daily-life scenarios (wrinkles, dust, etc.), bad scanning process and so on …
Text-DIAE: a self-supervised degradation invariant autoencoder for text recognition and document enhancement
In this paper, we propose a Text-Degradation Invariant Auto Encoder (Text-DIAE), a self-
supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) …
supervised model designed to tackle two tasks, text recognition (handwritten or scene-text) …
Historical text image enhancement using image scaling and generative adversarial networks
Historical documents such as newspapers, invoices, contract papers are often difficult to
read due to degraded text quality. These documents may be damaged or degraded due to a …
read due to degraded text quality. These documents may be damaged or degraded due to a …
A survey on deep learning based document image enhancement
Z Anvari, V Athitsos - arXiv preprint arXiv:2112.02719, 2021 - arxiv.org
Digitized documents such as scientific articles, tax forms, invoices, contract papers, historic
texts are widely used nowadays. These document images could be degraded or damaged …
texts are widely used nowadays. These document images could be degraded or damaged …
[HTML][HTML] ALDII: Adaptive Learning-based Document Image Inpainting to enhance the handwritten Chinese character legibility of human and machine
Abstract Document Image Inpainting (DII) has been applied to degraded documents,
including financial and historical documents, to enhance the legibility of images for:(1) …
including financial and historical documents, to enhance the legibility of images for:(1) …
Binarizing Documents by Leveraging both Space and Frequency
Abstract Document Image Binarization is a well-known problem in Document Analysis and
Computer Vision, although it is far from being solved. One of the main challenges of this task …
Computer Vision, although it is far from being solved. One of the main challenges of this task …
Npix2Cpix: A GAN-based Image-to-Image Translation Network with Retrieval-Classification Integration for Watermark Retrieval from Historical Document Images
The identification and restoration of ancient watermarks have long been a major topic in
codicology and history. Classifying historical documents based on watermarks can be …
codicology and history. Classifying historical documents based on watermarks can be …
LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach
The rapid evolution of intelligent document processing systems demands robust solutions
that adapt to diverse domains without extensive retraining. Traditional methods often falter …
that adapt to diverse domains without extensive retraining. Traditional methods often falter …
Unpaired document image denoising for OCR using BiLSTM enhanced CycleGAN
The recognition performance of optical character recognition (OCR) models can be sub-
optimal when document images suffer from various degradations. Supervised deep learning …
optimal when document images suffer from various degradations. Supervised deep learning …