End-to-End Unsupervised Document Image Blind Denoising

Removing noise from scanned pages is a vital step before their submission to the optical character recognition (OCR) system. Most available image denoising methods are supervised where the pairs of noisy/clean pages are required. However, this assumption is rarely met in real settings. Besides, ther...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-10
Main Authors: Gangeh, Mehrdad J, Plata, Marcin, Motahari, Hamid, Duffy, Nigel P
Format: Article
Language:English
Subjects:
Image quality
Machine learning
Noise
Noise reduction
Object recognition
Optical character recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Removing noise from scanned pages is a vital step before their submission to the optical character recognition (OCR) system. Most available image denoising methods are supervised where the pairs of noisy/clean pages are required. However, this assumption is rarely met in real settings. Besides, there is no single model that can remove various noise types from documents. Here, we propose a unified end-to-end unsupervised deep learning model, for the first time, that can effectively remove multiple types of noise, including salt \& pepper noise, blurred and/or faded text, as well as watermarks from documents at various levels of intensity. We demonstrate that the proposed model significantly improves the quality of scanned images and the OCR of the pages on several test datasets.
ISSN:2331-8422