EraseNet: A Recurrent Residual Network for Supervised Document Cleaning
Yashowardhan Shinde, Kishore Kulkarni, Sachin Kuberkar

TL;DR
This paper presents EraseNet, a supervised recurrent residual network designed to effectively clean and restore degraded scanned documents, thereby enhancing OCR accuracy through a novel auto-encoder architecture.
Contribution
The paper introduces a new fully convolutional auto-encoder architecture called EraseNet for supervised document cleaning, capable of handling various types of document degradation.
Findings
Model effectively learns to remove diverse noise types.
Significant improvement in OCR performance after cleaning.
Promising results on real-world degraded documents.
Abstract
Document denoising is considered one of the most challenging tasks in computer vision. There exist millions of documents that are still to be digitized, but problems like document degradation due to natural and man-made factors make this task very difficult. This paper introduces a supervised approach for cleaning dirty documents using a new fully convolutional auto-encoder architecture. This paper focuses on restoring documents with discrepancies like deformities caused due to aging of a document, creases left on the pages that were xeroxed, random black patches, lightly visible text, etc., and also improving the quality of the image for better optical character recognition system (OCR) performance. Removing noise from scanned documents is a very important step before the documents as this noise can severely affect the performance of an OCR system. The experiments in this paper have…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHandwritten Text Recognition Techniques · Industrial Vision Systems and Defect Detection · Digital Media Forensic Detection
