mlsanityData to 14 Oct 2026

EraseNet: A Recurrent Residual Network for Supervised Document Cleaning

arXiv 2210.00708 ↗First posted 3 Oct 2022cs.CV cs.LG eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

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 shown promising results as the model is able to learn a variety of ordinary as well as unusual noises and rectify them efficiently.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 41 references that are in the map. First posted on arXiv 3 Oct 2022.

Builds on

22 of 41 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,908
  5. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  6. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,552
  7. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  8. 2022Simple Baselines for Image Restorationcited by 708
  9. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 519
  10. 2021HINet: Half Instance Normalization Network for Image Restorationcited by 237
  11. 2017Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Ratescited by 199
  12. 2019High-Quality Self-Supervised Deep Image Denoisingcited by 161
10 more
  1. 2019Deep Learning on Image Denoising: An overviewcited by 128
  2. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  3. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  4. 2022AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Networkcited by 93
  5. 2016Medical image denoising using convolutional denoising autoencoderscited by 76
  6. 2018RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentationcited by 66
  7. 2019Learned Image Downscaling for Upscaling using Content Adaptive Resamplercited by 55
  8. 2018Collapse of Deep and Narrow Neural Netscited by 37
  9. 2018Deep Learning for Image Denoising: A Surveycited by 11
  10. 2021End-to-End Unsupervised Document Image Blind Denoisingcited by 7

Built on by

Not cited yet.