Image Noise Reduction with Autoencoder

Authors

  • Aparna Mote  Department of Computer Engineering, Zeal College of Engineering and Research, Pune, Maharashtra, India
  • Aditya Bhamre  Department of Computer Engineering, Zeal College of Engineering and Research, Pune, Maharashtra, India
  • Atharv Waghmare  Department of Computer Engineering, Zeal College of Engineering and Research, Pune, Maharashtra, India
  • Diptesh Thakare  Department of Computer Engineering, Zeal College of Engineering and Research, Pune, Maharashtra, India
  • Tanoj Handal  Department of Computer Engineering, Zeal College of Engineering and Research, Pune, Maharashtra, India

Keywords:

Deep-Learning, Machine-Learning, Tensor Flow, Autoencoder, Convolutional Neural Network, Image Denoising, Image Compression

Abstract

Digital images play an important role in our daily lives, and they can be used for a variety of applications such as fingerprint recognition, video viewing, etc. Transmission through audio channels, faults in the memory, etc. may cause noise in the image and when it is processed afterwards it will lead to inaccurate output. Therefore, there is necessity to remove the noise before in order for the image to be processed. Here comes in the need of efficient denoising technique that helps to deal with the noisy image. Image denoising is a technique to restore or repair a damaged image back to its original quality. In line with that, we sometimes need to colour the decoloured image. Image data formatting requires a special take in neural network, called Convolutional Neural Network (CNN) or Convolutional Autoencoder. For reducing the dimensions and image noise, autoencoders are widely preferred. Therefore, by its virtue, training the model to perform denoising of the images.

References

  1. Michael Nielsen, “Neural Networks and Deep Learning”, Springer International Publishing, 2019.
  2. Debjani Bhowmick, Deepak K Gupta, Saumen Maiti, Uma Shankar, “Stacked autoencoders based machine learning for noise reduction and signal reconstruction in geophysical data”, arXiv, 2019
  3. Martin Abadi, “Tensor Flow: Learning Functions at scale”, International Conference on Functional Programming, ACM, 2016
  4. Donghoon Leea Sunghoon Choib Hee-JoungKim,” Performance Evaluation of Image denoising developed using convolutional denoising autoencoders in chest radiography”, Vol 88, pp 97-104, 2018
  5. J. Kim, S. Song and S. Yu, "Denoising auto-encoder based image enhancement for high resolution sonar image," 2017 IEEE Underwater Technology (UT), Busan, 2017
  6. Kopczyk D., Denoising Autoencoder: Part I – Introduction to Autoencoders, https://dkopczyk.quantee.co.uk/dae-part1 .
  7. Jonathan Masci, Ueli Meier, Dan Ciresen, Jurgen Schmidhuber, “Stacked Convolutional AutoEncoders for Hierarchical Feature Extraction”, International Conference on Artificial Neural Networks, 2011
  8. R. Nagy, A. Dicker and K. Meyer̺ Wegener, "NEOCR: A Configurable Dataset for Natural Image Text Recognition". In CBDAR Workshop 2011 at ICDAR 2011. pp. 53̺58, September 2011. 2019 8th European Workshop on Visual Information Processing (EUVIP)
  9. Guo, S., Yan, Z., Zhang, K., Zuo, W., & Zhang, L. Toward convolutional blind denoising of real photographs. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 1712-1722.
  10. Bharambe, Yogesh, “Assessing employability of students using data mining techniques”, (ICACCI), 2017.

Downloads

Published

2022-05-30

Issue

Section

Research Articles

How to Cite

[1]
Aparna Mote, Aditya Bhamre, Atharv Waghmare, Diptesh Thakare, Tanoj Handal, " Image Noise Reduction with Autoencoder, IInternational Journal of Scientific Research in Computer Science, Engineering and Information Technology(IJSRCSEIT), ISSN : 2456-3307, Volume 8, Issue 3, pp.492-495, May-June-2022.