Filtering Gaussian noise in MNIST handwritten digits images using a convolutional autoencoder

  • Maria Alena A. Edora National Institute of Physics, University of the Philippines Diliman
  • Francis N. C. Paraan National Institute of Physics, University of the Philippines Diliman

Abstract

A convolutional autoencoder was used to filter Gaussian noise that was added to images in the MNIST handwritten digits dataset. The autoencoder is composed of four convolutional layers: two layers each for encoding the input image and decoding the compressed image. The effectiveness of the autoencoder filter at denoising was assessed using Linfoot's image quality criteria of fidelity, structural content, and correlation quality. The results show that the autoencoder was able to successfully filter noise from images up to a threshold noise factor.

Published
2020-08-28
How to Cite
[1]
M. A. Edora and F. Paraan. Filtering Gaussian noise in MNIST handwritten digits images using a convolutional autoencoder, Proceedings of the Samahang Pisika ng Pilipinas 38, SPP-2020-2A-02 (2020). URL: https://paperview.spp-online.org/proceedings/article/view/SPP-2020-2A-02.
Section
2A Complex Systems and Data Analytics (Short Presentations)