Denoising of Images using Deep Convolutional Neural Networks (DCNN)

  Susheel George Joseph,  Dr. Vijay Pal Singh

We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models. We demonstrate this approach on the challenging problem of natural image denoising. Using a test set with a hundred natural images, we find that convolutional networks provide comparable and in some cases superior performance to state of the art wavelet and Markov random field (MRF) methods. Moreover, we find that a convolutional network offers similar performance in the blind denoising setting as compared to other techniques in the non-blind setting. We also show how convolutional networks are mathematically related to MRF approaches by presenting a mean field theory for an MRF specially designed for image denoising. Although these approaches are related, convolutional networks avoid computational difficulties in MRF approaches that arise from probabilistic learning and inference. This makes it possible to learn image processing architectures that have a high degree of representational power, but whose computational expense is significantly less than that associated with inference in MRF approaches with even hundreds of parameters.

Keywords- Convolutional networks, Image denoising, Deep learning networks, Convolutional architecture

Unique Identification Number - IJEDR1903143
Page Number(s) - 826-832
Pubished in - Volume 7 | Issue 3 | September 2019
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Susheel George Joseph,  Dr. Vijay Pal Singh,   "Denoising of Images using Deep Convolutional Neural Networks (DCNN)", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.7, Issue 3, pp.826-832, September 2019, Available at :http://www.ijedr.org/papers/IJEDR1903143.pdf