Tampere University of Technology

TUTCRIS Research Portal

Deep Convolutional Autoencoder for Estimation of Nonstationary Noise in Images

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication2019 8th European Workshop on Visual Information Processing (EUVIP)
PublisherIEEE
Pages238-243
Number of pages6
ISBN (Electronic)978-1-7281-4496-2
ISBN (Print)978-1-7281-4497-9
DOIs
Publication statusPublished - Oct 2019
Publication typeA4 Article in a conference publication
EventEuropean Workshop on Visual Information Processing -
Duration: 1 Jan 1900 → …

Publication series

NameEuropean Workshop on Visual Information Processing
ISSN (Print)2164-974X
ISSN (Electronic)2471-8963

Conference

ConferenceEuropean Workshop on Visual Information Processing
Period1/01/00 → …

Abstract

A precise estimation of noise parameters is very important in many image processing applications, such as denoising, deblurring, compression, etc. This problem is well studied for the case of stationary noise in images, and much less studied for the case of nonstationary noise. In this paper, we develop an efficient method of nonstationary noise variance estimation in image regions, based on specially designed deep convolutional autoencoder (DCAE) with a small dimensionality reduction. Training of the proposed DCAE is carried out for a large set of image blocks, including fragments of noise free textures, faces and texts. In the numerical analysis, we compare the proposed method and method of blind estimation of nonstationary noise, based on block matching (BM). Additionally, we analyze efficiency of the proposed DCAE in comparison with the conventional autoencoder (AE). We show that usage of the proposed DCAE provides an error of noise variance estimation about 2 times smaller, that the error when the standard AE is used, and 4 times smaller than the variance estimation error of the BM method.

Keywords

  • noise parameters estimation, autoencoder, deep convolutional networks, image denoising, image compression, image visual quality assessment

Publication forum classification

Field of science, Statistics Finland