Presentation 2012-07-30
Noise reduction for images by ensemble learning
Eiji WATANABE, Takashi OZEKI, Takeshi KOHAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This report discusses a restoration method for JPEG images based on ensemble learning algorithm for multiple multi-layered neural networks. When images have edge and non-edge regions, it is difficult for single filter having fixed coefficients to reduce both blocky and mosquito noises adequately. Here, new restoration methods for JPEG images are proposed by introducing multiple muliti-layered neural networks. Each neural network can be adapted for edge, flat, and texture regions in images by ensemble learning. From experimental results, the proposed method can obtain good restoration accuracy compared with conventional filters. Moreover, we have confirmed that the proposed method could automatically assign restoration tasks to each neural network according to the characteristics of each region in given distorted images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) JPEG image / ensemble learning / noise reduction / neural network
Paper # NC2012-16
Date of Issue

Conference Information
Committee NC
Conference Date 2012/7/23(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Noise reduction for images by ensemble learning
Sub Title (in English)
Keyword(1) JPEG image
Keyword(2) ensemble learning
Keyword(3) noise reduction
Keyword(4) neural network
1st Author's Name Eiji WATANABE
1st Author's Affiliation Faculty of Intelligence and Informatics, Konan University()
2nd Author's Name Takashi OZEKI
2nd Author's Affiliation Faculty of Engineering, Fukuyama University
3rd Author's Name Takeshi KOHAMA
3rd Author's Affiliation School of Biology-Oriented Science and Technology, Kinki University
Date 2012-07-30
Paper # NC2012-16
Volume (vol) vol.112
Number (no) 168
Page pp.pp.-
#Pages 6
Date of Issue