Presentation 2020-12-01
A Proposal of Convolutional Neural Networks detecting and removing noise for Random-Valued Impulse Noise Denoising
Yukiya Fukuda, Ryosuke Kubota, Hakaru Tamukoh,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When digital images are transmitted, Random-Valued Impulse Noise (RVIN) may cause image degradation. RVIN is known as noise that is difficult to remove, because random values are added independently to original image information. In this paper, we propose a new RVIN removal method using a Convolutional Neural Networks(CNNs) with high accuracy. The proposed method consists of a detection part that detects where the RVINs are added and a removal part that removes detected RVIN. A detection result by the detection part is obtained as a matrix and it becomes input of the removal part with an input image. In experiments, the proposed method is compared with the conventional method from both viewpoints of detection and removal accuracy. As a result, some of the detection accuracies of the proposed method were lower than that of the conventional method, while the removal accuracy was improved.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Denoising / Random-Valued Impulse Noise / Convolutional Neural Network
Paper # SIS2020-34
Date of Issue 2020-11-24 (SIS)

Conference Information
Committee SIS
Conference Date 2020/12/1(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English) Smart Personal Systems, etc.
Chair Noriaki Suetake(Yamaguchi Univ.)
Vice Chair Tomoaki Kimura(Kanagawa Inst. of Tech.) / Naoto Sasaoka(Tottori Univ.)
Secretary Tomoaki Kimura(Kindai Univ.) / Naoto Sasaoka(National Inst. of Tech., Ube College)
Assistant Yukihiro Bandoh(NTT) / Soh Yoshida(Kansai Univ.)

Paper Information
Registration To Technical Committee on Smart Info-Media Systems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Proposal of Convolutional Neural Networks detecting and removing noise for Random-Valued Impulse Noise Denoising
Sub Title (in English)
Keyword(1) Denoising
Keyword(2) Random-Valued Impulse Noise
Keyword(3) Convolutional Neural Network
1st Author's Name Yukiya Fukuda
1st Author's Affiliation Kyusyu Institute of Technology(Kytutech)
2nd Author's Name Ryosuke Kubota
2nd Author's Affiliation National Institute of Technology, Ube College(NITUC)
3rd Author's Name Hakaru Tamukoh
3rd Author's Affiliation Kyusyu Institute of Technology(Kyutech)
Date 2020-12-01
Paper # SIS2020-34
Volume (vol) vol.120
Number (no) SIS-269
Page pp.pp.35-40(SIS),
#Pages 6
Date of Issue 2020-11-24 (SIS)