Presentation | 2019-10-24 Image Regularization with Total Variation and Morphological Gradient Priors Using Optimization of Structuring Element for Each Pixel Shoya Oohara, Hirotaka Oka, Mistuji Muneyasu, Soh Yoshida, Makoto Nakashizuka, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | As an image prior for image restoration, a method using the sum of morphological gradients has been proposed. Optimization of a structuring element (SE) used for this morphological gradient by a genetic algorithm (GA) has also been introduced. In this method, a single SE is selected for the entire image. However, since the whole image is processed with only one SE, it is difficult to deal with various edges and textures in the image. In this paper, we propose a method to optimize the SE for each pixel and to restore the image using its SE. For reducing the computational burden, simulated annealing is introduced, and the reduction of the computational cost in the evaluation of the SE is proposed. By optimizing the SE for each pixel, edges, and details in the image can be faithfully evaluated, and improvement in restoration accuracy can be expected. An experiment shows the effectiveness of the proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | morphology / morphological gradient / total variation / regularization / image restoration / simulated annealing |
Paper # | SIS2019-17 |
Date of Issue | 2019-10-17 (SIS) |
Conference Information | |
Committee | ITE-BCT / SIS |
---|---|
Conference Date | 2019/10/24(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Fukui International Activities Plaza |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | System Implementation Technology, Short Range Wireless Systems, Smart Multimedia Systems, Broadcasting Technology, etc. |
Chair | Kyoichi Saito(NHK) / Takayuki Nakachi(NTT) |
Vice Chair | / Noriaki Suetake(Yamaguchi Univ.) / Tomoaki Kimura(Kanagawa Inst. of Tech.) |
Secretary | (NHK) / Noriaki Suetake(NTV) / Tomoaki Kimura(NEC) |
Assistant | Shigeki Shiokawa(Kanagawa Inst. of Tech.) / Shoichiro Sekiguchi(NHK) / Toshiharu Morizumi(NTT) / Iwao Namikawa(Kansai Telecasting Corporation) / Hideaki Misawa(National Inst. of Tech., Ube College) / Yukihiro Bandoh(NTT) |
Paper Information | |
Registration To | Technical Group on Broadcasting and Communication Technologies / 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) | Image Regularization with Total Variation and Morphological Gradient Priors Using Optimization of Structuring Element for Each Pixel |
Sub Title (in English) | |
Keyword(1) | morphology |
Keyword(2) | morphological gradient |
Keyword(3) | total variation |
Keyword(4) | regularization |
Keyword(5) | image restoration |
Keyword(6) | simulated annealing |
1st Author's Name | Shoya Oohara |
1st Author's Affiliation | Kansai University(Kansai Univ.) |
2nd Author's Name | Hirotaka Oka |
2nd Author's Affiliation | Kansai University(Kansai Univ.) |
3rd Author's Name | Mistuji Muneyasu |
3rd Author's Affiliation | Kansai University(Kansai Univ.) |
4th Author's Name | Soh Yoshida |
4th Author's Affiliation | Kansai University(Kansai Univ.) |
5th Author's Name | Makoto Nakashizuka |
5th Author's Affiliation | Chiba Institute of Technology(CIT) |
Date | 2019-10-24 |
Paper # | SIS2019-17 |
Volume (vol) | vol.119 |
Number (no) | SIS-240 |
Page | pp.pp.47-52(SIS), |
#Pages | 6 |
Date of Issue | 2019-10-17 (SIS) |