Presentation 2019-06-13
[Invited Talk] Image Processing Based on Sparse and Low-rank Modeling
Seisuke Kyochi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents fundamental tools for image recovery by convex optimization and introduces some case study from the author’s related works. During the image acquisition, images are often corrupted by many kinds of degradation, such as noise, blur caused by incorrect focus or handshaking. In image recovery framework, each process of degradation is mathematically modeled as a regularizer and integrated into the cost function. Finally, by solving the inverse problem, the desired image is estimated. For accurate image recovery, a suitable regularizer should be designed. In this paper, some convex regularizers based on sparsity and low-rankness are presented and shown their effectiveness in experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image recovery / Convex optimization / Sparse modeling / Low-rank modeling
Paper # SIS2019-10
Date of Issue 2019-06-06 (SIS)

Conference Information
Committee SIS / IPSJ-AVM / ITE-3DIT
Conference Date 2019/6/13(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Fukue Culture Center
Topics (in Japanese) (See Japanese page)
Topics (in English) Intelligent Multimedia Systems, Applied Enbedded Systems, Three-Dimensional Image Technology (3DIT), etc.
Chair Takayuki Nakachi(NTT) / Sei Naito(KDDI Research, Inc.) / Tsutomu Horikoshi(Shonan Institute of Technology)
Vice Chair Noriaki Suetake(Yamaguchi Univ.) / Tomoaki Kimura(Kanagawa Inst. of Tech.)
Secretary Noriaki Suetake(Tokyo Metropolitan Univ.) / Tomoaki Kimura(Kindai Univ.) / (NTT) / (Tokyo Univ. of Science)
Assistant Hideaki Misawa(National Inst. of Tech., Ube College) / Yukihiro Bandoh(NTT)

Paper Information
Registration To Technical Committee on Smart Info-Media Systems / Special Interest Group on Audio Visual and Multimedia Information Processing / Technical Group on Three-Dimensional Image Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Invited Talk] Image Processing Based on Sparse and Low-rank Modeling
Sub Title (in English)
Keyword(1) Image recovery
Keyword(2) Convex optimization
Keyword(3) Sparse modeling
Keyword(4) Low-rank modeling
1st Author's Name Seisuke Kyochi
1st Author's Affiliation The University of Kitakyushu(The Univ. of Kitakyushu)
Date 2019-06-13
Paper # SIS2019-10
Volume (vol) vol.119
Number (no) SIS-78
Page pp.pp.55-60(SIS),
#Pages 6
Date of Issue 2019-06-06 (SIS)