Presentation 2016-06-13
A study on performance improvement of multi-class image classification using modified CS-LBP features
Toshiaki Inoue,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) LBP feature, suitable for robust and low-cost texture classification, is expected to be available for high-performance image recognition systems in various applications such as traffics, surveillance, and medicals. In this paper, we describe discrimination improvements of CS-LBP feature, one of LBP techniques. In original methods, features are expressed by binary encoding of primary spatial differentials about pixel values, whereas in our method, binary encoding of secondary spatial differentials followed by re-encoding with rotation-invariance relation between all binary patterns is adopted. Multi-class image classification tests using a framework composed of BoVW image descriptor and non-linear subspace method shows that our method is effective in various dataset such as generic objects, indoor/outdoor scenes, as well as texture images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) CS-LBP / bag of visual words / subspace method / classification
Paper # PRMU2016-35,SP2016-1,WIT2016-1
Date of Issue 2016-06-06 (PRMU, SP, WIT)

Conference Information
Committee PRMU / SP / WIT / ASJ-H
Conference Date 2016/6/13(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Eisaku Maeda(NTT) / Kazunori Mano(Shibaura Inst. of Tech.) / Kiyohiko Nunokawa(Tokyo International Univ.)
Vice Chair Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / Hiroki Mori(Utsunomiya Univ.) / Chikamune Wada(Kyushu Inst. of Tech.)
Secretary Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / Hiroki Mori(Kobe Univ.) / Chikamune Wada(Shizuoka Univ.) / (Nagoya Inst. of Tech.)
Assistant Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / Taichi Asami(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Tomohiro Amemiya(NTT) / Takeaki Shionome(Tsukuba Univ. of Tech.) / Manabi Miyagi(Tsukuba Univ. of Tech.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Speech / Technical Committee on Well-being Information Technology / Auditory Research Meeting
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A study on performance improvement of multi-class image classification using modified CS-LBP features
Sub Title (in English)
Keyword(1) CS-LBP
Keyword(2) bag of visual words
Keyword(3) subspace method
Keyword(4) classification
1st Author's Name Toshiaki Inoue
1st Author's Affiliation Pioneer Corporation(Pioneer)
Date 2016-06-13
Paper # PRMU2016-35,SP2016-1,WIT2016-1
Volume (vol) vol.116
Number (no) PRMU-89,SP-90,WIT-91
Page pp.pp.1-6(PRMU), pp.1-6(SP), pp.1-6(WIT),
#Pages 6
Date of Issue 2016-06-06 (PRMU, SP, WIT)