Presentation 2018-11-30
Classification of man-made objects and nature-made objects in images using independent component analysis and orientation map
Yukihiro Dozono, Yukinori Suzuki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Classification of man-made objects and nature-made objects is an essential task in region segmentation of natural images. We studied this task using both independent component analysis (ICA) and orientation maps. ICA bases were computed from image blocks of man-made objects and nature-made objects. Since an image block can be reconstructed by ICA bases and their weight coefficients, we used the weights coefficients computed by both image blocks of man-made objects and image blocks of nature-made objects. A support vector machine (SVM) was used to learn the weight coefficients for classification. Cross-validation was used to determine the optimal parameters for the SVM. We also carried out experiments using the SVM to classify blocks in a natural image in which there were both man-made objects and nature-made objects. The ground truth was made by visual inspection. In comparison with ground truth, an average F-value of 0.55 (man-made objets) was obtained as classification accuracy. Orientation maps of the blocks of images were also learned by the SVM to classify man-made objects and nature-made objects. The experimental results showed that an orientation map is not effective for classifying man-made objects and nature-made objects.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) man-made objects / nature-made objects / ICA / SVM / region segmentation
Paper # CS2018-85,IE2018-64
Date of Issue 2018-11-22 (CS, IE)

Conference Information
Committee CS / IE / IPSJ-AVM / ITE-BCT
Conference Date 2018/11/29(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Tokushima University (Memorial Hall of Almuni(Engineering))
Topics (in Japanese) (See Japanese page)
Topics (in English) Image coding, Communications and streaming technologies, etc.
Chair Hidenori Nakazato(Waseda Univ.) / Takayuki Hamamoto(Tokyo Univ. of Science) / Hideaki Kimata(NTT) / Tomoaki Otsuki(Keio Univ.)
Vice Chair Jun Terada(NTT) / Hideaki Kimata(NTT) / Kazuya Kodama(NII) / / Kyoichi Saito(NHK) / Yasushi Kasuga(TV Asahi) / Masayoshi Fukumoto(NEC)
Secretary Jun Terada(NTT) / Hideaki Kimata(Waseda Univ.) / Kazuya Kodama(KDDI Research) / (Nagoya Univ.) / Kyoichi Saito(NTT) / Yasushi Kasuga(Tokyo Univ. of Science) / Masayoshi Fukumoto(KDDI Research, Inc.)
Assistant Kazutaka Hara(NTT) / Kentaro Toyoda(Keio Univ.) / Kazuya Hayase(NTT) / Yasutaka Matsuo(NHK) / / Toshiharu Morizumi(NTT) / Takahiro Shiozawa(National Inst. of Tech., Kagawa College) / Shigeru Watanabe(Nihon Dengyo Kosaku) / Shinya Takeuchi(NHK) / Takao Tsuda(NHK)

Paper Information
Registration To Technical Committee on Communication Systems / Technical Committee on Image Engineering / Special Interest Group on Audio Visual and Multimedia Information Processing / Technical Group on Broadcasting Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Classification of man-made objects and nature-made objects in images using independent component analysis and orientation map
Sub Title (in English)
Keyword(1) man-made objects
Keyword(2) nature-made objects
Keyword(3) ICA
Keyword(4) SVM
Keyword(5) region segmentation
1st Author's Name Yukihiro Dozono
1st Author's Affiliation Muroran Institute of Technology(Muroran IT)
2nd Author's Name Yukinori Suzuki
2nd Author's Affiliation Muroran Institute of Technology(Muroran IT)
Date 2018-11-30
Paper # CS2018-85,IE2018-64
Volume (vol) vol.118
Number (no) CS-328,IE-329
Page pp.pp.111-116(CS), pp.111-116(IE),
#Pages 6
Date of Issue 2018-11-22 (CS, IE)