Presentation | 2017-10-05 Segmentation of Campus Images based on Image Features for Building Recognition Kenta Yamanishi, Shun Hattori, Yukinori Suzuki, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We have been studying building recognition in natural images by taking picture in a college campus. Itis difficult to recognize buildings accurately because the campus image contains various objects other than buildings in a campus such as people, trees, grass, cars, bicycles and roads. We therefore carried out an image segmentation using image features for accurate building recognition. Two segmentation algorithms were examined: (1) supervised segmentation using Gabor features and a support vector machine and (2) unsupervised segmentation using statistical geometrical features. Segmentation was carried out after converting a color image to a gray scale image. An effective gray scale conversion for image segmentation was also investigated. Computational experiments showed that the supervised segmentation was not able to divide the test images (which were not used to train SVM) satisfactorily. On the other hand, the unsupervised segmentation was able to divide the test images roughly in both cases of luminance and MSB conversion, respectively. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | SGF / Gabor feature / image features / region segmentation / Gray scale conversion / SVM |
Paper # | IE2017-51 |
Date of Issue | 2017-09-28 (IE) |
Conference Information | |
Committee | IE / ITE-ME / ITE-AIT |
---|---|
Conference Date | 2017/10/5(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Takayuki Hamamoto(Tokyo Univ. of Science) / Miki Haseyama(Hokkaido Univ.) / Nobuhiko Mukai(Tokyo Cisy Univ.) |
Vice Chair | Kazuya Kodama(NII) / Hideaki Kimata(NTT) |
Secretary | Kazuya Kodama(Nagoya Univ.) / Hideaki Kimata(KDDI Research) |
Assistant | Yasutaka Matsuo(NHK) / Kazuya Hayase(NTT) |
Paper Information | |
Registration To | Technical Committee on Image Engineering / Technical Group on Media Engineering / Technical Group on Artistic Image Technology |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Segmentation of Campus Images based on Image Features for Building Recognition |
Sub Title (in English) | |
Keyword(1) | SGF |
Keyword(2) | Gabor feature |
Keyword(3) | image features |
Keyword(4) | region segmentation |
Keyword(5) | Gray scale conversion |
Keyword(6) | SVM |
1st Author's Name | Kenta Yamanishi |
1st Author's Affiliation | Muroran Institute of Technology(Muroran-IT) |
2nd Author's Name | Shun Hattori |
2nd Author's Affiliation | Muroran Institute of Technology(Muroran-IT) |
3rd Author's Name | Yukinori Suzuki |
3rd Author's Affiliation | Muroran Institute of Technology(Muroran-IT) |
Date | 2017-10-05 |
Paper # | IE2017-51 |
Volume (vol) | vol.117 |
Number (no) | IE-228 |
Page | pp.pp.25-30(IE), |
#Pages | 6 |
Date of Issue | 2017-09-28 (IE) |