Presentation 2017-10-12
Extracting photographic subjects with deep learning and automatically select to best composition
Soma Nagadome, Shigeki Aoki, Takao Miyamoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Recently, opportunities for taking pictures are increasing, but many people are difficult to take pictures beautifully. There are extracting photographic subjects and matching composition in existing methods. However, since this method can't estimate induced pictures, it is not necessarily that photographic subjects are taken beautifully for mixed different photographic subjects and background. In this paper, we propose a method to extract photographic subjects from moving images with deep learning and automatically select pictures taken at best composition based on size or position of photographic subjects.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Deep-learning / Extracting subjects / Pictures / Composition
Paper # PRMU2017-65
Date of Issue 2017-10-05 (PRMU)

Conference Information
Committee PRMU
Conference Date 2017/10/12(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Shinichi Sato(NII)
Vice Chair Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron)
Secretary Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST)
Assistant Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Extracting photographic subjects with deep learning and automatically select to best composition
Sub Title (in English)
Keyword(1) Deep-learning
Keyword(2) Extracting subjects
Keyword(3) Pictures
Keyword(4) Composition
1st Author's Name Soma Nagadome
1st Author's Affiliation Osaka Prefecture University(Osaka Pref. Univ.)
2nd Author's Name Shigeki Aoki
2nd Author's Affiliation Osaka Prefecture University(Osaka Pref. Univ.)
3rd Author's Name Takao Miyamoto
3rd Author's Affiliation Osaka Prefecture University(Osaka Pref. Univ.)
Date 2017-10-12
Paper # PRMU2017-65
Volume (vol) vol.117
Number (no) PRMU-238
Page pp.pp.13-18(PRMU),
#Pages 6
Date of Issue 2017-10-05 (PRMU)