| Presentation | 2019-10-24 Image enhancement-based data augmentation for improving deep learning in image classification problem Weihang Zhang, Yuma Kinoshita, Hitoshi Kiya, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a novel data augmentation method based on image enhancement. In DNN-based image classification, it is required to prepare sufficient training datasets taken in different weather conditions and lighting conditions for achieving a high performance. Hence, various data augmentation methods have been studied. In this paper, we propose applying an image enhancement method to data augmentation to generate images with different exposures. Experimental results show that the proposed method is effective as an image data augmentation method. The results also demonstrate that it can be used in combination with other existing data augmentation methods. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Deep learning / Image classification / Image enhancement / Data augmentation |
| Paper # | SIS2019-11 |
| Date of Issue | 2019-10-17 (SIS) |
| Conference Information | |
| Committee | ITE-BCT / SIS |
|---|---|
| Conference Date | 2019/10/24(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Fukui International Activities Plaza |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | System Implementation Technology, Short Range Wireless Systems, Smart Multimedia Systems, Broadcasting Technology, etc. |
| Chair | Kyoichi Saito(NHK) / Takayuki Nakachi(NTT) |
| Vice Chair | / Noriaki Suetake(Yamaguchi Univ.) / Tomoaki Kimura(Kanagawa Inst. of Tech.) |
| Secretary | (NHK) / Noriaki Suetake(NTV) / Tomoaki Kimura(NEC) |
| Assistant | Shigeki Shiokawa(Kanagawa Inst. of Tech.) / Shoichiro Sekiguchi(NHK) / Toshiharu Morizumi(NTT) / Iwao Namikawa(Kansai Telecasting Corporation) / Hideaki Misawa(National Inst. of Tech., Ube College) / Yukihiro Bandoh(NTT) |
| Paper Information | |
| Registration To | Technical Group on Broadcasting and Communication Technologies / Technical Committee on Smart Info-Media Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Image enhancement-based data augmentation for improving deep learning in image classification problem |
| Sub Title (in English) | |
| Keyword(1) | Deep learning |
| Keyword(2) | Image classification |
| Keyword(3) | Image enhancement |
| Keyword(4) | Data augmentation |
| 1st Author's Name | Weihang Zhang |
| 1st Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
| 2nd Author's Name | Yuma Kinoshita |
| 2nd Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
| 3rd Author's Name | Hitoshi Kiya |
| 3rd Author's Affiliation | Tokyo Metropolitan University(Tokyo Metro. Univ.) |
| Date | 2019-10-24 |
| Paper # | SIS2019-11 |
| Volume (vol) | vol.119 |
| Number (no) | SIS-240 |
| Page | pp.pp.1-4(SIS), |
| #Pages | 4 |
| Date of Issue | 2019-10-17 (SIS) |