Presentation | 2016-03-23 A Study of Sparse Feature Learning in the Learning Process of Deep Convolutional Neural Network Yoshihiro Kusano, Hayaru Shouno, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A study to make an image and a video high resolution with the improvement of the display and print technology is conducted actively, and there is super resolution in one of these studies. One of the super resolution technique is using convolutinal neural network suggested by Dong and we call this SRCNN. SRCNN was known as the technique that had high performance and,in this study,tried this technique of the strong MicroCT image of the noise. Because only the strong image of the noise is observed when I use MicroCT image for learning data set,this is more likely to fall into overlearning. I evaluate a super resolution system using only CT image dataset and CT image and natural image dataset and only natural natural image dataset based on the technique of Suzuki. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Super resolution / Convolutional neural network / MicroCT image |
Paper # | NC2015-81 |
Date of Issue | 2016-03-15 (NC) |
Conference Information | |
Committee | MBE / NC |
---|---|
Conference Date | 2016/3/22(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Tamagawa University |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Tetsuo Kobayashi(Kyoto Univ.) / Toshimichi Saito(Hosei Univ.) |
Vice Chair | Yutaka Fukuoka(Kogakuin Univ.) / Shigeo Sato(Tohoku Univ.) |
Secretary | Yutaka Fukuoka(akita noken) / Shigeo Sato(Kogakuin Univ.) |
Assistant | Takenori Oida(Kyoto Univ.) / Ryota Horie(Shibaura Inst. of Tech.) / Hiroyuki Kanbara(Tokyo Inst. of Tech.) / Hisanao Akima(Tohoku Univ.) |
Paper Information | |
Registration To | Technical Committee on ME and Bio Cybernetics / Technical Committee on Neurocomputing |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Study of Sparse Feature Learning in the Learning Process of Deep Convolutional Neural Network |
Sub Title (in English) | |
Keyword(1) | Super resolution |
Keyword(2) | Convolutional neural network |
Keyword(3) | MicroCT image |
1st Author's Name | Yoshihiro Kusano |
1st Author's Affiliation | University of Electro-Communications(UEC) |
2nd Author's Name | Hayaru Shouno |
2nd Author's Affiliation | University of Electro-Communications(UEC) |
Date | 2016-03-23 |
Paper # | NC2015-81 |
Volume (vol) | vol.115 |
Number (no) | NC-514 |
Page | pp.pp.65-70(NC), |
#Pages | 6 |
Date of Issue | 2016-03-15 (NC) |