| Presentation | 2019-03-18 Improvement of Tree-Drawing Classification Using Convolutional Neural Network Tosuke Sonoda, Motoi Iwata, Hiroyuki Inadomi, Koichi Kise, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The Baum test is a psychological examination of a projection method. In a Baum test, the patient is requested to draw a tree that bears fruit and the psychologist analyze the patient's personality by evaluating the tree-drawing. If tree-drawings are automatically classified with a computer, psychologists can use the classification results by the computer as a reference when evaluating tree-drawings. The samples of tree-drawings are difficult to increase, because of the patient's privacy and ethical problem, so we need to train CNN with few samples. In this paper, we propose methods to improve the accuracy of the classifier of tree-drawings using CNN. As a result of the experiments, the accuracy is improved from 60.3 % to 69.7 %. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | convolutional neural networks / rehabilitation / baum test / tree-drawing classification / sociopsychology |
| Paper # | BioX2018-54,PRMU2018-158 |
| Date of Issue | 2019-03-10 (BioX, PRMU) |
| Conference Information | |
| Committee | PRMU / BioX |
|---|---|
| Conference Date | 2019/3/17(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Kazuhiko Sumi(AGU) |
| Vice Chair | Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) / Hitoshi Imaoka(NEC) / Tetsushi Ohki(Shizuoka Univ.) |
| Secretary | Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) / Hitoshi Imaoka(Fujitsu Labs.) / Tetsushi Ohki(Univ. of Electro-Comm.) |
| Assistant | Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) / Norihiro Okui(KDDI Research) / Daishi Watabe(Saitama Inst. of Tech.) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Biometrics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Improvement of Tree-Drawing Classification Using Convolutional Neural Network |
| Sub Title (in English) | |
| Keyword(1) | convolutional neural networks |
| Keyword(2) | rehabilitation |
| Keyword(3) | baum test |
| Keyword(4) | tree-drawing classification |
| Keyword(5) | sociopsychology |
| 1st Author's Name | Tosuke Sonoda |
| 1st Author's Affiliation | Osaka Prefecture University(Osaka Pref Univ.) |
| 2nd Author's Name | Motoi Iwata |
| 2nd Author's Affiliation | Osaka Prefecture University(Osaka Pref Univ.) |
| 3rd Author's Name | Hiroyuki Inadomi |
| 3rd Author's Affiliation | Kyoto University(Kyoto Univ) |
| 4th Author's Name | Koichi Kise |
| 4th Author's Affiliation | Osaka Prefecture University(Osaka Pref Univ.) |
| Date | 2019-03-18 |
| Paper # | BioX2018-54,PRMU2018-158 |
| Volume (vol) | vol.118 |
| Number (no) | BioX-512,PRMU-513 |
| Page | pp.pp.149-154(BioX), pp.149-154(PRMU), |
| #Pages | 6 |
| Date of Issue | 2019-03-10 (BioX, PRMU) |