Presentation | 2020-12-18 CNN and 2D BLSTM for Local Feature Extraction in Handwritten Mathematical Expression Recognition Kei Morizumi, Cuong Tuan Nguyen, Ikuko Shimizu, Masaki Nakagawa, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Descriptive questions in mathematics are effective to examine learners’ understanding, but marking handwritten answers are costly and time-consuming. Therefore, it is anticipated to automate marking them. Their recognition and clustering must be established. However, the performance even by the latest methods is not adequate. In this paper, we propose 2D BLSTM for feature extraction to improve their recognition rate. It is effective for extracting 2D context to improve the recognition rate by about 3.5. We also propose CTC training for further improving the feature extraction. It improves the recognition rate by about 5.5. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Machine Learning / Mathematical expression recognition / CNN / BLSTM |
Paper # | PRMU2020-56 |
Date of Issue | 2020-12-10 (PRMU) |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2020/12/17(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Transfer learning and few shot learning |
Chair | Yoichi Sato(Univ. of Tokyo) |
Vice Chair | Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.) |
Secretary | Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.) |
Assistant | Takashi Shibata(NTT) / Masashi Nishiyama(Tottori 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) | CNN and 2D BLSTM for Local Feature Extraction in Handwritten Mathematical Expression Recognition |
Sub Title (in English) | |
Keyword(1) | Machine Learning |
Keyword(2) | Mathematical expression recognition |
Keyword(3) | CNN |
Keyword(4) | BLSTM |
1st Author's Name | Kei Morizumi |
1st Author's Affiliation | Tokyo University of Agriculture and Technology(TUAT) |
2nd Author's Name | Cuong Tuan Nguyen |
2nd Author's Affiliation | Tokyo University of Agriculture and Technology(TUAT) |
3rd Author's Name | Ikuko Shimizu |
3rd Author's Affiliation | Tokyo University of Agriculture and Technology(TUAT) |
4th Author's Name | Masaki Nakagawa |
4th Author's Affiliation | Tokyo University of Agriculture and Technology(TUAT) |
Date | 2020-12-18 |
Paper # | PRMU2020-56 |
Volume (vol) | vol.120 |
Number (no) | PRMU-300 |
Page | pp.pp.105-110(PRMU), |
#Pages | 6 |
Date of Issue | 2020-12-10 (PRMU) |