Presentation | 2023-03-02 A trial of writer identification using a deep neural network trained by handwriting of multiple character types Yoshinori Akao, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We attempted to identify the writer by learning a deep network (GoogLeNet) using a handwriting database of 548 kanji characters (401 participants, 5 times repetitions) as a sample. The output of the network's activation function enabled us to identify the writer even when a character type not included in the training set. The deep network after training was considered to capture the characteristics of the writer's handwriting that transcended the character types. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | handwriting / writer identification / deep learning / character-independent |
Paper # | PRMU2022-72,IBISML2022-79 |
Date of Issue | 2023-02-23 (PRMU, IBISML) |
Conference Information | |
Committee | PRMU / IBISML / IPSJ-CVIM |
---|---|
Conference Date | 2023/3/2(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Future University Hakodate |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Seiichi Uchida(Kyushu Univ.) / Masashi Sugiyama(Univ. of Tokyo) |
Vice Chair | Takuya Funatomi(NAIST) / Mitsuru Anpai(Denso IT Lab.) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
Secretary | Takuya Funatomi(CyberAgent) / Mitsuru Anpai(Univ. of Tokyo) / Toshihiro Kamishima(NTT) / Koji Tsuda(Hokkaido Univ.) |
Assistant | Nakamasa Inoue(Tokyo Inst. of Tech.) / Yasutomo Kawanishi(Riken) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Information-Based Induction Sciences and Machine Learning / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A trial of writer identification using a deep neural network trained by handwriting of multiple character types |
Sub Title (in English) | A study using a handwriting database of 401 writers |
Keyword(1) | handwriting |
Keyword(2) | writer identification |
Keyword(3) | deep learning |
Keyword(4) | character-independent |
1st Author's Name | Yoshinori Akao |
1st Author's Affiliation | National Research Institute of Police Science(NRIPS) |
Date | 2023-03-02 |
Paper # | PRMU2022-72,IBISML2022-79 |
Volume (vol) | vol.122 |
Number (no) | PRMU-404,IBISML-405 |
Page | pp.pp.76-81(PRMU), pp.76-81(IBISML), |
#Pages | 6 |
Date of Issue | 2023-02-23 (PRMU, IBISML) |