Presentation | 2004/6/11 Performance evaluation of on-line handwritten mathematical formula recognition systems Kenichi TOYOZUMI, Naoya YAMADA, Takayuki KITASAKA, Kensaku MORI, Yasuhito SUENAGA, Kenji MASE, Tomoichi TAKAHASHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We propose a new method for evaluating the performance of on-line handwritten mathematical formula recognition systems. The proposed method uses the number of interactive "error correction" operations required according to incorrect recognition of handwritings. When we input mathematical formulas into a computer using on-line handwriting recognition systems, errors may occur in three stages : (1) symbol segmentation, (2) symbol recognition, and (3) mathematical structure recognition. In general, it is not so simple to evaluate the performance of whole recognition system since the errors often depend on each other. In this paper, we present an intuitive and quantitative method for evaluating the whole recognition system by measuring the number of "error correction" operations to obtain correct formulas interactively based on incorrect recognition results. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | on-line recognition of handwritten mathematical formulas / performance evaluation / correction operation / tree structure |
Paper # | PRMU2004-38 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2004/6/11(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Performance evaluation of on-line handwritten mathematical formula recognition systems |
Sub Title (in English) | |
Keyword(1) | on-line recognition of handwritten mathematical formulas |
Keyword(2) | performance evaluation |
Keyword(3) | correction operation |
Keyword(4) | tree structure |
1st Author's Name | Kenichi TOYOZUMI |
1st Author's Affiliation | Graduate School of Information Science, Nagoya University() |
2nd Author's Name | Naoya YAMADA |
2nd Author's Affiliation | Graduate School of Information Science, Nagoya University:Canon Inc. |
3rd Author's Name | Takayuki KITASAKA |
3rd Author's Affiliation | Graduate School of Information Science, Nagoya University |
4th Author's Name | Kensaku MORI |
4th Author's Affiliation | Graduate School of Information Science, Nagoya University |
5th Author's Name | Yasuhito SUENAGA |
5th Author's Affiliation | Graduate School of Information Science, Nagoya University |
6th Author's Name | Kenji MASE |
6th Author's Affiliation | Graduate School of Information Science, Nagoya University |
7th Author's Name | Tomoichi TAKAHASHI |
7th Author's Affiliation | Faculty of Science and Technology, Meijo University |
Date | 2004/6/11 |
Paper # | PRMU2004-38 |
Volume (vol) | vol.104 |
Number (no) | 125 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |