| Presentation | 1994/1/21 An Improvement of Nonlinear Normalization Method in Handprinted Character Recognition Yan Deng, Tetsushi Wakabayashi, Shinji Tsuruoka, Fumitaka Kimura, Yasuji Miyake, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Although there are many problems that should be solved in handprinted character recognition,the most fundamental one is absorbing′ the local variation in handprinted character pattem.For the purpose,several nonlinear normalization methods^(3)(4)(5)> that use line density features have been proposed.It is effective to deal with this problem using the method of paper(5)proposed by Dr.Yamada,but there are still some defects which can be improved. In this paper,a nonlinear normalization method using the closure rates of character which reflect the structure information about the directions of strokes of character is proposed.Furthermore,to confirm the efficiency of the statistical recognition method,we have carried out recognition experiments with Database ETL9B by using the weighted direction index histogram features and modified quadratic discriminant function,and have shown the effects of the experiments. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | character recognition / line density / closure rate / feature extraction / weighted direction index histogram / discriminant function |
| Paper # | PRU93-126 |
| Date of Issue |
| Conference Information | |
| Committee | PRU |
|---|---|
| Conference Date | 1994/1/21(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 Understanding (PRU) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | An Improvement of Nonlinear Normalization Method in Handprinted Character Recognition |
| Sub Title (in English) | |
| Keyword(1) | character recognition |
| Keyword(2) | line density |
| Keyword(3) | closure rate |
| Keyword(4) | feature extraction |
| Keyword(5) | weighted direction index histogram |
| Keyword(6) | discriminant function |
| 1st Author's Name | Yan Deng |
| 1st Author's Affiliation | Department of Information Engineering,Faculty of Engineering,Mie University() |
| 2nd Author's Name | Tetsushi Wakabayashi |
| 2nd Author's Affiliation | Department of Information Engineering,Faculty of Engineering,Mie University |
| 3rd Author's Name | Shinji Tsuruoka |
| 3rd Author's Affiliation | Department of Electrical and Electronic Engineering,Faculty of Engineering,Mie University |
| 4th Author's Name | Fumitaka Kimura |
| 4th Author's Affiliation | Department of Information Engineering,Faculty of Engineering,Mie University |
| 5th Author's Name | Yasuji Miyake |
| 5th Author's Affiliation | Department of Information Engineering,Faculty of Engineering,Mie University |
| Date | 1994/1/21 |
| Paper # | PRU93-126 |
| Volume (vol) | vol.93 |
| Number (no) | 431 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |