| Presentation | 2018-06-29 Symbol Classification and Pitch Recognition in Offline Handwritten Musical Score Yuki Hayakawa, Tetsushi Wakabayashi, Yasuji Miyake, Wataru Ohyama, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | To realize automatic recognition of handwritten music score in Optical Music Recognition (OMR), there are many problems : trimming of notation on staff, variety of notation appearance among writers, difference of distance between music symbols, to be solved. We propose classification and recognition methods for music symbols from offline handwritten music scores. We perform classification of music symbols and pitch recognition to notes with offline handwritten music score which removed staff. In classification step, we extract feature using chain code histogram from connected component in score without staff and classify each component into 18 classes using Modified Quadratic Discriminant Function. In recognition step, we divide a note into notehead, flag and stem and decide pitch from centroid’s position of notehead. As result, Accuracy of 90.2% was obtained in music symbol classification and Accuracy of 88.9% was obtained in pitch recognition, in the evaluation experiment on the CVC-MUSCIMA database. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Optical Music Recognition / Handwritten Music Score / Chain Code Histogram / Modified Quadratic Discriminant Function |
| Paper # | PRMU2018-35,SP2018-15 |
| Date of Issue | 2018-06-21 (PRMU, SP) |
| Conference Information | |
| Committee | PRMU / SP |
|---|---|
| Conference Date | 2018/6/28(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Yoichi Yamashita(Ritsumeikan Univ.) |
| Vice Chair | Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) / Akinobu Ri(Nagoya Inst. of Tech.) |
| Secretary | Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) / Akinobu Ri(Kyoto Univ.) |
| Assistant | Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) / Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Speech |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Symbol Classification and Pitch Recognition in Offline Handwritten Musical Score |
| Sub Title (in English) | |
| Keyword(1) | Optical Music Recognition |
| Keyword(2) | Handwritten Music Score |
| Keyword(3) | Chain Code Histogram |
| Keyword(4) | Modified Quadratic Discriminant Function |
| 1st Author's Name | Yuki Hayakawa |
| 1st Author's Affiliation | Mie University(Mie Univ.) |
| 2nd Author's Name | Tetsushi Wakabayashi |
| 2nd Author's Affiliation | Mie University(Mie Univ.) |
| 3rd Author's Name | Yasuji Miyake |
| 3rd Author's Affiliation | Mie University(Mie Univ.) |
| 4th Author's Name | Wataru Ohyama |
| 4th Author's Affiliation | Kyushu University(Kyushu Univ.) |
| Date | 2018-06-29 |
| Paper # | PRMU2018-35,SP2018-15 |
| Volume (vol) | vol.118 |
| Number (no) | PRMU-111,SP-112 |
| Page | pp.pp.73-77(PRMU), pp.73-77(SP), |
| #Pages | 5 |
| Date of Issue | 2018-06-21 (PRMU, SP) |