本論文提出了一個書面樂譜辨識的方法，利用手機內建的相機拍攝市售樂譜或自製的樂譜，以藍芽將影像回傳至電腦端進行書面校正與樂譜辨識。辨識功能分為隨機及指定歌曲辨識；隨機歌曲進行整首歌曲的辨識，而指定歌曲則以小節為單位進行辨識與資料庫比對做歌曲搜尋。最後將辨識出來的音階與節拍轉成MIDI音樂檔於電腦端直接播放，或是回傳至手機當成手機鈴聲播放。 本論文的辨識系統分成兩大部分，第一部份是幾何扭曲校正的部分: 以角點偵測抓取書面的四個角，根據此四角的範圍偵測書面的邊界位置，利用書面的邊界對整個書面作水平和垂直方向的校正，則書本裝訂所造成扭曲可以得到校正。第二部份是樂譜辨識的部分: 利用校正完的影像，抓出主要譜表的部分，接著對譜表做譜線消去、音符抓取，最後利用音符範圍比例及符頭位置，判斷音階及節拍，加入樂理的修正後產生最後的辨識結果。This thesis presents a system for music recognition on non-flat surface music score, whether commercial or self-made music score by image processing. In this system, the image is captured by a mobile phone and sent to PC through Bluetooth protocol. And then the image distortion correction and music recognition are applied. Two modes are built in this system, namely random and assignment recognition mode. All and one part of music notes are recognized in random and assignment recognition mode, respectively. The recognition results are matched with the database for the song correction. Finally, the recognized music is converted to a MIDI file and played on the PC or mobile phone. The recognition system comprises two part processes, namely geometric distortion correction and music recognition. In geometric distortion correction, the corner and boundary detection and vertical and horizontal correction are applied to correct the image warping which is due to bookbinding. The meter and scale of music are recognized in music recognition part. The steps of music recognition are music staves detection, stuff lines detection and the music notes recognition. Finally, the music theory is applied to check the recognized results again. The experiment shows the recognition rate is about 95% in more than 30 songs, and the recognition time for each song is about 2.5 seconds.
