五線譜之即時辨識與演奏

Real-Time Music Score Recognition and Playing

張智鈞(Chih-Chun Chang)

指導教授 ： 王文俊

國立臺北科技大學/電資學院/電機工程系研究所/碩士(2009年)

摘要

本論文提出了一個樂譜辨識的方法，以市售的webcam攝影機，對於複雜環境下的樂譜進行擷取與辨識。在辨識完成後可由兩種方式進行演奏：第一，結合目前熱門的機器人領域，透過另一位同學所設計之娛樂型音樂機器人，根據辨識完成的結果，在鐵琴上敲打出樂音；第二，將辨識結果編碼後，轉換成電子音樂MIDI格式，透過播放軟體將音樂播放出來。
本論文辨識樂譜經過兩個步驟，第一為影像處理的技術，從擷取複雜環境下的樂譜開始，到對各音符進行辨識，以階層的方式，逐步縮小辨識範圍。其次在樂譜辨識過程後導入樂理知識，檢驗辨識結果是否符合樂理，若不符合再加以修正錯誤的辨識結果。
本研究提供了一個兼具辨識速度與辨識率的樂譜辨識方法，實驗中使用了近三十首包含單、雙部的鋼琴譜進行辨識，依據攝影機的影像解析度與各樂譜的複雜度，在解析度為1028×960的情況下，平均每首歌曲的辨識時間為4秒左右，辨識率可達95%以上。不僅如此，本辨識系統也可以對於手機所拍攝樂譜影像進行辨識，使樂譜辨識更富應用性。

關鍵字

影像辨識 ； 樂譜辨識

並列摘要

This thesis presented a method for music score recognition. When a commercial webcam captures the music notes in a complex environment, there are two ways to play the recognized music score. One is played by the percussion robot. The other way is transformed the recognized music score to electronic music MIDI code and played by a music software.
This thesis has two steps to recognize music score, the first one is the image processing techniques which detects music score in the complex environment and recognizes the music notes. The other is adding music theory to check the recognized music score and modify it as correct as possible.
This research proposes the method of music score recognition fast and correctly. In the experiment, we have recognized 30 songs from printed piano scores. Moreover, the system can recognize the image of music score from the picture taken from the camera of cell phone. Based on the camera resolution and the complexity of music, the average accuracy is over 95% on an average.

並列關鍵字

Image Recognition ； Music Score Recognition

參考文獻

[1] S. Degallier, C.P. Santos, L. Righetti, and A. Ijspeert, “Movement generation using dynamical systems : a humanoid robot performing a drumming task,” Proceedings of IEEE-RAS International Conference on Humanoid Robots, Genova, 2006, pp. 512 – 517.

[3] K. Shibuya, S. Matsuda and A. Takahara, “Toward Developing a Violin Playing Robot - Bowing by Anthropomorphic Robot Arm and Sound Analysis -,” Proceedings of IEEE International Conference on Robot and Human Interactive Communication, Jeju, 2007, pp. 763 – 768.

[4] E. Sicard, “An Efficient Method for the Recognition of Printed Music,” Proceedings of the 11th IAPR International Conference on Pattern Recognition vol. 3. Conference C: Image, Speech and Signal Analysis, The Hague, 1992, pp. 573 – 576.

[5] M. Szwoch, “Guido: a Musical Score Recognition System,” Proceedings of the 9th International Conference on Document Analysis and Recognition, Parana, 2007, pp. 809 – 813.

[6] F. Rossant, “A global method for music symbol recognition in typeset music sheets,” Pattern Recognition Letters, vol. 23, no. 10, 2002, pp. 1129 – 1141.