印刷樂譜辨識系統(OMR)可自動辨識光學掃描印刷樂譜，並轉換為電子音樂MIDI格式。將一般樂譜數位化有許多好處，例如：表演者可用電腦伴奏來做練習，或建立音樂資料庫且佔用較少記錄空間，還可以針對樂譜做編輯、修改或列印。
不像一般文件，樂譜為二維關係 — 五線譜上水平方向不同音樂標誌代表不同音長，垂直方向不同位置代表不同音高，而且樂譜中符號大小並不固定，形狀也為動態。由於印刷品質與排版情形不同，而且每次進行光學掃描時所設定解析度也可能有所不同，再加上人為造成樂譜傾斜或雜訊，種種因素使得許多相關研究無法很彈性處理這些問題，或只能在某些限制下進行辨識。
本論文涵蓋了兩個領域知識：一者為影像處理技術，主要使用投影法擷取水平與垂直線段以縮小辨識範圍，再利用型態學法辨識各種音樂符號，另一者為樂理知識，用來提供分析上之輔助，並修正辨識錯誤之處。
本系統分成三大階段，第一階段為前置處理，為避免人為掃描影像之傾斜，首先將影像做角度修正，以利接下來五線譜偵測與移除，移除五線譜是為了使所有音樂符號孤立出來，避免五線譜妨礙辨識。第二階段，針對垂直線段，與非垂直線段音樂符號進行辨識，並組成音樂標誌進行樂理焠鍊。第三階段，將所有音樂標誌記錄成音樂表示語言，再經程式轉換成電子音樂MIDI格式，可藉由播放軟體將旋律播放出來。
實驗結果顯示本系統可在短時間內成功辨識各式印刷樂譜，並且沒有解析度之硬性限制。

Optical music recognition (OMR) allows pages of sheet music to be interpreted by a computer, and converted into a versatile machine-readable format. There are many advantages of such a system. For instance, a soloist could have the computer play an accompaniment for rehearsal; a user could build music database occupying less memory; or a musicologist could make an edition, modification, or print of the captured image.
Typically, OCR techniques can not be used in music score recognition since music notation presents a two dimensional structure: in a staff the horizontal position denotes different duration for notes and the vertical position defines the height of the note. That the quality or the typesetting of a score is not the same, or some of the man-made factors make many related researches could not process flexibility, or could only recognize with restriction.
The paper covers two fields of knowledge: one is image processing technology, mainly based on projection, which is employed to extract horizontal and vertical line to abridge the recognition field, and morphology, which recognize musical symbols. The other is music metric, which provides the help on the analysis, and corrects the errors after recognizing.
This system divides into three phases. It starts with all the pre-processing that is needed to de-skew input image, which afford to staff line detection and removal. Then, the symbol recognition, detects the vertical and non-vertical line musical symbol respectively, which are combined into a notation to refine by metric. Finally, the results are stored in a musical representation language, which could be converted into the MIDI format and the music can be played on a MIDI synthesizer.
The experiment shows this system could get a satisfied result successfully in short time, and there is no hard-and-fast claim for image resolution.

摘要 I
第一章 緒論 1
1.1 前言 1
1.2 基本音樂知識 2
1.3 相關研究 10
1.4 研究概述 18
第二章 理論基礎 20
2.1 正交投影法 20
2.2 型態學法 22
2.3 樂理使用 28
第三章 研究方法及步驟 31
3.1前置處理 31
3.1.1 傾斜修正 31
3.1.2 五線譜偵測 34
3.2 符號辨識 39
3.2.1 垂直線段音樂符號辨識 40
3.2.2 非垂直線段音樂符號辨識 44
3.2.3辨識步驟 48
3.2.4樂理焠鍊 58
3.3 格式轉換 60
第四章 實驗與討論 64
4.1 結果比較 64
4.2 討論 71
第五章 結論 72
參考文獻 73

[1] D. Pruslin, “Automatic recognition of sheet music,” Sc.D. Dissertation, Massachusetts Institute of Technology, 1966.
[2] M. Eden, “Other pattern recognition problems and some generalizations,” Recognizing Patterns, edited by M. Eden and P. Kolers, MIT Press, 1968.
[3] D. S. Prerau, “Computer pattern recognition of printed music,” AFIP Conference proceedings, Vol.39 1971 fall joint computer conference, pp. 153-62, 1971.
[4] A. Andronico and A. Ciampa, “On automatic pattern recognition and acquisition of printed music,” Proceedings of the ICMC, pp. 245-78, 1982.
[4] N. P. Carter, “Automatic recognition of printed music in the context of electronic publishing,” Ph.D. thesis, University of Surrey, 1989.
[5] S. Inokuchi, and H. Katayose, “Computer and music,” Journal of the IEICE, 73(9), pp. 965-7, 1990.
[6] H. Miyao and Y. Nakano, “Head and stem extraction from printed music scores using a neural network approach,” Proceedings of the 3th ICDAR, pp. 1074-9, 1995.
[7] K. C. Ng and R. D. Boyle, “Recognition and reconstruction of primitives in music scores,” Image and Vision Computing, 14(1), pp. 39-46, 1996.
[8] T. Hori, S. Wada, T. Howzan, S. Y. D. E. Kung and W. Bastiaan Kleijn, “Automatic music score recognition/play system based on decision based neural network,” 1999 IEEE Third Workshop on Multimedia Signal Processing, Cat. No.99TH8451, pp. 183-4, 1999.
[9] D. Blostein, and H. S. Baird, “A critical survey of music image analysis,” H. S. Baird, H. Bunke, and K. Yamamoto, editor, Structured Document Image Analysis. Springer-Verlag, 1992.
[10] K. T. Reed and J. R. Parker, “Automatic computer recognition of printed music,” Proceedings of the ICPR, pp. 803-7, 1996.
[11] E. Sicard, “An efficient method for the recognition of printed music,” Proceedings of the 11th IAPR, pp. 573-6, 1992.
[12] Y. C. Chung, "Recognition of Printed Sheet Music Using Hough Transform And Morphology Operations," Master thesis, National Taiwan Normal University, Taiwan, 1995.
[13] R. O. Duda and P. E. Hart, “Use of the Hough transform to detect lines and curves in pictures,” Commun. ACM, vol 15 No 1, pp. 11-15, 1972.
[14] F. Kimura and M. Shridha, “Handwritten numerical recognition based on multiple algorithms,” Pattern Recognition, 19(1), pp. 1-12, 1986.
[15] R. J Randriamahefa, J. P. Cocquerez, C. Fluhr, F. Pépin, and S. Philipp, “Printed music recognition,” Proceedings of ICDAR, pp. 898-901, 1993.
[16] N. P.Carter, R. A. Bacon, “Automatic Recognition of Printed Music,” In H. S. Baird, H. Bunke, and K. Yamamoto, editor, Structured Document Image Analysis. Springer-Verlag, Heidelberg, 1991.
[17] B. Modayur, “Music score recognition – a selective attention approach using mathematical morphology,” Technical Report, Electrical Engineering Department, University of Washington, Seattle, 1996.
[18] B. Couasnon, B. Rétif, “Using a grammar for a reliable full score recognition system,” Proceeding of ICMC, Ban., Canada, pp. 187–194, 1995.
[19] D. Blostein, L. Haken, “Using diagram generation software to improve diagram recognition: a case study of music notation,” IEEE Trans. on PAMI, 21(11), pp. 1121–1135, 1999.
[20] K. C. Ng and R. D. Boyle, “Recognition and reconstruction of primitives in music scores,” Image and Vision Computing, 14(1), pp. 39-46, 1996.
[21] I. Fujinaga, “Adaptive Optical Music Recognition,” Ph. D. thesis, McGill University, 1996.
[22] F. Rossant, “A global method for music symbol recognition in typeset music sheets,” Pattern Recognition Letters, 23(10), pp. 1129-41, 2002.
[23] J. Serra, “Image Analysis and Mathematical Morphology,” Academic Press, London, 1982.
[24] J. Serra, “Image Analysis and Mathematical Morphology:Theoretical Advances,” Academic Press, London, 1988.
[25] 紀華麟, “流行輕鬆彈,” 樂匠音樂出版社, p. 113, 2003.
[26] 施富然, “Old Jazz 鋼琴精選 No.1,” 卓著出版社, p. 33, 2003.
[27] Kenny G, “Spanish Nights,” p. 29, Hal Leonard, 2002.
[28] 羅炳良, “香港聲樂作品集,” 基督教文藝出版社, p. 67, 1999.
[29] H. H. Hoos, and K. A. Hamel, “The GUIDO music notation format version 1.0, Specification Part 1: Basic GUIDO,” Technical Report TI 20/97, Technische Universität Darmstadt, 1997.
[30] L. Martin, and H. H. Hoos, “gmn2midi version 1.0,” Computer Program, 1997. <http://www.informatik.tu-darmstadt.de/AFS/GUIDO/>.
[31] Neuratron Limited, “PhotoScore Demo Version,” Commerical Package, 2003. <http://www.neuratron.com/>.
[32] 紀華麟, “流行輕鬆彈,” 樂匠音樂出版社, p. 8, 2003.
[33] 紀華麟, “流行輕鬆彈,” 樂匠音樂出版社, p. 90, 2003.