Research On Digitization Of Chinese Gong-che Notation

Gong-che Notation (GCN) is a type of musical notation that was developed and cultivated in East Asia, flourishing mainly in ancient China, and is a widely accepted form of musical notation in East Asia. Many traditional Chinese musical manuscripts have been written in GCN, including the Kunqu Opera script, which was proclaimed one of the Masterpieces of the Oral and Intangible Heritage of Humanity by UNESCO. This paper focuses on the possibility of digitizing GCN and GCN scores by using multidisciplinary knowledge such as Chinese traditional musicology, Western musicology from Europe, computer technology, pattern recognition and digital media technology.This paper studies the digitization of Chinese Gong-che Notation and GCN musical scores; image segmentation of GCN musical scores; pattern recognition of the notes of GCN musical scores; storage method of the information of GCN musical scores; and transmission, display and reconstruction of GCN musical scores. This paper covers the following five sections:1. It presents a metadata scheme for GCN: The scheme includes a set of 51 elements based on the Dublin Core Metadata Element Set (DCMES), and references other musical metadata schemes as well as the MAchine-Readable Cataloging(MARC) standard. In addition, the metadata scheme includes a subset of 33 elements that are not included in DCMES such as"writing form","note","preface","collector","opera type","patois","quality of manuscript"and so on.2. It presents three methods for image segmentation of GCN musical scores: The first method is a novel connected-component labeling algorithm for a binary image using DFS(Depth-first Search). The experimental results demonstrate that the average execution time of the algorithm is faster than the conventional connected-component labeling algorithm. The second method is an algorithm of Axis-aligned Bounding Box based on an object pixel's seed expansion for an image of GCN musical score without lyrics, using this method, the algorithm can extract all notes in the score. The last method is an algorithm of the projection method and the iteration smoothing for an image of GCN musical score with lyrics such as a script score of Kunqu Opera.3. It presents the method of pattern recognition for the notes of GCN musical scores by proposing an integration method of multiple classifiers based on the prior probability of each classifier, and the experimental results show that the average rate of note recognition increased over experiments using classifiers such as Bayes classifier, genetic algorithm classifier and nearest neighbor classifier.4. It presents three methods for storing information in GCN musical scores. It also presents a novel file format for GCN musical scores based on MIDI protocol and GCN, indicates the method of text storage for the musical information of GCN scores, and puts forward a conceptual and logical model of a GCN score database using the metadata scheme of GCN.5. It presents a method for displaying and reconstructing the GCN musical scores. If the Document Type Definition (DTD) document of GCN and the SVG group of a note font are defined, then the GCN score can be displayed and reconstructed using the DTD document, the SVG group of a note font and the geometric construction rules of the score of GCN.This paper has researched the digitization of Chinese traditional musical notation using an interdisciplinary approach and presented a series of methods and schemes to develop and transmit Chinese traditional music in the digital age. Digitization can help protect the proclaimed masterpieces of the oral and intangible heritage of humanity, and promote the development of Chinese traditional art and arts technology.