Advanced Digitization for Ancient Chinese Guqin Scores Based on Mask R-CNN Algorithm

Abstract

This paper announced a novel digitization method for Chinese Guqin scores, to translate all Guqin scores from image version in books to digital version. As one of the global heritages, Guqin kept using its typical score system called Ch'in Tablature (means “reduced notation”, and pronounced as “Jian Zi Pu” in Chinese pinyin) in past over one thousand years, which was created from using typical Chinese characters. However, translating Ch'in Tablature from images to digital version was still not solved. In this paper, the world's first Ch'in Tablature character dataset was created which includes over 12,000 characters, a novel method based on Mask R-CNN algorithm was announced as well. The tests with the initial dataset showed over 95% of success rate for recognizing Ch'in Tablature characters. The technical challenges and future works are also discussed in this paper.