摘要
提出一种基于像素跟踪法获取最小包围盒的算法,分割和提取琵琶工尺谱乐谱的谱字图像,采用逆时针旋转扩展扫描的方法,寻找和建立琵琶工尺谱乐谱图像中谱字所对应的每一个像素的连通区域的最小外接矩形包围盒,根据包围盒的位置关系将属于同一谱字的包围盒进行合并,从而提取出单个谱字的完整图像。实验结果表明,该算法能有效准确地从琵琶工尺谱谱图中分割和提取出各个音乐谱字。
A new kind of algorithm which can get the minimum Bounding Boxes（BB） based on the pixel tracing method is presented, and the music score symbols in Pipa Gong-Che notation image can be cut and extracted. By means of counterclockwise rotation extension scanning, the smallest external rectangle can be labeled surrounding each pixel connected region which is the component of the music sore symbols. And then the BB which belong to the same symbols are merged depending on the position of each other. Single music score symbol is extracted. Results of experiments indicate the algorithm can cut and extract each music score symbol correctly.
出处
《计算机工程》
CAS
CSCD
北大核心
2011年第3期186-188,共3页
Computer Engineering
基金
上海大学研究生创新基金资助项目(B.16-0114-09-012)
关键词
工尺谱
字符分割
像素跟踪
逆时针旋转
包围盒
Gong-Che notation： charactcr scgmentation
pixel tracing
counterclockwisc rotation
Bounding Box（P,B）
