电子学报 ›› 2021, Vol. 49 ›› Issue (4): 716-728.DOI: 10.12263/DZXB.20200209

• 学术论文 • 上一篇    下一篇

纸质简谱图像的分割、倾斜校正及音符歌词提取

邓翔宇, 杨雅涵   

  1. 西北师范大学物理与电子工程学院, 甘肃兰州 730070
  • 收稿日期:2020-02-26 修回日期:2020-07-29 出版日期:2021-04-25 发布日期:2021-04-25
  • 通讯作者: 邓翔宇
  • 作者简介:杨雅涵 女,1997年3月出生,甘肃兰州人.现为西北师范大学电子信息专业硕士研究生.主要研究领域为人工神经网络及其在图像处理中的应用.E-mail:yangyh111@126.com
  • 基金资助:
    国家自然科学基金(No.61961037);西北师范大学研究生培养与课程改革项目

Segmentation,Tilt Correction and Note Lyrics Extraction of Paper Numbered Musical Notation Images

DENG Xiang-yu, YANG Ya-han   

  1. College of Physics and Electronic Engineering, Northwest Normal University, Lanzhou, Gansu 730070, China
  • Received:2020-02-26 Revised:2020-07-29 Online:2021-04-25 Published:2021-04-25

摘要: 乐谱图像的自动分割、倾斜校正是乐谱识别过程中的关键技术,各种计算机光学乐谱识别技术在乐谱图像的数字化中有着广泛的应用,但对于乐谱中简谱的识别一直鲜有研究.本文针对人工拍摄条件下光照不理想的简谱图像,提出一种基于PCNN(脉冲耦合神经网络)和DNN(深度神经网络)相结合的分块简谱图像自动分割算法,该方法根据简谱图像灰度分布特征对图像进行自适应分块处理,依据每个分块的灰度特征与PCNN最佳迭代次数之间的关系构造合适的DNN神经网络,从而实现了最优分割图的自适应选取;进一步利用最优分割图像中音符小节线的水平投影,提出一种双尺度下降法实现了简谱图像的倾斜校正;提出去边垂直投影法和连通域距离判断法实现了简谱图像中音符及歌词的提取.实验仿真结果表明:本文算法对复杂光照条件下的简谱图像处理都具有较好的鲁棒性,同时表现出更高的效率.

关键词: PCNN分块分割, DNN最优选择, 双尺度下降, 倾斜校正, 去边垂直投影, 音词符提取

Abstract: Automatic segmentation and tilt correction of music images are key techniques in music recognition.Various computer optical music score recognition technologies have been widely used in the digitization of music score images,but there has been little research on the recognition of numbered musical notation.In this paper,an automatic image segmentation algorithm based on PCNN(Pulse Coupled Neural Networks) and DNN(Deep Neural Networks) is proposed to solve the problem of a variety of lighting conditions.The image is processed by adaptive block processing according to the gray scale distribution of the spectral image and analyze the relationship between the gray scale characteristics of each block and the optimal PCNN iteration time,construct an appropriate DNN neural network to realize the adaptive selection of optimal segmentation graph.Further using the horizontal projection of bar lines,we propose a dual-scale descent method to realize the skew correction of numbered musical notation image.We propose an edgeless vertical projection method and connected domain distance judgment method to extract the note and lyrics from numbered musical notation image.Simulation experiments show that the proposed algorithm exibits better robustness for numbered musical notation image under complex illumination conditions and faster speed.

Key words: PCNN block segmentation, DNN optimal selection, double scale descent, tilt correction, removable edges vertical projection, extraction of notes and lyrics

中图分类号: