• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Huang, Zhiqing (Huang, Zhiqing.) | Jia, Xiang (Jia, Xiang.) | Guo, Yifan (Guo, Yifan.) | Zhang, Jing (Zhang, Jing.)

收录:

EI CSCD

摘要:

Optical music recognition(OMR)is an important technology in music information retrieval. Note recognition is the key part of music score recognition. In view of the low accuracy of notes recognition and the cumbersome steps of the recogni-tion of music score image, an end-to-end note recognition model based on deep learning is designed. The model uses the deep convolutional neural network to input the whole score image as the input, and directly outputs the duration and pitch of the note. In data preprocessing, the music image and the corresponding tag data required for model training were obtained by parsing the MusicXML file, the label data was a vector composed of note pitch, note duration and note coordinates, therefore, the model learned the label vector through training to transform the note recognition task into detection and classification tasks. Data enhancement methods such as noise and random cropping were added to increase the diversity of data, which made the trained model more robust. In the model design, based on the darknet53 basic network and feature fusion technology, an end-to-end target detection model was designed to recognize the notes. The deep neural network darknet53 was used to extract the feature image of the music image, so that the notes on the feature map had a large enough receptive field, and then the upper layer feature map of the neural network and the feature map were spliced, and the feature fusion is completed to make the note have more obvious feature and texture, allowing the model to detect small objects such as notes. The model adopted multi-task learning, and learned the pitch and duration classification task and note coordinates task, which improved the generalization ability of the model. Finally, the model was tested on the test set generated by MuseScore. The note recognition accuracy is high, and the duration accuracy of 0.96 and the pitch accuracy of 0.98 can be achieved. © 2020, Editorial Board of Journal of Tianjin University(Science and Technology). All right reserved.

关键词:

Convolutional neural networks Deep learning Deep neural networks Feature extraction Learning systems Multilayer neural networks Multi-task learning Object detection Textures

作者机构:

  • [ 1 ] [Huang, Zhiqing]Faculty of Information Science, Beijing University of Technology, Beijing; 100022, China
  • [ 2 ] [Jia, Xiang]Faculty of Information Science, Beijing University of Technology, Beijing; 100022, China
  • [ 3 ] [Guo, Yifan]Faculty of Information Science, Beijing University of Technology, Beijing; 100022, China
  • [ 4 ] [Zhang, Jing]Faculty of Information Science, Beijing University of Technology, Beijing; 100022, China

通讯作者信息:

  • [huang, zhiqing]faculty of information science, beijing university of technology, beijing; 100022, china

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

Journal of Tianjin University Science and Technology

ISSN: 0493-2137

年份: 2020

期: 6

卷: 53

页码: 653-660

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次: 7

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 2

归属院系:

在线人数/总访问数:703/3579895
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司