claVision: visual automatic piano music transcription

Thumbnail Image
Akbari, Mohammad
Journal Title
Journal ISSN
Volume Title
Lethbridge, Alta. : University of Lethbridge, Dept. of Mathematics and Computer Science
One significant problem in the science of Musical Information Retrieval is Automatic Music Transcription, which is an automated conversion process from played music to a symbolic notation such as sheet music. Since the accuracy of previous audio-based transcription systems is not satisfactory, an innovative visual-based automatic music transcription system named claVision is proposed to perform piano music transcription. Instead of processing the music audio, the system performs the transcription only from the video performance captured by a camera mounted over the piano keyboard. claVision can be used as a transcription tool, but it also has other applications such as music education. The software has a very high accuracy (over 95%) and a very low latency (less than 6.6 ms) in real-time music transcription, even under different illumination conditions. This technology can also be used for other musical keyboard instruments. claVision is the winner of the 2014 Microsoft Imagine Cup Competition in the category of innovation in both Canadian national finals and world semifinals. As one of the top 11 teams in the world, claVision advanced to World Finals in Seattle to be demonstrated at the University of Washington, Microsoft headquarters, and the Museum of History & Industry.
claVision , automatic music transcription , piano , computer vision