Recognition of pen-based music notation with finite-state machines
作者：
Highlights：
• Pen-based music notation provides an ergonomic interface for music composition.
• Our approach makes use of stroke dissimilarity functions and finite-state machines.
• We are able to provide a probability for each well-formed musical sequence.
• Several decoding strategies can be applied, depending on the goal pursued.
• Results report competitive performances in all metrics and scenarios considered.
摘要
•Pen-based music notation provides an ergonomic interface for music composition.•Our approach makes use of stroke dissimilarity functions and finite-state machines.•We are able to provide a probability for each well-formed musical sequence.•Several decoding strategies can be applied, depending on the goal pursued.•Results report competitive performances in all metrics and scenarios considered.
论文关键词：Pen-based recognition,Optical music recognition,Finite-State machines
论文评审过程：Received 22 January 2016, Revised 31 August 2016, Accepted 17 October 2016, Available online 29 October 2016, Version of Record 2 January 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.10.041
