GMM posterior features for improving online handwriting recognition

作者：

Highlights：

• Proposal of GMM posterior (GP) features for online handwriting recognition.

• The features include inter-class variability and minimize intra-class variability.

• Development of character/word recognition system using GP features in SVM framework.

• Proposal tested on Assamese digit, UNIPEN Character & UNIPEN ICROW-03 word database.

摘要

•Proposal of GMM posterior (GP) features for online handwriting recognition.•The features include inter-class variability and minimize intra-class variability.•Development of character/word recognition system using GP features in SVM framework.•Proposal tested on Assamese digit, UNIPEN Character & UNIPEN ICROW-03 word database.

论文关键词：Character/word recognition,Assamese database,UNIPEN database,SVM

论文评审过程：Received 6 August 2017, Revised 2 December 2017, Accepted 28 December 2017, Available online 29 December 2017, Version of Record 9 January 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.12.047