An online writer identification system using regression-based feature normalization and codebook descriptors
作者：
Highlights：
• Adaptation of the VLAD framework to online writer identification.
• Addressal of a potential drawback with the VLAD framework.
• Proposal of a novel descriptor that alleviates the drawback of the VLAD.
• A feature normalization method that enhances the writer identification performance.
• Proposal tested on IAM and IBM UB 1 Online Handwriting Databases.
摘要
•Adaptation of the VLAD framework to online writer identification.•Addressal of a potential drawback with the VLAD framework.•Proposal of a novel descriptor that alleviates the drawback of the VLAD.•A feature normalization method that enhances the writer identification performance.•Proposal tested on IAM and IBM UB 1 Online Handwriting Databases.
论文关键词：Online writer identification,Codebook descriptors,Feature normalization,IAM Online Handwriting Database,IBM UB1 database
论文评审过程：Received 20 September 2016, Revised 22 November 2016, Accepted 29 November 2016, Available online 15 December 2016, Version of Record 29 December 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.11.038
