Multimodal biometrics recognition based on local fusion visual features and variational Bayesian extreme learning machine

作者：

Highlights：

• A new approach for multimodal biometrics recognition is proposed.

• Local fusion visual feature has better characterization capability.

• Variational Bayesian ELM provides superior performance with full Bayesian prior.

• Variational technology solves the automatic selection problem of hidden nodes in ELM.

摘要

•A new approach for multimodal biometrics recognition is proposed.•Local fusion visual feature has better characterization capability.•Variational Bayesian ELM provides superior performance with full Bayesian prior.•Variational technology solves the automatic selection problem of hidden nodes in ELM.

论文关键词：Multimodal biometrics recognition,Local fusion visual feature,Extreme learning machine,Variational Bayesian

论文评审过程：Received 4 November 2014, Revised 4 July 2016, Accepted 5 July 2016, Available online 19 July 2016, Version of Record 28 July 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.07.009