Using a Discrete Hidden Markov Model Kernel for lip-based biometric identification

作者：

Highlights：

• We model a lip biometric approach based on shape information.

• This system is working with static lip on three public datasets.

• We develop a kernel based Hidden Markov Model (DHMMK).

• The use of DHMMK obtains discriminative information.

• The use of DHMMK on lip gets a robust approach for identification.

摘要

•We model a lip biometric approach based on shape information.•This system is working with static lip on three public datasets.•We develop a kernel based Hidden Markov Model (DHMMK).•The use of DHMMK obtains discriminative information.•The use of DHMMK on lip gets a robust approach for identification.

论文关键词：Discrete Hidden Markov Model Kernel,Image processing,Lip-based biometrics,Pattern recognition

论文评审过程：Received 17 October 2013, Revised 31 May 2014, Accepted 2 October 2014, Available online 22 October 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.10.001