LEDTD: Local edge direction and texture descriptor for face recognition

作者：

Highlights：

• A new image descriptor LEDTD is presented for face recognition.

• LEDTD is the occurrence of local image center pixel edge direction and the texture information.

• WPCA is introduced to reduce the feature dimension and improve recognition performance.

• Experimental results on four databases demonstrate the superiority of our LEDTD compared with other image representation approaches.

摘要

Highlights•A new image descriptor LEDTD is presented for face recognition.•LEDTD is the occurrence of local image center pixel edge direction and the texture information.•WPCA is introduced to reduce the feature dimension and improve recognition performance.•Experimental results on four databases demonstrate the superiority of our LEDTD compared with other image representation approaches.

论文关键词：Face recognition,Local binary pattern,Kirsch mask,Local edge direction,Image texture feature

论文评审过程：Received 22 June 2015, Revised 2 October 2015, Accepted 7 December 2015, Available online 17 December 2015, Version of Record 23 December 2015.

论文官网地址：https://doi.org/10.1016/j.image.2015.12.003