Unrestricted pose-invariant face recognition by sparse dictionary matrix
作者：
Highlights：
• We have presented a method for facial expression invariant face recognition.
• We propose a novel method for real-world pose-invariant face recognition.
• Proposed method use a single image in gallery with any facial expressions.
• We generate a sparse dictionary matrix for each people based on triplet pose angles.
• Convincing results were acquired to handle pose on the FERET, CMU PIE and LFW databases.
摘要
•We have presented a method for facial expression invariant face recognition.•We propose a novel method for real-world pose-invariant face recognition.•Proposed method use a single image in gallery with any facial expressions.•We generate a sparse dictionary matrix for each people based on triplet pose angles.•Convincing results were acquired to handle pose on the FERET, CMU PIE and LFW databases.
论文关键词：Real-world,Facial expression generic elastic models,Face synthesis,Pose-invariant face recognition,Sparse representation,Sparse dictionary matrix
论文评审过程：Received 6 April 2014, Revised 16 September 2014, Accepted 19 January 2015, Available online 19 February 2015.
论文官网地址：https://doi.org/10.1016/j.imavis.2015.01.007
