Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns
作者：
Highlights：
• We reduce the dimension of local Gabor features into Spiking Neuron Patterns (SNP).
• The reduced Gabor features called LGFV//LN//SNP are classified using soft kNN classifier.
• SNP does not require projection vector and is more efficient than the original representation.
• SNP improves the face recognition accuracy of local Gabor features.
• The results show that our method is robust against numerous forms of variations.
摘要
•We reduce the dimension of local Gabor features into Spiking Neuron Patterns (SNP).•The reduced Gabor features called LGFV//LN//SNP are classified using soft kNN classifier.•SNP does not require projection vector and is more efficient than the original representation.•SNP improves the face recognition accuracy of local Gabor features.•The results show that our method is robust against numerous forms of variations.
论文关键词：Gabor Wavelets,Feature representation,Face recognition,Spiking neurons,Dimensionality reduction
论文评审过程：Received 14 February 2015, Revised 15 August 2015, Accepted 25 November 2015, Available online 3 December 2015, Version of Record 8 February 2016.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.11.020
