Recognizing faces with normalized local Gabor features and Spiking Neuron Patterns. (May 2016)

• Record Type: Journal Article
• Authors: Kamaruzaman, Fadhlan; Shafie, Amir Akramin
• Is Part Of: Pattern recognition. Volume 53(2016:May)
• Page Start: 102
• Page End: 115
• Publication Date: 2016-05
• Subjects: Gabor Wavelets -- Feature representation -- Face recognition -- Spiking neurons -- Dimensionality reduction; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2015.11.020
• Languages: English
• ISSNs: 0031-3203

Abstract

Abstract: Gabor Wavelets (GW) have been extensively used for facial feature representation due to its inherent multi-resolution and multi-orientation characteristics. In this work we extend the work on Local Gabor Feature Vector (LGFV) and propose a new face recognition method called LGFV//LN//SNP, which employs local normalization filter in pre-processing stage. We propose a novel Spiking Neuron Patterns (SNP) as a dimensionality reduction method to reduce the dimensions of local Gabor features. SNP is acquired from projection of LGFV//LN features using Spike Response Model (SRM), a neuron model describing the spike behavior of a biological neuron. Results on AR, FERET, Yale B and FRGC 2.0 face datasets showed that SNP implementation delivered significant improvement in accuracy. Comparisons with several previously published results also suggested that LGFV//LN//SNP achieved better results in some tests. Additionally, LGFV//LN//SNP requires relatively smaller number of GW than LGFV//LN to produce optimal results. Graphical abstract: 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.