Study on MACE Gabor Filters, Gabor Wavelets, DCT-Neural Network, Hybrid Spatial Feature Interdependence Matrix, Fusion Techniques for Face Recognition

Author(s): Steven L. Fernandes, Josemin G. Bala.

Journal Name: Recent Patents on Engineering

Volume 9 , Issue 1 , 2015

Become EABM
Become Reviewer


In this paper we have developed and analyzed Minimum Average Correlation Energy Gabor Filters (MACE GF), Gabor Wavelets (GW), Discrete Cosine Transform Neural Network (DCT NN), Hybrid Spatial Feature Interdependence Matrix (HSFIM), Score Level Fusion Techniques (SLFT) for Face Recognition in the presence of various noises and blurring effects. All the 5 systems were trained in the absence of noise, blurring effect but tested by imposing different levels of noises and blurring effects. To compare the performance of MACE GF, GW, DCT NN, HSFIM, and SLFT six public face databases: IITK, ATT, JAFEE, CALTECH, GRIMACE, and SHEFFIELD are considered. Patents analyzed are “Gabor filtering and joint sparsity model-based face recognition method” “Gabor human face recognizing method based on simplified intelligent single-particle optimizing algorithm.

Keywords: Minimum average correlation energy, gabor filter, gabor wavelets, discrete cosine transform, neural network, hybrid spatial feature interdependence matrix.

Rights & PermissionsPrintExport Cite as

Article Details

Year: 2015
Page: [29 - 36]
Pages: 8
DOI: 10.2174/2210686303666131118220632

Article Metrics

PDF: 17