Recent Patents on Engineering

Togay Ozbakkaloglu  
School of Civil, Environmental and Mining Engineering
The University of Adelaide
Adelaide, SA
Australia

 

Back

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.

Abstract:

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.

Order Reprints Order Eprints Rights & PermissionsPrintExport

Article Details

VOLUME: 9
ISSUE: 1
Year: 2015
Page: [29 - 36]
Pages: 8
DOI: 10.2174/2210686303666131118220632