OPTIMIZED GABOR FEATURES FOR FACIAL RECOGNITION SYSTEM

Journal Title: Scientific Bulletin, Series: Electronics and Computer Science - Year 2018, Vol 18, Issue 1

Abstract

Feature extraction is a significant process in any pattern recognition, computer vision and image processing. Among several feature extraction techniques like Fisher Linear Discriminant Analysis (FLDA), Principal Component Analysis (PCA), Elastic Bunch Graph Matching (EBGM) and Local Binary Pattern (LBP), Gabor-filters possess the ability of obtaining multi-orientation features from a facial image at several scales with the derived information being of local nature. Its optimal functionality in facial recognition is linked to its biological importance (similarity to the receptive fields of simple cells in primary visual cortex) and computational properties (optimal for calculating local spatial frequencies). Despite all the outstanding properties of Gabor-filters, this technique suffers high feature dimensionality. This paper addresses the problem of high feature dimensionality by application of Ant Colony Optimization meta-heuristic algorithm for feature selection of relevant and optimal features. Two face image databases; Olivetti Research Laboratory (ORL) Database and Locally Acquired Face Image Database (LAFI) are used to evaluate the performance of the proposed facial recognition model. The final experimental results showed better performance.

Authors and Affiliations

Taye Oladele ARO, OLUWAKEMI CHRISTIANA ABIKOYE, Amos Orenyi BAJEH

Keywords

Related Articles

SYSTEM FOR MONITORING DRONE POSITION INSIDE BUILDINGS

The constant need to monitor devices has increased in recent years to the point that devices are not only tracked outside, via GPS or similar systems, but inside too, using Internal Positioning Systems. These systems are...

AN IMPLEMENTATION OF THE GREEDY ALGORITHM FOR MULTICORE SYSTEMS

The great variety of parallel systems that appeared in the last period and use multicore chips leads inevitably to the development of applications with parallel algorithms. A multicore algorithm uses several threads in t...

REAL TIME GPS TRACKING APPLICATION FOR WINDOWS ENVIRONMENT

Real time GPS tracking application is a graphical application used to monitor a personal journey with a simple smart-phone. The software is a client-server application based on authentication. At least one first time aut...

TEACHING ARDUINO PROGRAMMING AT HIGH SCHOOL LEVEL

Developing the programming skills for the high school pupils in the Romanian educational system is mostly a theoretical issue, with very little applications to real hardware systems. This can be in some cases an issue a...

DESIGN AND IMPLEMENTATION OF A TRANSLATOR FOR CONVERTING A MINIMALIST LANGUAGE TO VHDL

This paper presents the design and implementation of a software application that performs the conversion of an algorithm, written in a high-level language, into a VHDL description of the logic circuits required for the h...

Download PDF file
  • EP ID EP362354
  • DOI -
  • Views 79
  • Downloads 0

How To Cite

Taye Oladele ARO, OLUWAKEMI CHRISTIANA ABIKOYE, Amos Orenyi BAJEH (2018). OPTIMIZED GABOR FEATURES FOR FACIAL RECOGNITION SYSTEM. Scientific Bulletin, Series: Electronics and Computer Science, 18(1), 15-26. https://europub.co.uk/articles/-A-362354