Non Linear Fusion of Colors to Face Authentication using LDA

Journal Title: Annals. Computer Science Series - Year 2018, Vol 16, Issue 1

Abstract

In this article, we propose the use of information color to authenticate face; several spaces of colors were used for the transformation of colorimetric components RGB of the original images. The results obtained in different spaces/or component colorimetric are combined by the use of a nonlinear fusion with a simple neuron network type MLP (Multi layer perceptron). We applied the method of linear discriminant analysis (LDA) to extract the characteristic vector of the face image. To validate this work we tested this approach on frontal images of the data base XM2VTS according to its associated protocol (protocol of Lausanne).

Authors and Affiliations

Meriem FEDIAS, Djamel SAIGAA, Mohammed Souri MIMOUNE, Mohamed BOUMEHRAZ

Keywords

Related Articles

Multimedia Application for Solving a Sudoku Game<br /> <br />

This article explains the way in which, with the help of Action Script 3 in combination with Flash, a method of solving Sudoku game was implemented, through searching for the certain numbers and after that trying to gues...

Analytic Approach To Face Emotion Recognition With SVM Kernels

Face emotion recognition is one of the challenges known with emotion recognition and it has received much attention during the recent years due to its application in different fields. SVM kernels were adopted to increase...

Quadratic Regression and Factorial Analysis on the Effect of Climatic Elements on Global Food Production and Land Nutrients in Africa

The United Nation has its number one Sustainable Development Goal (SDG #1) of No Poverty Global World which is, Agriculture and Food Security. The question to be asked is how do we make production of food like maize, ric...

Mathematical Models in Danube Water Quality

The mathematical shaping in the study of water quality has become a branch of environmental engineering. The comprehension and effective application of mathematical models in studying environmental phenomena keep up with...

XML Technologies in Computer Assisted Learning and Testing Systems

The learning and assessment activities have undergone major changes due to the development of modern technologies. The computer-assisted learning and testing has proven a number of advantages in the development of modern...

Download PDF file
  • EP ID EP521552
  • DOI -
  • Views 121
  • Downloads 0

How To Cite

Meriem FEDIAS, Djamel SAIGAA, Mohammed Souri MIMOUNE, Mohamed BOUMEHRAZ (2018). Non Linear Fusion of Colors to Face Authentication using LDA. Annals. Computer Science Series, 16(1), 71-75. https://europub.co.uk./articles/-A-521552