Multilayer perceptron for face recognition
Articles
Ričardas Toliušis
Lietuvos edukologijos universitetas
Olga Kurasova
Lietuvos edukologijos universitetas
Published 2017-12-20
https://doi.org/10.15388/LMR.B.2017.11
PDF

Keywords

artificial neural networks
multilayer perceptron
face recognition

How to Cite

Toliušis R. and Kurasova O. (2017) “Multilayer perceptron for face recognition”, Lietuvos matematikos rinkinys, 58(B), pp. 62–67. doi: 10.15388/LMR.B.2017.11.

Abstract

In this paper, an algorithm is proposed which uses facial landmarks to calculate normalized Euclidean distances between different facial parts and performs faces recognition by using Multilayer Perceptron. In order to determine the most effective model, different neural network parameters have been changed in an experimental way, such as hidden layers and the number of neurons, gradient descent optimization algorithms, error and activation functions, and different sets of distances.

PDF
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Please read the Copyright Notice in Journal Policy