Different Approaches for Face Authentication as Part of a Multimodal Biometrics System

This paper describes different approaches for the face authentication from the features and classification abilities point of view. Authors compare two types of features - Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) including their combination. These parameters are classifi...

Full description

Saved in:
Bibliographic Details
Published inAdvances in electrical and electronic engineering Vol. 16; no. 1; pp. 118 - 124
Main Authors Tovarek, Jaromir, Voznak, Miroslav, Rozhon, Jan, Rezac, Filip, Safarik, Jakub, Partila, Pavol
Format Journal Article
LanguageEnglish
Published Ostrava Faculty of Electrical Engineering and Computer Science VSB - Technical University of Ostrava 01.03.2018
VSB-Technical University of Ostrava
Subjects
Biometrics
Classifiers
Conditional probability
Error detection
face authentication
Face recognition
Feature extraction
hog
lbp
mlnn
Neural networks
Parameters
Rejection rate
Support vector machines
svm
Online AccessGet full text

Cover

More Information
Summary:This paper describes different approaches for the face authentication from the features and classification abilities point of view. Authors compare two types of features - Histogram of Oriented Gradients (HOG) and Local Binary Patterns (LBP) including their combination. These parameters are classified using Multilayer Neural Network (MLNN) and Support Vector Machines (SVM). Face authentication consists of several steps. The first step contains Viola-Jones algorithm for face detection. Authors resize the detected face for a fixed vector and afterwards, it is converted into grayscale. Next, feature extraction with a simple Min-Max normalization is applied. Obtained parameters are evaluated by classifiers and for each detected face, authors get posterior probability as the output of the classifier. Different approaches for face authentication are compared with each other using False Acceptance Rate (FAR), False Rejection Rate (FRR), Equal Error Rate (EER), Receiver Operating Characteristic (ROC) and Detection Error Tradeoff (DET) curves. The results are verified with AR Face Database and elaborated in a feature extraction and classifier design point of view. Best results were achieved by HOG feature for SVM classifier. Detailed results are listed in the text below.
ISSN:1336-1376
1804-3119
DOI:10.15598/aeee.v16i1.2547