Abstract

Developing a robust system for face recognition is a challenge in the field of Computer Vision. Texture is one of low-level visual features that mostly used to represent a unique characteristic of an image in face recognition. In this study, a face recognition system is implemented using two well-known texture extraction methods, i.e., wavelet and Local Binary Pattern (LBP). The texture features of face image are then classified using multilayer Perceptron. The face dataset used in experiment consists of 2260 images from 113 people. The experiment is carried out by comparing the performance of the two texture extraction methods. Both methods achieve high accuracy in recognizing face images. The recognition rates achieved by the wavelet and LBP methods are 99.63 and 93.19%, respectively.

Original languageEnglish
Title of host publicationLecture Notes in Networks and Systems
PublisherSpringer
Pages225-235
Number of pages11
DOIs
Publication statusPublished - 2019

Publication series

NameLecture Notes in Networks and Systems
Volume67
ISSN (Print)2367-3370
ISSN (Electronic)2367-3389

Keywords

  • Face recognition
  • Local binary pattern
  • Multilayer perceptron
  • Wavelet

Fingerprint

Dive into the research topics of 'Face recognition using texture features and multilayer perceptron'. Together they form a unique fingerprint.

Cite this