A novel face recognition method using PCA, LDA and support vector machine

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Here an efficient and novel approach was considered as a combination of PCA, LDA and support vector machine. This method consists of three steps: I) dimension reduction using PCA, ii) feature extraction using LDA, iii) classification using SVM. Combination of PCA and LDA is used for improving the capability of LDA when new samples of images are available and SVM is used to reduce misclassification caused by not linearly separable classes.

Original languageEnglish
Title of host publicationAdvances in Computer Science and Information Technology
Subtitle of host publicationComputer Science and Engineering - Second International Conference, CCSIT 2012, Proceedings
Pages241-249
Number of pages9
Volume85
EditionPART 2
DOIs
Publication statusPublished - 2012
Event2nd International Conference on Computer Science and Information Technology, CCSIT 2012 - Bangalore, India
Duration: 02-01-201204-01-2012

Publication series

NameLecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
NumberPART 2
Volume85
ISSN (Print)1867-8211

Conference

Conference2nd International Conference on Computer Science and Information Technology, CCSIT 2012
Country/TerritoryIndia
CityBangalore
Period02-01-1204-01-12

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'A novel face recognition method using PCA, LDA and support vector machine'. Together they form a unique fingerprint.

Cite this