Academic Journals Database
Disseminating quality controlled scientific knowledge

Modified Incremental Linear Discriminant Analysis for Face Recognition

ADD TO MY LIST
 
Author(s): R. K. Agrawal | Ashish Chaudhary

Journal: BVICAM's International Journal of Information Technology
ISSN 0973-5658

Volume: 1;
Issue: 1;
Date: 2008;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Statistical pattern recognition | Feature extraction | Face ecognition | Linear Discriminant Analysis

ABSTRACT
Linear Discriminant analysis is a commonly used and valuableapproach for feature extraction in face recognition. In thispaper, we have proposed and investigated modified incrementalLinear Discriminant Analysis (MILDA). We have compared theperformance of proposed MILDA method against Pang et alILDA in terms of classification accuracy, execution time andmemory. It is found on the basis of experimental results withdifferent face datasets that the proposed MILDA scheme iscomputationally efficient in terms of time and memory incomparison to batch method and Pang et al method. Theexperimental results also show that the classification accuracydue to MILDA, batch method and Pang et al are in completeagreement with each other.
Affiliate Program      Why do you need a reservation system?