PCA Based Face Recognition System Using ORL Database

This Package implements 'Eigenface' PCA based face recognition technique.

This package implements a well-known PCA-based face recognition method, which is called 'Eigenface'.

The program is easy to use. Furthermore, a sample Project file demo_PCA.m' is added that demonstrate how to use, ORL training and test database is also included to show Performance comparison for execution time and Recognition percentage, on different size of testing and training dataset by picking images randomly.

Additional file LOOCV.m for LOOCV (Leave One Out Cross Validation) Test.

Additional file Comparision.m for Comparision of PCA with mean,mode and median modifications.

Additional file PRR.m is added in the Sub Functions for calculating Precision and Recall of individual class.

for better understanding of PCA and the Tests involved you can use the tutorials given : http://www.cs.otago.ac.nz/cosc453/student_tutorials/principal_components.pdf

http://www.creighton.edu/fileadmin/user/HSL/docs/ref/Searching_-_Recall_Precision.pdf

ORL Dataset Description and source

Introduced by Ferdinand Samaria et al. in Parameterisation of a stochastic model for human face identification

The ORL Database of Faces contains 400 images from 40 distinct subjects. The size of each image is 92x112 pixels, with 256 grey levels per pixel.Source: https://cam-orl.co.uk/facedatabase.html