Used SVD-Based Face Recognition for Windows?


Editors’ Review

Download.com staff
This Matlab source code builds a face recognition system using SVD. It offers projection-based face retrieval with efficient memory usage and a high accuracy rate on gray scale images.
  • Pros

    • Efficient memory usage for storing face features
    • Achieves a 97.5% recognition rate on test data
    • Provided as implementable Matlab source code
    • Implements an SVD-based face retrieval algorithm
    • Validated on the standard ORL face database
  • Cons

    • Requires a Matlab environment to run the code
    • Designed for static gray scale images
    • Recognition rate specified for a single database
    • Does not mention support for color images
    • Provided as source code, not a packaged application

Used SVD-Based Face Recognition for Windows?


Explore More


Full Specifications

GENERAL
Release
Latest update
Version
1.0
OPERATING SYSTEMS
Platform
Windows
Operating System
  • Windows NT
  • Windows Server
  • Windows 98
  • Windows 7
  • Windows 8
  • Windows XP
  • Windows ME
  • Windows 10
  • Windows 2003
  • Windows Vista
  • Windows 2000
Additional Requirements
Matlab
POPULARITY
Total Downloads
129
Downloads Last Week
1

Report Software

Last Updated


Developer’s Description

Use Matlab source code to set up SVD-based face recognition system.
Projection-based face recognition has been widely studied during the past two decades. One of the problems is to require a huge storage space to save the face features obtained from training faces. We propose an SVD-based face retrieval system which requires less memory than the PCA, 2DPCA, Fisher, and 2DFisher approaches. The algorithm tested on the famous ORL (AT&T) face database, consisted of 400 112 x 92 gray level face images equally contributed by 40 subjects, achieves 97.5% recognition rate of retrievals.

Download.com
Your review for SVD-Based Face Recognition