Scribd
Upload
522 views24 pages

Face Recognition Using Laplacian Faces

This document proposes a face recognition method called Laplacianfaces that uses Locality Preserving Projections (LPP) to map face images into a subspace for analysis. It summarizes that existing methods like PCA have disadvantages like being inaccurate and not preserving the manifold structure of data. The proposed Laplacianfaces method overcomes these issues by using LPP, which learns a locality preserving subspace. The document describes the Laplacianfaces algorithm and provides experimental results on several databases that show it achieves better recognition accuracy than other methods.

Uploaded by

aditya_kumar_me
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
522 views24 pages

Face Recognition Using Laplacian Faces

This document proposes a face recognition method called Laplacianfaces that uses Locality Preserving Projections (LPP) to map face images into a subspace for analysis. It summarizes that existing methods like PCA have disadvantages like being inaccurate and not preserving the manifold structure of data. The proposed Laplacianfaces method overcomes these issues by using LPP, which learns a locality preserving subspace. The document describes the Laplacianfaces algorithm and provides experimental results on several databases that show it achieves better recognition accuracy than other methods.

Uploaded by

aditya_kumar_me
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 24

Face Recognition Using Laplacianfaces

Project Work By
J.Thiru kumaran.
M.Umamaheshwaran.

Guide By
Miss.N.Vasuki, M.E.,
Abstract

 We propose an appearance-based face


recognition method called the
Laplacianface approach.

 Using Locality Preserving Projections


(LPP), the face images are mapped into a
face subspace for analysis.
Existing System

 Principal Component Analysis (PCA) and Linear


Discriminant Analysis (LDA).

 PCA is to reduce the large dimensionality of the


data space to the smaller intrinsic dimensionality
of feature space.

 The jobs of PCA are prediction, redundancy


removal, feature extraction, data compression,
etc.
Disadvantages

 Less accurate.

 Does not deal with manifold structure.

 It doest not deal with biometric characteristics.


Proposed System
 Locality Preserving Projection (LPP), a new algorithm
for learning a locality preserving subspace.

 LPP is a general method for manifold learning.

 The difficulty that the matrix XDXT is Sometimes


singular.

 To overcome the complication of a singular XDXT ,


we first project the image set to a PCA subspace so
that the resulting matrix XDXT is nonsingular.
The Algorithm

1)PCA projection.

2)Constructing the nearest-neighbor graph.

3)Choosing the weights.

if node i and j are connected then

else
Sij=0;
4)Eigenmap.
To compute eigenvector
Solve:
Gives: w0;w1; . . . ;wk_1

5)Calculate Laplacianface:
W=Wpca Wlpp;
Where,
Wlpp=[w0;w1; . . . ;wk_1] ;
Wpca=Transformation matrix of PCA;
W=Transformation matrix of Laplacianface.
Project Modules

 Read/Write Module.
The image files are read, processed and new
images are written into the output images.

 Resizing Module.
In this module large images or smaller images are
converted into standard sizing.
 Image Manipulation.
The face recognition algorithm using
Locality Preserving Projections (LPP) is developed for
various enrolled into the database.

 Testing Module.
The Intermediate image and find the tested
image then again compared with the laplacian faces
Design Flow Diagram
Experimental Results

 Yale Database.

 PIE Database.

 MSRA Database.
Yale Database
 Constructed at the Yale Center for Computational
Vision and Control.

 It contains 165 grayscale images of 15


individuals.

 The images demonstrate variations in lighting


condition,facial expression, and with/without
glasses.
Performance Comparison on the Yale Database
PIE Database
 In PIE Database, the error rate of our
Laplacianfaces method decreases fast as the
dimensionality of the face subspace.

 Table shows the recognition results.


Performance Comparison on the PIE Database
MSRA Database
 This database was collected at Microsoft Research
Asia.

 Sixty-four to eighty face images were collected


for each individual in each session.

 Table shows the Laplacian faces method has


lower error rate than those of Eigen faces and
fisher faces.
Performance Comparison on the MSRA Database
Form Design
Entering New Image
Identifying Images
Image Not Found
Application
 It could benefit the visually impaired person.

 A computer vision-based authentication system


could be put in place to allow computer access.

 Access to a specific room using face recognition.


Conclusion
 Our system is proposed to use Locality Preserving
Projection in Face Recognition which eliminates
the flaws in the existing system.

 This system makes the faces to reduce into lower


dimensions and algorithm for LPP is performed for
recognition.
THANK YOU………

You might also like