Face Recognition Using Face Recognition Using Laplacian faces Laplacian faces Presented by, Pulkit, Shashank, Tanuj, Shreyash FACE DETECTION FEATURE EXTRACTION FACE RECOGNITION
Jul 17, 2015
Face Recognition Using Face Recognition Using Laplacian facesLaplacian faces
Presented by,Pulkit, Shashank, Tanuj,
Shreyash
FACE DETECTION
FEATURE EXTRACTION
FACE RECOGNITION
Table of contentsTable of contents1. Introduction.
2. Objective of the project.
3. Working of the project.
4. Algorithm used.
5. Modules.
6. References.
AbstractAbstractWe propose an appearance based face
recognition method called the laplacianface approach.
Using Locality Preserving Projection (LPP), the face images are mapped into a face subspace for analysis.
Existing SystemExisting SystemPrincipal 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.
DisadvantageDisadvantageLess accuracy.
Does not deal with manifold structure.
It doesn’t deal with biometric characteristics.
Proposed System (Objective)Proposed System (Objective)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.
Working (Flow Diagram)Working (Flow Diagram)
InputDBMS
Resizing Resizing
IntermediateFace
LaplacianFace
ComposedImage
Output
SourceDBMS
Compare
Compare
Compare
Average
The AlgorithmThe Algorithm1) PCA projection.
2) Constructing the nearest-neighbor graph.
3) Choosing the weights.If node I and j are connected the
else Sij=0;
4) Eigenmap.
to compute eigenvectorSolve: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 ModulesProject ModulesRead/ 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.
Project ModulesProject ModulesImage Manipulation.
The face recognition algorithm using locality Preserving Projection (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.
Form DesignForm Design
Entering New ImageEntering New Image
Identifying ImageIdentifying Image
Match Not FoundMatch Not Found
Image Not FoundImage Not Found
ApplicationApplicationIt 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.
ConclusionConclusionOur 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.
ReferencesReferences Avinash Kaushal1, J P S Raina, A., “Face Detection using Neural Network
& Gabor Wavelet Transform”, IJCST Vol. 1, Iss ue 1, September 2013 I S S N : 0 9 7 6 - 8 4 9 1
Steve Lawrence , Lee Giles “Face Recognition: A Convolutional Neural Network Approach “ IEEE Transactions on Neural Networks, Special Issue on Neural Networks and Pattern Recognition. vol.3, no110, 2009
Parvinder S. Sandhu, Iqbaldeep Kaur, “Face Recognition Using Eigen face Coefficients and Principal Component Analysis”, International Journal of Electrical and Electronics Engineering 3:8 2009 ISSN 0978-9481
Stan Z. Li and Juwei Lu., “Face Recognition Using the Nearest Feature Line Method” , IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 10, NO. 2, MARCH 1999 pp-439-443
S. T. Gandhe, K. T. Talele, and A.G.Keskar “Face Recognition Using Contour Matching” IAENG International Journal of Computer Science, 35:2, IJCS_35_2_06
Thank YouThank You