Face Recognization

65
A PROJECT REPORT ON FACE RECOGNIZATION. 1

Transcript of Face Recognization

Page 1: Face Recognization

A

PROJECT REPORT

ON

FACE RECOGNIZATION.

1

Page 2: Face Recognization

TABLE OF CONTENT

CHAPTER NO. TITLE

ABSTRACT

LIST OF TABLES

LIST OF ABREVATIONS

1. INTODUCTION

1.1 Problem Definition

System Environment

2. SYSTEM ANALYSIS

2.1 Existing System

2.1.1 Principle Component Analysis

2.1.2 Linear Discriminant Analysis (LDA) 2.2 Proposed System

2.3 System Requirement

2.4 System Analysis Method

2.5 Feasibility Study

2.5.1 Technical Analysis

2.5.2 Economic Analysis

2.5.3 Performance Analysis

2

Page 3: Face Recognization

2.5.4 Efficiency Analysis

3. SYSTEM DESIGN

3.1 Project Module.

3.1.1 Read\Write Module.

3.1.2 Resizing Module.

3.1.3 Image Manipulation

3.1.4 Testing Module.

3.2 System Development

4. IMPLEMENTATION

4.1 Implementation Details

4.2 Coding

4.2.1 Form Design

4.2.2 Input Design

4.2.3 Menu Design

4.2.4 Database Design

4.2.5 Code Design

5. SYSTEM TESTING

5.1 Software Testing

5.2 Efficiency of Laplacian Algorithm

5.2.1. Experimental Result

5.2.2 Face Recognition Using

Laplacianfaces

3

Page 4: Face Recognization

5.2.3 Yale Database

5.2.4 PIE Database

5.2.5 MSRA Database

6. CONCLUSION

8 SNOPSHOT

9 REFERENCES

4

Page 5: Face Recognization

ABSTRACT

We propose an appearance-based face recognition method called the Laplacianface

approach. By using Locality Preserving Projections (LPP), the face images are mapped into a face

subspace for analysis. Different from Principal Component Analysis (PCA) and Linear Discriminate

Analysis (LDA) which effectively see only the Euclidean structure of face space, LPP finds an embedding

that preserves local information, and obtains a face subspace that best detects the essential face manifold

structure.

The Laplacianfaces are the optimal linear approximations to the eigen functions of the

Laplace Beltrami operator on the face manifold. In this way, the unwanted variations resulting from

changes in lighting, facial expression, and pose may be eliminated or reduced. Theoretical analysis shows

that PCA, LDA, and LPP can obtained from different graph models. We compare the proposed

Laplacianface approach with Eigen face and Fisher face methods on three different face data sets.

Experimental results suggest that the proposed Laplacianface approach provides a better representation

and achieves lower error rates in face recognition.

5

Page 6: Face Recognization

LIST OF TABLES

TABLE NO TITLE

1 Performance Comparison on the

Yale Database

2 Performance Comparison on the

PIE Database

3 Performance Comparison on the

MSRA Database

6

Page 7: Face Recognization

LIST OF FIGURES

FIGURE NO CAPTION

1 Designing Flow Diagram

2 Laplacian Images

3 Reduced Representation of Laplacian Images

4 Eigen Value of LPP

5 Images in Yale Database

6 Original and Cropped Image Image in Yale Database.

7 Error Rate Versus Dimensionality Reduction.

8 Face Images in PIE Database

9 Face Images in MISRA Database

7

Page 8: Face Recognization

LIST OF ABBREVIATIONS

PCA : Principle Component Analysis

LDA : Linear Discriminant Analysis

LLP : Locality Preserving Projections

FRR : False Rejection Rate

FAR : False Acceptance Rate

8

Page 9: Face Recognization

CHAPTER-1

INTRODUCTION

A smart environment is one that is able to identify people, interpret their actions, and react appropriately. Thus, one of the most important building blocks of smart environments is a person identification system. Face recognition devices are ideal for such systems, since they have recently become fast, cheap, unobtrusive, and, when combined with voice-recognition, are very robust against changes in the environment. Moreover, since humans primarily recognize each other by their faces and voices, they sense relaxed interact with an situation that does the same.

Facial recognition system is built on CPU program that analyze images of human faces for the purpose of identifying them. The programs take a facial image, measure characteristics such as the distance between the eyes, the length of the nose, and the angle of the jaw, and generate a single file called a "template." Using templates, the software then compares that image with another image and produce a score that actions how like the images are to each other. Typical sources of images for use in facial recognition include video camera signals and pre-existing photos such as those in driver's license databases.

Facial identification system is computer-based refuge system that are able to automatically detect and identify human faces. These systems depend on a gratitude algorithm, such as eigenface or the hidden Markov model. The first step for a facial recognition system is to recognize human features and remove it for the rest of the scene. Next, the system measures nodal points on the face, such as the reserve linking the eye, the figure of the cheekbones and other distinguishable features.

These nodal points are then compared to the nodal points computed from a folder of movies in order to locate a match. Obviously, such a system is incomplete base on the position of the face captured and the lighting conditions present. New technologies are currently in development to create three-dimensional models of a person's face based on a digital photograph in order to create more nodal points for comparison. However, such technology is inherently susceptible to error given that the computer is extrapolating a three-dimensional model from a two-dimensional photograph.

Principle module study is an eigenvector method calculated to model linear variation in high-dimensional data. PCA performs dimensionality reduction by projecting the

Original n-dimensional data onto the k << n -dimensional linear subspace spanned by the leading eigenvectors of the data’s covariance matrix. Its goal is to find a set of mutually orthogonal basis function that arrest the information of most variance in the data and for which the coefficients are pair wise decorrelated. For linearly fixed manifolds, PCA is sure to discover the dimensionality of the manifold and produces a compact representation.

9

Page 10: Face Recognization

Facial Recognition Applications:

Facial recognition is deployed in large-scale citizen recognition application, observation application, law enforcement applications such as booking stations, and kiosks.

10

Page 11: Face Recognization

1.1 Problem Definition

Facial recognition systems are computer-based security systems that are able to automatically detect and identify human faces. These systems depend on a recognition algorithm. But the good number of the algorithm consider some what global data patterns while recognition process. This will not yield accurate recognition system. So we offer a face recognition scheme which can able to recognition with maximum accuracy as possible.

1.2 System Environment

The front end is designed and executed with the J2SDK1.4.0 usage the core java part with User boundary Swing module. Java is robust , object oriented , multi-threaded , distributed , secure and platform independent language. It has wide variety of package to implement our requirement and number of classes and methods can be utilized for programming purpose. These features make the programmer’s to implement to require concept and algorithm very easier way in Java.

The features of Java as follows:

Core java contains the concepts like Exception handling, Multithreading; Streams can be well utilized in the project environment.

The Exception handling can be done with predefined exception and has provision for writing custom exception for our application.

Garbage collection is done automatically, so that it is very secure in memory management.

The user interface can be done with the Abstract Window tool KitAnd also Swing class. This has variety of classes for components and containers. We can make instance of these classes and this instances denotes particular object that can be utilized in our program.

Event handling can be performed with Delegate Event model. The objects are assigned to the Listener that observe for event, when the event takes place the corresponding methods to handle that event will be called by Listener which is in the form of interfaces and executed.

11

Page 12: Face Recognization

This application makes use of Action Listener interface and the event click event gets handled by this. The separate method actionPerformed () method contains details about the response of even Java also contains concepts like Remote method invocation; Networking can be useful in distributed environment.

12

Page 13: Face Recognization

CHAPTER-2

SYSYTEM ANALYSIS

2.1 Existing System:

Many face recognition techniques have been developed over the past few decades. One of the most successful and well-studied techniques to face recognition is the appearance-based method. When using appearance-based methods, we usually represent an image of size n *m pixels by a vector in an n *m-dimensional space. In practice, however, these n*m dimensional spaces are too large to allow robust and fast face recognition. A common method to effort to decide this problem is to use dimensionality reduction techniques.

Two of the most popular techniques for this purpose are,2.1.1 Principal Component Analysis (PCA). 2.1.2 Linear Discriminant Analysis (LDA).

2.1.1 Principal Component Analysis (PCA):

The purpose of PCA is to reduce the large dimensionality of the data space (observed variables) to the smaller essential dimensionality of quality gap (self-regulating variables), which are needed to describe the data economically. This is the box when there is a tough association between observed variables. The job which PCA can do is prediction, job loss removal, feature extraction, data compression, etc. Because PCA is a known powerful technique which can do something in the linear domain, applications having linear models are suitable, such as signal giving out, figure meting out, system and organize theory, connections, etc.

The main idea of using PCA for face recognition is to express the large 1-D vector of pixels constructed from 2-D face image into the compact principal components of the feature space. This is called eigenspace ridge. Eigenspace is considered by identify the eigenvectors of the covariance medium derived from a set of fingerprint images (vectors).

2.1.2 Linear Discriminant Analysis (LDA):

LDA is a supervised learning algorithm. LDA searches for the project axes on which the data points of different classes are far from each other while requiring data point of the similar group to be close to each other. Unlike PCA which encodes information in an orthogonal

13

Page 14: Face Recognization

linear space, LDA encodes sharp in order in a linearly divisible space using bases that are not essentially orthogonal. It is generally believed that algorithms based on LDA are superior to those based on PCA.

But the nearly all of the algorithm consider some what universal data patterns while recognition process. This will not defer correct detection system.

Less accurate

Does not deal with manifold structure

It doest not deal with biometric characteristics.

2.2 Proposed System:

PCA and LDA aim to preserve the global structure. However, in many real-world applications, the local organization is more important. In this piece, we explain Locality Preserving shelf (LPP), a new algorithm for learning a locality preserving subspace.

The objective function of LPP is as follows,

The manifold structure is modeled by a nearest-neighbor graph which preserves the local structure of the image space. A face subspace is obtain by Locality preserve projection (LPP).Each face image in the image space is mapped to a low-dimensional face subspace, which is characterized by a set of feature images, called Laplacianfaces. The face subspace preserves local structure and seems to have more discriminating power than the PCA approach for classification purpose. We also provide

Theoretical analysis to show that PCA, LDA, and LPP can be obtained from different graph models. Central to this is a graph structure that is inferred on the data points. LPP finds a projection that respects this graph structure. In our the theoretical analysis, we show how PCA, LDA, and LPP happen from the same code applied to dissimilar choices of this graph structure.

It is worth while to highlight several aspects of the proposed approach here:

14

Page 15: Face Recognization

1. While the Eigenfaces method aims to preserve the global structure of the image freedom, and the Fisher faces way aims to preserve the discriminating information .Our Laplacianfaces way aims to protect the limited structure of the image space which real -world application mostly needs.

2. An proficient subspace education algorithm for face recognition should be able to discover the nonlinear manifold structure of the face space. Our proposed Laplacianfaces method explicitly considers the manifold structure which is modeled by an adjacency graph and they reflect the intrinsic face manifold structures.

3. LPP shares some similar properties to LLE. LPP is linear, while LLE isnonlinear. Moreover, LPP is defined everywhere, while LLE is defined only on the guidance data points and it is uncertain how to evaluate the maps for new test points. In contrast, LPP may be only practical to any new data point to locate it in.

The algorithmic practice of Laplacianfaces is properly declared below:

1. PCA projection. We project the image set into the PCA subspace by throwing away the smallest

major mechanism. In our experiment, we kept 98 percent in order in the intellect of reconstruction error. For the sake of ease, we still use x to denote the images in the PCA subspace in the following steps. We indicate by WPCA the revolution medium of PCA.

2. Constructing the nearest-neighbor diagram.

Let G stand for a diagram with n nodes. The ith node correspond to the face picture xi . We locate an edge among nodes i and j if xi and xi are “close,” i.e., xi is among k nearest neighbors of xi, or xi is between k nearest neighbors of xj. The construct nearby national diagram is an approximation of the local manifold structure. Note that here we do not use the region to create the chart. This is simply because it is often difficult to choose the optimal “in the real-world application, while k nearest-neighbor graph can be constructed more stably. The drawback is that the k nearest-neighbor exploration will increase the computational complexity of our algorithm. When the computational complexity is a major concern, one can switch to the "-neighborhood.

15

Page 16: Face Recognization

3. Choosing the weight If node i and j are connected, put

where t is a suitable constant. Otherwise, put Sij = 0.The weight template S of graph G models the face various structure by preserve local formation. The explanation for this pick of weights preserve be traced.

where D is a diagonal matrix whose entries are column (or row, since S is symmetric) sums of S, Dii = ∑j Sji. L =D - S is the Laplacian matrix. Theith row of matrix X is xi.

These eigenvalues are identical to or better than zero since the matrices XLXT and XDXT are both symmetric and constructive semi exact. Thus, the embedding be as follow:

where y is a k-dimensional vector. W is the transformation matrix. This linear mapping best conserve the manifold’s predictable basic geometry in a linear brains. The piece vectors of W are the so-called Laplacianfaces.

This opinion is implement with unconfirmed knowledge thought with training and test data.

The system must require to implement Principle Component Analysis to reduce image in the dimension less than n and co-variance of the data.The system have to be use in Unsupervised knowledge algorithm. So it must be taught properly with applicable facts sets. Based on this preparation, enter data is experienced by the use and result is displayed to the client.

16

Page 17: Face Recognization

2.3 System Requirement

Hardware specifications:

Processor : Intel Processor IV

RAM : 128 MB

Hard disk : 20 GB

CD drive : 40 x Samsung

Floppy drive : 1.44 MB

Monitor : 15’ Samtron color

Keyboard : 108 mercury keyboard

Mouse : Logitech mouse

Software Specification:

Operating System – Windows XP/2000

Language used – J2sdk1.4.0

2.4 System Analysis Methods

System analysis can be defined, as a method that is determined to use the resources, machine in the best manner and perform tasks to meet the information needs of an organization. It is also a organization method that help us in wily a new system or improving an accessible system. The four basic elements in the system analysis are

Output Input Files ProcessThe above-mentioned are mentioned are the four basis of the System Analysis.

2.5 Feasibility Study

Feasibility is the study of whether or not the project is worth doing. The

procedures that follow this purpose is called a possibility Study. This study is taken in right time

17

Page 18: Face Recognization

constraint and in general culminates in a written and oral possibility statement. This possibility

study is categorized into seven diverse types. They are

Technical Analysis

Economical Analysis

Performance Analysis

Control and Security Analysis

Efficiency Analysis

Service Analysis

2.5.1 Technical Analysis

This analysis is concerned with specifying the software that will successfully

satisfy the user requirements. The technical needs of a system are to have the facility to produce

the outputs in a given time and the response time under certain conditions..

2.5.2 Economic Analysis

Economic Analysis is the most frequently used technique for evaluating the

effectiveness of prepared system. This is called Cost/Benefit analysis. It is used to conclude the

profit and reserves that are predictable from a future system and compare them with costs. If the

profit overweigh the price, then the judgment is taken to the plan stage and gear the system.

2.5.3 Performance Analysis

The analysis on the performance of a system is also a very important analysis. This analysis about the show of the system together before and after the planned system. If the study proves to be pleasing from the company’s side then this study result is moved to the next analysis phase. Performance study is nothing but invoking at program effecting to identify where bottle neck or other presentation problems such as memory leaks might occur. If the problem is spotted out then it can be rectified.

18

Page 19: Face Recognization

2.5.4 Efficiency Analysis

This analysis mainly deals with the efficiency of the system based on this project. The funds necessary through the program to execute a picky function are analyzed in this phase. It is also checks how resourceful the scheme is on the system, in spite of any changes in the system. The competence of the system should be analyzed in such a way that the client should not feel any distinction in the way of working. Besides, it should be in use into thought that the map on the system should last for a longer time.

19

Page 20: Face Recognization

CHAPTER-3

SYSTEM DESIGN

Design is concerned with identifying software mechanism specifying relationships among components. Specifying software arrangement and given that blue print for the text phase.

Modularity is individual of the attractive property of big systems. It implies that the system is divided into several parts. In such a manner, the contact between parts is least visibly specified.

Design will clarify software workings in detail. This will help the implementation of the system. Moreover, this will show the more change in the system to suit the prospect requirements.

3.1 Project modules:

3.1.1 Read/Write Module:

Here, the essential operation for loading and saving effort and ensuing images respectively from the algorithms. The picture records are read, processed and original images are write into the output images.

3.1.2 Resizing Module:

Here, the faces are changed into equal mass using linearity algorithm, for the computation and judgment. In this unit large similes or lesser images are changed into usual sizing.

3.1.3 Image Manipulation:

20

Page 21: Face Recognization

Here, the face detection algorithm by means of Locality Preserving projection

(LPP) is developed for a variety of enrolled into the file.

3.1.4 Testing Module:

Here, the effort images are resized then compare with the middle image and find

the qualified image then again compared with the laplacian faces to locate the aureate faces.

FIGURE: 1

21

Page 22: Face Recognization

Designing Flow Diagram

3.2 System Development

This system is developed to implement Principle component analysis. Image manipulation: This module designed to view all the faces that are considered in our training case.

Principle Component Analysis is an eigenvector technique calculated to replica linear distinction in high-dimensional data. PCA performs dimensionality reduction by projecting the original n-dimensional data onto the k << n -dimensional linear subspace spanned by the leading

Eigenvectors of the data’s covariance matrix. Its goal is to find a set of equally orthogonal basis functions that capture the directions of highest variance in the information and future for which the coefficients are couple wise decorrelated. For linearly fixed manifolds, PCA is definite to discover the dimensionality of the manifold and produces a solid representation.

1) Training module:

Unsupervised learning - this is learning from observation and discovery. The data

mining system is supplied with objects but no classes are defined so it has to observe the

examples and recognize patterns (i.e. class description) by itself. This process requires training

data set .This system provides training set as 17 faces and each contains three different poses of

faces. It undergoes iterative process stores require detail in face Template two dimension array.

2) Test module:

After training process is over , it process the input image face for eigenface process then can able to say whether it recognizes or not.

22

Page 23: Face Recognization

CHAPTER 4

IMPLEMENTATION

Implementation includes all those activities that take place to convert from the old system to the new. The new system may be completely new, replacing an accessible system or it may be main modification to the system currently put into use.

This system “Face Recognition” is a new system. Implementation as a complete involve every those tasks that we do for effectively replacing the existing or introduce new software to assure the requirement.

The whole work can be describe as retrieval of faces from file, processed for eigen faces training process and test case are executed and finally result is displayed to the user.

The test case has performed in all aspect and the system has given correct result in all the cases.

23

Page 24: Face Recognization

4.1. Implementation Details:

4.1.1 Form design

Form is a tool with a message; it is the physical carrier of data or information. It

also can constitute authority for actions. In the form design files are used to do each module. The

following are list of forms used in this project:

1) Main Form

Contains option for viewing face from data base. The system retrieves the images stored in the folder called train and test folder, which is available in bin folder of your application.

2) View database Form:

This form retrieves face available in the train folder. It is just for viewing purpose

for the user.

3) Recognition Form: This form provides option for loading input image from test folder. Then user has

to click Train button which leads the application for training to gain knowledge as it is of the form unsupervised learning algorithm.

Unsupervised learning - This is learning from observation and discovery. The data mining

system is supplied with objects but no classes are defined so it has to observe the examples and

recognize patterns (i.e. class description) by itself. This system results in a set of class

descriptions, one for each class discovered in the environment. Again this is similar to cluster

analysis as in statistics.

Then user can click the test button Test button to see the matching for the faces.

The matched face will be displayed in the place provided for matched face option. In case of any

difference the information will be displayed in place provided in the for input.

24

Page 25: Face Recognization

4.1.2 Input design

Accurate input data is the most common case of errors in data processing. Errors entered by data entry operators can control by input design. Input design is the process of converting user-originated inputs to a computer-based format. Input data are collected and organized into group of similar data.

4.1.3 Menu Design

The menu in this application is organized into mdiform that organizesViewing of image files from folder. Also it has option for loading image as input, try to perform training method and test whether it recognizes the face or not.

4.1.4 Data base design:

A database is a collection of related data. The database has following properties:i) Database reflects the changes of the information.ii)A database is logically coherent collection of data with some inherent

meaning.This application takes the images form the default folder set for this application

train and test folders. The file extension is .jpeg option.

4.1.5 Code Design

o Face Enrollment -a new face can be added by the user into face space database

o Face Verification -verifies a persons face in the database with reference to his/her identity.

o Face Recognition -compares a persons face with all the images in database and choose the closest

match. Here Principle Component Analysis is performed with training data set . The result is performed from test data set.

o Face Retrieval -displays all the faces and its templates in the database

o Statistics

25

Page 26: Face Recognization

-stores a list of recognition accuracy for analyzing the FRR (False Rejection Rate) and FAR (False Acceptance Rate)

4.2 Coding:

import java.lang.*;import java.io.*;

public class PGM_ImageFilter{

//constructorpublic PGM_ImageFilter(){inFilePath="";outFilePath="";

}

//get functionspublic String get_inFilePath(){

return(inFilePath);}

public String get_outFilePath(){

return(outFilePath);}

//set functionspublic void set_inFilePath(String tFilePath){

inFilePath=tFilePath;}

public void set_outFilePath(String tFilePath){

outFilePath=tFilePath;}

//methodspublic void resize(int wout,int hout){

PGM imgin=new PGM();PGM imgout=new PGM();

if(printStatus==true)

26

Page 27: Face Recognization

{System.out.print("\nResizing...");

}int r,c,inval,outval;

//read input imageimgin.setFilePath(inFilePath);imgin.readImage();

//set output-image headerimgout.setFilePath(outFilePath);imgout.setType("P5");imgout.setComment("#resized image");imgout.setDimension(wout,hout);imgout.setMaxGray(imgin.getMaxGray());

//resize algorithm (linear)double win,hin;int xi,ci,yi,ri;

win=imgin.getCols();hin=imgin.getRows();

for(r=0;r<imgout.getRows();r++){

for(c=0;c<imgout.getCols();c++){

xi=c;yi=r;

ci=(int)(xi*((double)win/(double)wout));ri=(int)(yi*((double)hin/(double)hout));

inval=imgin.getPixel(ri,ci);outval=inval;

imgout.setPixel(yi,xi,outval);}

}

if(printStatus==true){

System.out.println("done.");}

//write output imageimgout.writeImage();

}

27

Page 28: Face Recognization

CHAPTER-5

SYSTEM TESTING

5.1 Software Testing

Software Testing is the process of confirming the functionality and correctness of

software by running it. Software testing is usually performed for one of two reasons:

i) Defect detection

ii)Reliability estimation.

Software Testing contains two types of testing. They are

1) White Box Testing

2) Block Box Testing

1) White Box Testing

White box testing is concerned only with testing the software product, it cannot

guarantee that the complete specification has been implemented. White box testing is testing

against the implementation and will discover faults of commission, indicating that part of the

implementation is faulty.

2) Block Box Testing

Black box testing is concerned only with testing the specification; it cannot assurance that every parts of the implementation have been tested. Thus black box testing is testing against the specification and will find out faults of omission, representative that part of the specification has not been satisfied.

28

Page 29: Face Recognization

Functional testing is a testing process that is black box in nature. It is aimed at examine the overall functionality of the product. It usually includes testing of all the interfaces and should therefore involve the clients in the process.

The key to software testing is trying to find the myriad of failure modes – something that requires exhaustively testing the code on all possible inputs. For mainly programs, this is computationally infeasible. It is common place to attempt to test as many of the syntactic features of the code as possible (within some set of resource constraints) are called white box software testing technique. Techniques that do not consider the code’s structure when test cases are selected are called black box technique.

In order to entirely test a software creation both black and white box testing are required. The problem of applying software testing to defect detection is that software can only propose the company of flaws, not their absence (unless the testing is exhaustive). The problem of applying software testing to reliability estimation is that the input distribution used for selecting test cases may be flawed. In both of these cases, the mechanism used to determine whether program output is correct is often impossible to develop. Obviously the benefit of the entire software testing process is highly dependent on many different pieces. If some of these parts is faulty, the whole procedure is compromised.

Software is now unique unlike other physical processes where inputs are received and outputs are produced. Where software differs is in the manner in which it fails. Most physical systems fail in a fixed (and reasonably small) set of ways. By contrast, software can fail in several bizarre way. Detecting every of the dissimilar disappointment modes for software is generally infeasible.

Final stage of the testing process should be System Testing. This type of test involves examination of the whole computer system, all the software components, all the hard ware components and any interfaces. The entire computer based system is check not simply for validity but also to meet the objectives.

5.2 Efficiency of Laplacian Algorithm

Now, consider a simple example of image variability. Imagine that a set of face similes are generated while the human face rotates slowly. Thus, we can say that the deposit of face images are basically one dimensional. Many recent works shows that the face images do reside on a low dimensional(image space).Therefore, an effectual subspace education algorithm should be able

29

Page 30: Face Recognization

to notice the nonlinear manifold structure. PCA and LDA, effectively see only the Euclidean structure; thus, they fail to detect the intrinsic low-dimensionality. With its neighborhood preserving character, the Laplacian faces capture the intrinsic face manifold structure .

30

Page 31: Face Recognization

FIGURE:2

Two-dimensional linear embedding of face images by Laplacianfaces Fig. 1 shows an instance that the face similes with various pose and expression of a person are mapped into two-dimensional subspace. This data set contains face images. The size of each image is 20 _ 28 pixels, with256 gray-levels per pixel. Thus, each face picture is represented by a end in the 560-dimensional ambientspace. However, these images are believed to come from a sub manifold with few degrees of freedom.

The face similes are mapped into a two-dimensional gap with continuous change in pose and expression. The delegate face similes are exposed in the different parts of the space. The face images are divided into two parts. The left piece includes the expression images with open mouth, and the right part includes the face images with closed mouth. This is because in trying to preserve local structure .. Specifically, it makes the neighboring point in the picture face nearer in the face space. . The 10 testing samples can be simply located in the reduced representation space by the Laplacian faces (columnvectors of the matrix W).

FIGURE:3

Fig. 2. Distribution of the 10 testing samples in the compact representation subspace. As mind for be seen, these testing samples optimally find their coordinates which reflect their intrinsic properties, i.e., pose and expression.

31

Page 32: Face Recognization

As preserve be seen, these testing sample optimally find their coordinates which reflect their intrinsic properties, i.e., pose and expression. This study tells us to the Laplacianfaces are able of capturing the intrinsic face manifold structure.

FIGURE:4

The eigenvalues of LPP and LaplacianEigenmap.

Fig. 3 shows the eigen values computed by the two methods. As can be seen,the eigen values of LPP is consistently greater than those of Laplacian Eigenmaps.

5.2. 1 Experimental Results

A face image can be represented as a point in image space. However, due to the unwanted variations resulting from changes in lighting, facial look, and create, the picture space might not be an optimal space for visual representation.

We can display the eigenvectors as images. These images may be called Laplacianfaces. Using the Yale face file as the preparation set, we present the first 10 Laplacianfaces in Fig. 4, together with Eigen faces and Fisher faces. A face picture can be mapped into the area preserving subspace by using the Laplacian faces.

FIGURE:5

32

Page 33: Face Recognization

Fig (a) Eigenfaces, (b) Fisher faces, and (c) Laplacianfaces calculated from the face images in the YALE database.

5.2.2 Face Recognition Using Laplacianfaces

In this section, we investigate the performance of our proposed Laplacianfaces method for face recognition. The system performance is compared with the Eigen faces method and the Fisher faces method.

In this study, three face databases were experienced. The first one is the PIE (pose, enlightenment, and expression) .The second one is the Yale database and theThird one is the MSRA database.

In short, the recognition method has three steps. First, we calculate the Laplacianfaces from the training set of face images; then the new face image to be identified is probable into the expression subspace spanned through the Laplacianfaces; finally, the new face image is identified by a nearest neighbor classifier.

FIGURE:6

Fig 5.The original face image and the cropped image

5.2.3 Yale Database

The Yale face database was constructed at the Yale Center for Computational Vision and Control. It contains 165 grayscale images of 15 individuals. The images demonstrate

33

Page 34: Face Recognization

variations within lighting situation (left-light, center-light, right light),facial look (normal, happy, sad, sleepy, surprised, and flash), and with/without glasses.

A random division with six similes was full for the preparation set. The rest was in use for testing. The testing sample were then projected interested in the low-dimensional Representation. Recognition was performed by means of a nearest-neighbor classifier.

In general, the show of the Eigen face way and the Laplacian faces method varies with the number of dimensions. We explain the top results obtain by Fisher faces, Eigen faces, and Laplacian faces. The recognition fallout are exposed in Table 1. It is found that the Laplacian faces method significantly outperforms both Eigen faces and Fisher faces methods.

TABLE: 1

Performance Comparison on the Yale Database

FIGURE:7

Fig. 6 shows the plots of error rate versus dimensionality reduction.

5.2.4 PIE Database

34

Page 35: Face Recognization

Fig. 7 shows several of the faces with front, illumination and expression variation in the PIE database. Table 2 shows the recognition results. As can be seen Fisher faces perform comparably to our algorithm on this folder, while Eigenfaces performs poorly. The error rate for Laplacian faces, Fisher faces, and Eigen faces .As can be seen, the error rate of our Laplacianfaces way decreases quick as the dimensionality of the expression subspace.

FIGURE:8

Fig. 7. The section cropped face similes of one person from PIE database. The unique look similes are taken under varying pose, illumination, and expression.

TABLE :2

Performance Comparison on the PIE Database

5.2.5 MSRA Database

This database was collected at Microsoft Research Asia. Sixty-four to eighty face images were collected for each individual in each session. All the faces are frontal. Fig. 9 shows the sample cropped face similes from this folder. In this test, one assembly was use for training and the other was used for testing.

35

Page 36: Face Recognization

FIGURE:9

Fig.8 The section cropped face similes of one individual from MISRA database. The original face images are taken

under varying pose, illumination, and expression.

TABLE: 3

Shows the recognition results. Laplacian faces method has lower error rate than those of Eigen faces and fisher faces .

Performance Comparison on the MSRA Database

36

Page 37: Face Recognization

Performance comparison on the MSRA database with different number of

training samples

37

Page 38: Face Recognization

CHPTER-6

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 cut into lower scope and algorithm for LPP is performed for recognition. The function is developed effectively and implemented as mentioned above.

This system seem to be functioning fine and productively. This scheme can able to supply the proper preparation set of data and test input for recognition. The face matched or not is given in the form of picture image if matched and text message in case of any difference.

38

Page 39: Face Recognization

SNAPSHOT

OUTPUT PAGE:1

39

Page 40: Face Recognization

OUTPAGE:2

40

Page 41: Face Recognization

OUTPUT PAGE:3

41

Page 42: Face Recognization

OUTPUTPAGE:4

42

Page 43: Face Recognization

OUTPUT PAGE:5

43

Page 44: Face Recognization

OUTPUT PAGE:6

44

Page 45: Face Recognization

OUTPUT PAGE:7

45

Page 46: Face Recognization

REFERENCES

1. X. He and P. Niyogi, “Locality Preserving Projections,” Proc. Conf.Advances in Neural Information Processing Systems, 2003.

2. A.U. Batur and M.H. Hayes, “Linear Subspace for IlluminationRobust Face Recognition,” (dec2001).

3. M. Belkin and P. Niyogi, “Laplacian Eigenmaps and SpectralTechniques for Embedding and Clustering,”

4. P.N. Belhumeur, J.P. Hespanha, and D.J. Kriegman, “Eigenfaces

Vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” Pattern Analysis and Machine Intelligence (July 1997).

5. M. Belkin and P. Niyogi, “Using Manifold Structure for PartiallyLabeled Classification (2002).

6. M. Brand, “Charting a Manifold,” Proc. Conf. Advances in NeuralInformation Processing Systems, 2002.

7. F.R.K. Chung, “Spectral Graph Theory,” Proc. Regional Conf. Seriesin Math., no. 92, 1997.

8. Y. Chang, C. Hu, and M. Turk, “Manifold of Facial Expression,”Proc. IEEE Int’l Workshop Analysis and Modeling of Faces andGestures, Oct. 2003.

9. R. Gross, J. Shi, and J. Cohn, “Where to Go with FaceRecognition,” Proc. Third Workshop Empirical Evaluation Methodsin Computer Vision, Dec. 2001.

46

Page 47: Face Recognization

10. A.M. Martinez and A.C. Kak, “PCA versus LDA,” IEEE Trans.Pattern Analysis and Machine Intelligence, Feb. 2001.

47