Sie sind auf Seite 1von 11

FACE RECOGNITION SYSTEM

BY

GOVIND SINGH BISHT PRASHANT KUMAR DEEPAK SINGH AIR SAURABH MISHRA

08430101018 08430101060 08430101014 08430101048

Department of Computer Science and Engineering Quantum School of Technology, Roorkee (Affiliated to Uttarakhand Technical University)
2012

FACE RECOGNITION SYSTEM


Project report submitted in partial fulfilment of the requirement for the award of the Degree of B.Tech

By

GOVIND SINGH BISHT PRASHANT KUMAR DEEPAK SINGH AIR SAURABH MISHRA

08430101018 08430101060 084301010 084301010

Department of Computer Science and Engineering Quantum School of Technology, Roorkee (Affiliated to Uttarakhand Technical University)
ii

CERTIFICATE

This is to certify that the project report entitled FACE VARIFICATION being submitted by Mr Govind Singh Bisht, Mr Prashant Kumar, Mr. Deepak Singh Bisht, Mr. Saurabh Mishra in partial fulfillment for the award of the Degree of Bachelor of Technology in Computer Science and Engineering to the Uttarakhand Technical University is a record of bonafide work carried out by him/her under my guidance and supervision.

Project Incharge Mrs.Ruchika Monga

Guide Mr. Anchit Bijalwan

HOD (CSE/IT) Mr. N. S. Chetty

iii

DECLARATION

I hereby declare that the project entitled FACE VERIFICATION submitted for the B.Tech Degree in Computer Science and Engineering / Information Technology is my original work and the project has not formed the basis or submitted for the award of any degree, diploma, or any other similar titles in any other college / institute / university.

GOVIND SINGH BISHT PRASHANT KUMAR DEEPAK SINGH AIR SAURABH MISHRA

08430101018 08430101060 084301010 084301010

Place: Date:

iv

ACKNOWLEDGEMENT
We convey our most sincere heartfelt thanks to Head of the Department of Computer Science and Engineering Mr. N S Chetty, for the motivation she had given as during the progress of this project work.

At the outset we are very much thankful to our Project Incharg Mrs. RuchikaMonga, for all the facilities provided to us in carrying out this project.

We convey our most sincere thanks to Mr. Anchit Bijalwan, Department of CSE, for his guidance and effort throughout this project for us.

We also convey our heartfelt thanks to all the individuals who have helped me directly and indirectly to carry out this project successfully.

ABSTRACT
The proposed approach essentially was to implement and verify the algorithm Eigenfaces for Face Recognition, which solves the recognition problem for two dimensional representations of faces, using the principal component analysis.From Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) which effectively see only the Euclidean structure of face space. The snapshots, representing input images for the proposed system, are projected in to a face space (feature space) which best defines the variation for the face images training set. The face space is defined by the eigenfaces which are the eigenvectors of the set of faces. These eigenfaces contribute in face reconstruction of a new face image projected onto face space with a meaningful (named ).The projection of the new image in this feature space is then compared to the available projections of training set to identify the person using the Euclidian distance. The implemented system is able to perform face recognition and can give feedback giving a window with the subject's info from database.

vi

TABLE OF CONTENTS
1. INTRODUCTION

1
3 3 3 4 5 5 5 6 7 7 7 7 8 8 8 8 9 9 9 9 10 10

2. SOFTWARE AND HARDWARE REQUIREMENT


2.1 HARDWARE 2.2 SOFTWARE 3. LITERATURE STUDY 3.1 BIOMETRIC RECOGNITION 3.2 EMERGENCE 3.3 ADVANTAGES 3.4 TYPES 3.4.1 EYE 3.4.2 IRIS 3.4.3 RATINA 3.4.4 FACE 3.4.5 FINGER 3.4.6 HAND 3.4.7 HAND GEOMETRY 3.4.8 VEIN PATTERN RECOGNITION 3.4.9 PALM 3.4.10 VOICE 3.5 MODULES OF BIOMETRICS 3.5.1 SENSOR OR CAPTURE MODULE 3.5.2 FEATURE EXTRACTION MODULE 3.5.3 MATCHER MODULE

vii

3.5.4 SYSTEM DATABASE MODULES 3.6 TYPICAL BIOMETRIC RECOGNITION SYSTEM 3.6.1 FACIAL RECOGNITION 3.6.2 AUTOMATIC FACIAL RECOGNITION PROCESS FLOW 3.6.3 FACIAL RECOGNITION TECHNIQUES 3.6.3.1 EIGEN FACES 3.6.3.2 NEURAL NETWORK 3.6.3.4 GRAPH MATCHING 3.6.3.5 HIDDEN MARKOVER MODELS(HMMS) 3.6.3.6 GEOMATRICAL FEATURE MATCHING 3.6.3.7 TEMPLATE MATCHING 3.6.3.8 3D MORPHABLE MODEL 4. SOFTWARE REQUIREMENT ANALYSIS 4.1 PROBLEM DEFINITION 4.2 MODULES AND THEIR FUNCTIONALITIES 4.2.1 INTRODUCTION 4.2.2 COLOR BASED TECHNIQUES 4.2.3 PCA 4.2.3.1 FACE FORMATION PHASE 4.2.3.2 TRAINING PHASE 4.2.3.3 RECOGNITION AND LEARNING PHASE 4.2.3.4 THE USE OF EIGENFACES FOR RECOGNITION 4.2.4 THE USE OF EIGEN FACES FOR RECOGNITION 4.2.4.1 EIGENVALUES AND EIGEN VECTORS 4.2.5 COMPUTATION STEP viii

10 11 11 12 14 14 14 14 14 15 15 15 16 16 17 17 18 19 21 21 21 21 23 23 25

4.2.6 CLARIFYING IMAGE 4.2.7 I/P AND O/P 5. SOFTWARE DESIGN 5.1 DATA FLOW DIAGRAM 5.1.1 LEVEL 0 5.1.2 LEVEL 1 5.1.3 PROCESSING 5.1.4 RECOGNITION 5.1.5 LEVEL 2 5.2 UML DIAGRAM 5.2.1 USECASE DIAGRAM 5.2.2 SEQUENCE DIAGRAM 5.2.3 OBJECT DIAGRAM 5.3 CONTROL FLOW DIAGRAM 5.3.1 COLOR BASED TECHNIQUES 5.3.2 PCA TRAINING 5.3.3 PCA RECOGNITION 6. CODING

28 29 30 30 31 32 33 34 35 36 36 37 38 39 39 40 41

42 72 77 78 80 81

7. OUTPUT SCREENS 8. CONCLUSION 9. FURTHER ENHANCEMENT AND RECOMMENDATION 10. REFERENCE 11. APPENDIX

ix

LIST OF DIAGRAMS
3.6. TYPICAL BIOMETRIC RECOGNITION SYSTEM 3.6.4 FACE RECOGNITION PROCESSING FLOW 5.1.1 LEVEL 0 DFD 5.1.2 LEVEL 1 DFD 5.1.3 DATA FLOW DIAGRAM PROCESSING 5.1.4 DATA FLOW DIAGRAM RECOGNITION 5.1.5 LEVEL 2 DFD 5.2.1 USE CASE DIAGRAM 5.2.2 SEQUENCE DIAGRAM 5.3 OBJECT DIAGRAM 5.4.1.COLOR BASED TECHNIQUE 5.4.2.PCA TRAINING PHASE 5.4.3.PCA RECOGNITION PHASE 10 12 31 32 33 34 35 35 36 38 39 40 41

LIST OF IMAGES

4.2.4 SAMPLE EIGENFACES FORM THE SAMPLE TRAINING SET 7.1 A SIMPLE FORM 7.2. AN UNKNOWN PERSON 7.3. ADDING A NEW PERSON TO THE DATABASE

25 72 73 74

7.3. ANOTHER FACE OF SAME PERSON ADDED TO GET THE BETTER RESULTS 75 7.4. RECOGNIZING A PERSON REGISTERED IN THE DATABASE 76

xi

Das könnte Ihnen auch gefallen