Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
HUMAN FACE IDENTIFICATION
1. Design Seminar
on
HUMAN FACE IDENTIFICATION
Submitted for partial fulfillment of the degree of
Bachelor of Engineering
BY
1.Vishal Dhote 2.Bhupesh Lahare
3.Akash Bonde 4.Shrinath Wadyalkar
5.Nidhi Meshram
7th Semester
Department of Information Technology
Er.C.D.Bawankar Er. Ashvini Kheole Prof. S. V. Sonekar
Project Guide Project Incharge HOD(CSE/IT)
Department of Information Technology,
J D College of Engineering & Management, Nagpur.
Rashtrasant Tukdoji Maharaj Nagpur University, Nagpur.
Session: 2012-2013
2. Contents:
Aim
Objective
Literature Survey
-Problem Definition
Research Methodology
Software Requirements
Hardware Requirements
Limitations
Result
Conclusion
Bibliography
3. Aim:
Face recognize that works under varying poses.
Importance of faces
Central role in human interactions
Communicate a wealth of social information:
Age, gender, personal identity (physical structure)
Mood and emotional state (facial expression)
4. Objective
Develope a computational model.
Why face recognition?
To apply it to wide area of problems.
1)Criminal Identification
2)Security
3)Image and Film Processing
5. Literature Survey:
1. Avinash Kaushal1, J P S Raina, A., “Face Detection using
Eigenface method ,Gabor Wavelet Transform”, IJCST Vol. 1,
Iss ue 1, September 2010 I S S N : 0 9 7 6 - 8 4 9 1
Eigenface method, template matching, graph matching,
method. The eigenface approach applies the Karhonen-Loeve
transform for feature extraction. It greatly reduces the facial
feature dimension and yet maintains reasonable discriminating
power.
2. Steve Lawrence , Lee Giles “Face Recognition: A
Convolutional Eigenface method “ IEEE Transactions on
special issue on Pattern Recognition. vol.3, no110, 2009
Eigenface method, though some variants of the algorithm work
on feature extraction as well, mainly provides sophisticated
modeling scheme for estimating likelihood densities in the
pattern recognition phase.
6. Problem Definition :
To retrieve the similar images(based on a heuristic)
from the given database of face images.
It used to take much time to find any criminals
Not very much accurate.
Danger of losing the files in some case.
7. Research Methodology:
Eigen face method is based on an information theory
approach that decomposes face images into a small set
of characteristic feature images called eigenfaces.
• Recognition is performed by projecting a new image
into the subspace[3].
8. Process Flow Diagram:
Start
Login
Authentication
Valid User
Invalid User
Main Screen
Add Image Clip Image Update Details Construct Image Search Process
Enter Make Clips Open Record Specify Feature
Search Image &
Details & Update
Get Details
Add to Add Clips to Add to Search
Result
Database Database database Image
End
30. Hardware Requirements:
Processor : Processor with 400 Mhz.
Hard disk : 1 GB hard disk.
RAM : 256MB
Mouse : MS mouse or compatible.
Keyboard : standard 101 or 102 Keys.
31. Limitations:
Face Recognition Is Not Perfect And Struggles To
Perform Under Certain Conditions.
1. Poor Lighting
2.Other Objects Partially Covering The Subject’s
Face.
3.Low Resolution Images.
4.It is not platform independent
32. Result:
Thus we have reduced the problem of matching faces
with previous applications.
This application will find the approximate match of
human face at various angles.
33. Conclusion:
A face recognition system must be able to recognize a
face in many different imaging situations.
It will find faces efficiently without exhaustively
searching the image.
Face recognition systems are going to have
widespread application in smart environments.
.
34. Bibliography:
[1] Avinash Kaushal1, J P S Raina, A., “Face Detection using Neural
Network & Gabor Wavelet Transform”, IJCST Vol. 1, Iss ue 1,
September 2010 I S S N : 0 9 7 6 - 8 4 9 1
[2]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
[3] 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
[4] 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
[5] 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