This Presentation is for project work which will work on the "FACE DETECTION USING MATLAB".
This presentation will be prepared on the practical basis instead of theoretical knowledge. So result may vary on the basis of your practical work.
This Presentation is of standard format which is also beneficial for the engineering student for project work.
1. Project Presentation
On
Face Detection Using MATLAB 7.10
Submitted in partial fulfillment of the requirements for the award of
Degree of
BACHELOR OF TECHNOLOGY
IN
ELECTRONICS AND COMMUNICATION ENGINEERING
ELECTRONICS DEPARTMENT
SACHDEVA INSTITUTE OF TECHNOLOGY, MATHURA, U.P.
Session: 2014-2015
SUBMITTED TO: SUBMITTED BY:
Rajesh Kumar Sudhasnhu Saxena
Tushar Singh
Indrajeet
2. Introduction
• Facial expressions deliver rich information about human relation and human emotion and play an
essential role in human communication.
•Automatic facial expression recognition had been studied worldwide in last 10 years, which has become
the very active research area in computer vision and pattern recognition.
• There are two main categories for face recognition:
• Holistic based methods treat the face and its different properties as one unit. Certain face properties are
then extracted in order to distinguish faces.
• Feature based method are based on facial characteristics and it divides the face into smaller areas,
which later on are analyse. This method has several advantages when it comes to handling varying light
condition and different angels compared with the holistic approach. On the other hand this method has
downsides when dealing with identification of closed eyes or mouth.
• There have been many attempts to solve human face detection problem. The early approaches for grey
label image only and image pyramid schemes are necessary to scale with unknown face sizes.
3. Objectives
• There have been great achievements and progress in this particular field of study but there are many
challenges left to overcome.
• Still today, low accuracy is one of the main drawbacks of face recognition. Also considering that this
technology can be applied in several important areas is making it an appropriate technology to develop.
• The purpose of this project is to create a face recognition algorithm that can recognize faces in
manipulated images.
•The objective of this project is to develop a very efficient algorithm, in terms of low computational
complexity, with the maximum number of face detection and the minimum number of false alarms.
•The final step is to determine real faces from the face candidates using a multilayer classification
scheme.
4. Flowchart
Start
Connect Camera to Computer
Matching
The
Images
Software Compare the image using MATLAB
Algorithm with existed images
END
Take the image of User
Image Detected
If No
If Yes
5. How It Work
• All methods are design to detect and recognised faces in given image with limited conditions.
•We name the data base folder as ‘Train’.
•Then the images will detect are stored in ‘Test’.
•Then we will match the method of ‘Test’ folder with images already stored in ‘Train’ folder.
•This matching is based on algorithm and commands used in programming.
•First the images were stored in the data base.
• Fortunately, the images used in this project have some degree of uniformity thus the detection algorithm
can be simpler:
I. All the faces are vertical and have frontal view.
II. They are under almost the same illuminate condition.
• This project present a face detection technique mainly based on the colour segmentation, image
segmentation and template matching methods.
6. Face Recognition Technique (FRT)
• Face Recognition Technique (FRT) can only recognize a face if a specific individual face has already
been added to the system in advance.
•The condition of the enrolment and the quality of resulting image have significant impact on the final
efficiency of FRT.
• Image quality is more significant than any other single factor in the overall performance of FRT.
7. Applications
Face recognition is a technology that can be applied and implemented in many part of today’s society.
Some areas of applications are:
• Biometrics: Using a face as a biometric is proved to be a successful approach since it is the way
humans recognize each other.
• Identification System: A face could be used to examine if a person exist or not in the list of individuals.
Based on that information the system can allow respectively deny access.
• Law Enforcement: Face recognition technology can be used to increase performance of surveillance
and law enforcement.
8. Methodology
Phase I: Selection of Project topic
Phase II: Literature review
Phase III: Data Analysis
Phase IV: Feasibility of equipment
Phase V: Mathematical calculations (either manually or by software)
Phase VI: Designing process in software
Phase VII: Simulation
Phase VIII: Obtain Result of simulation
Phase IX: Testing
9. Conclusion
• In this project, we introduce our FER system based on Gabor feature and PCA (Principal Component
Analysis) + LDA (Linear Discriminate Analysis).
• The experiment suggests the following conclusion:
• PCA can significantly reduce the dimensionality of the original feature without loss of much
information in the sense of representation, but it may lose important information for discrimination
between different classes.
•When using PCA + LDA method, the dimensionality drastically reduced to six dimensions and the
recognition performance is improved several percent compare with PCA.
• Experiment shows that PCA + LDA feature may be partially eliminate the sensitivity of illumination.
•Future work will be focused on verifying the algorithm performance against general image and studying
the required modifications to make the algorithm robust with any image.
10. Software
MATLAB 7.10
• Cleve Moler, The chairman of the computer science department at the University of New Mexico,
started developing MATLAB in the late 1970s.
•MATLAB was first adopted by Researchers and practioners in control engineering, little’s speciality, but
quickly spread many other domains. It is now also used in education, in particular the teaching of linear
algebra and numerical analysis and is popular amongst scientist involved in image processing.
• MATLAB (Matrix Laboratory) is a numerical commuting environment and fourth generation
programming language.
• MATLAB allows matrix manipulations, plotting of functions and data, implementation of algorithms,
creation of user interfaces, and interfacing with programs written in other languages including C, C++,
Java and FORTRAN.
• MATLAB is intended primarily for numerical computing.
• MATLAB is widely used in academic in research institution as well as industrial enterprises.