Upload
independent
View
0
Download
0
Embed Size (px)
Citation preview
PROJECT – A REPORT
on
FACE RECOGNITION TO RETREIVE DATA FROM DATABASE.
Submitted in partial fulfillment of the
requirements for the degree of
BACHELOR OF ENGINEERINGIn
INFORMATION TECHNOLOGYBy
Group No. 34Roll No. Names127 Rohit Bachwani128 Kailash Nadkar
129
130
Chirag
Pardasani
Rushabh ShahUnder the guidance of
Mrs. Sampada Pinge
(Associate Professor, Department of Information
Technology, TSEC)
Thadomal Shahani Engineering College
1
University Of Mumbai
2014-2015
Project Report Approval for B. E.(I.T)
This project report entitled “FACE RECOGNITION TO RETREIVE
DATA FROM DATABASE” by Rohit bachwani, Kailash nadkar,
Chirag Pardasani and Rushabh shah is approved for the
degree of Bachelor of Engineering in Information
Technology of Mumbai University.
Examiners
1.---------------------------------------------
2.---------------------------------------------
2
Supervisor
1.---------------------------------------------
Chairman
----------------------------
-------------------
Date: 07.11.2014
Place: TSEC, Bandra.
THADOMAL SHAHANI ENGINEERING COLLEGE
UNIVERSITY OF MUMBAI
2014-2015
THADOMAL SHAHANI ENGINEERING COLLEGE
(Department of Information Technology)
CERTIFICATE
This is to certify that Rohit Bachwani, Kailash Nadkar,
Chirag Pardasani and Rushabh shah have satisfactorily
3
carried out the dissertation work entitled “FACE
RECOGNITION, RETRIEVAL OF DATA FROM DATABASE” for the
degree of Bachelor of Engineering in Information
Technology of Mumbai University.
_______________
Mrs. Sampada Pinge,
Information Technology Department,
Thadomal Shahani Engineering College,
Bandra (W), Mumbai-400050.
__________________
Dr. G.T. Thampi
PRINCIPAL
Thadomal Shahani Engineering College,
Bandra (W), Mumbai-400050.
Declaration
4
We, Rohit Bachwani, Kailash nadkar, Chirag
pardasani and Rushabh shah, declare that this written
submission represents our ideas in our own words and
where others' ideas or words have been included, we
have adequately cited and referenced the original
sources. We also declare that we have adhered to all
principles of academic honesty and integrity and have
not misrepresented or fabricated or falsified any
idea/data/fact/source in our submission. We understand
that any violation of the above will be cause for
disciplinary action by the Institute and can also evoke
penal action from the sources which have thus not been
properly cited or from whom proper permission has not
been taken when needed.
-------------------------
----------------
Roll No. 127, Rohit
Bachwani
-------------------------
----------------
Roll No. 128, Kailash
5
Nadkar
-------------------------
----------------
Roll No. 129,Chirag
Pardasani
-------------------------
----------------
Roll No. 130,Rushabh Shah
Date:8.11.2014
6
TABLE OF CONTENTS
Sr. No Topic
Page No.
List of Figures…………………………………………………………….……….7
Abstract……………………………………………………………………..……..8
1.Introduction…………………………………………………………….…..9
1.1 Problem Definition…………………………………………………….10
1.2Relevance of Project…………………………………………………….....11
1.3 Scope of
Project……………………………………………….............11
2.Review of Literature.………………………………………………………12
2.1 Introduction to Face Detection……………………………………….…
13
7
3. Description...………………………………………..……………………....15
3.1 Proposed System…………………………………………..………….16
3.2 Methodology and Analysis……………………...…………...
…………..17
3.3 Design Approach……………………………….....……………………18
4. Implementation……………………………………………………………19
4.1 Software Requirements…………………….…………..
………....19
4.2 Functional Requirements…….……………….….
………...……..20
4.3 Non-Functional Requirements…………………………...
……….20
5.Further Work…………………………………………………………….....…21
8
ABSTRACT
Face (facial) recognition is the identi cation of humans by the fi
unique characteristics of their Faces.Face recognition
technology is the least intrusive and fastest bio-metric
technology.It works with the most obvious individual identi er fi
the human face. With increasing se-curity needs and with
advancement in technology extracting information has become
muchsimpler. This project aims on building an application based
on face recognition using different algorithms and comparing the
results. The basic purpose being to identify the faceand
retrieving information stored in database. It involves two main
steps. First to identifythe distinguishing factors in image n
storing them and Second step to compare it with theexisting
images and returning the data related to that image. The various
algorithms usedfor face detection are PCA Algorithm and Gray
Scale Algorithm
10
1. INTRODUCTION
The face is our primary focus of attention in social life
playing an important role in conveying identity and emotions. We
can recognize a number of faces learned throughout our lifespan
and identify faces at a glance even after years of separation.
This skill is quite robust despite of large variations in visual
stimulus due to changing condition, aging and distractions such
as beard, glasses or changes in hairstyle. Human face detection
by computer systems has become a major field of interest. Face
detection algorithms are used in a wide range of applications,
such as security control, video retrieving, biometric signal
processing, human computer interface, face recognitions and
image database management. However, it is difficult to develop a
complete robust face detector due to various light conditions,
face sizes, face orientations, background and skin colors.
1.1 PROBLEM DEFINITION
Considering an image, Face recognition is a particularly
complex task that involves detection and location of faces. The
human face is a very challenging pattern to detect and
recognize, because while its anatomy is rigid enough so that all
faces have the same structure, at the same time there is a lot
14
of environmental and personal factors affecting facial
appearance. The main problem of face recognition is large
variability of the recorded images due to pose, illumination
conditions, facial expressions, use of cosmetics, different
hairstyles, presence of glasses, beard etc.
1.2 RELEVANCE OF THE PROJECT
Trying to nd a face within a large database of faces:fi In
this approach the system returns a possible list of faces from
the database. The most useful applications contain crowd
surveillance, video content indexing, personal identi cationfi
(example: drivers license), mug shots matching, etc.
Real time face recognition: Here, face recognition is used
to identify a person on the spot and grant access to a building
or a compound, thus avoiding security hassles. In this case the
face is compared against a multiple training samples of a person
1.3 SCOPE OF THE PROJECT
15
Face detection has two primary tasks, first is to
identify(feature extraction) and second is to locate the
image(Matching it from database).The project basically focuses
on high level of technology consideration. The project contains
two steps feature extraction and decision making. Our motive is
to easily identify the image and quickly compare it from the
database and give the result.
.
16
2. LITERATURE REVIEW
2.1INTRODUCTION
In recent years, face recognition has attracted much
attention and its research has rapidly expanded by not only
engineers but also neuroscientists, since it has many potential
applications in computer vision communication and automatic
access control system. Especially, face detection is an
important part of face recognition as the first step of
automatic face recognition. However, face detection is not
straightforward because it has lots of variations of image
appearance, such as pose variation (front, non-front),
occlusion, image orientation, illuminating condition and facial
expression.
2.2FACE RECOGNITION
Automatic recognition of people is a challenging problem
which has received much attention during recent years due to
its many applications in different fields. Face recognition is
one of those challenging problems and up to date, there is no
technique that provides a robust solution to all situations.
This paper presents a new technique for human face
18
recognition.This technique uses an image-based approach towards
artificial intelligence by removing redundant data from face
images through image compression using the two-dimensional
discrete cosine transform (2D-DCT).The DCT extracts features
from face images based on skin color. A self-organizing map
(SOM) using an unsupervised learning technique is used to
classify DCT-based feature vectors into groups to identify if
the subject in the input image is “present” or “not present” in
the image database. Face recognition with SOM is carried out by
classifying intensity values of grayscale pixels into different
groups.
Given an image that consists of many objects our goal is to
detect humans faces, extract these faces and identify each face
using a database of known humans. So, our algorithm is divided
to three main steps, first: face detection, the proposed
algorithm depends heavily on the open-source library OpenCV in
this step. Second: facial feature extraction, an effective
method to extract facial features like eyes, nose and mouth
depending on their locations with respect to the face region is
developed. Third: similar face identification or image
searching; the goal of this step is to scan the database of
known faces to find the most similar faces to the faces
extracted from the test image in the first step.
Since face recognition is not a difficult task for human
19
beings, selection of biologically motivated Gabor filters is
well suited to this problem. Gabor filters, modeling the
responses of simple cells in the primary visual cortex, are
simply plane waves restricted by a Gaussian envelope function
[1].An image can be represented by the Gabor wavelet transform
allowing the description of both the spatial frequency
structure and spatial relations. Convolving the image with
complex Gabor filters with 5 spatial frequency (v = 0,…,4) and
8 orientation (µ = 0,…,7) captures the whole frequency
spectrum, both amplitude and phase.
Euclidean distance based classifier is used which is obtained
by calculating of distance between image to test and available
images that are taken as training images. Using the given set
of values minimum distance can be found. In testing, for every
expression computation of
Euclidean distance (ED) is done between new image (testing)
Eigenvector and Eigen
subspaces, to find the input image expression classification
based on minimum Euclidean
distance is done. The formula for the Euclidean distance is
given by:
ED ¿∑√ (x2−x1)^2
The recognition rate for the system proposed is found to be
95%.
20
3. DESCRIPTION
3.1 PROPOSED SYSTEM
The previous sections illustrate di erent techniques and methodsff
of face detection and recog-nition. Each category of method
performs well in certain criteria and also has drawbacksas well.
Systems with robustness and certain level of accuracy are still
far away. Keepingin view case study the following architecture
23
Image scanned
Database
Image scanned
Face detection
Face recognition
Recog/not-recognized
is proposed for the detection and recognitionsystem.As discussed
earlier that the robust system catering the needs of real world
situation is achallenging task. The images will be scanned by
scanner and stored into database. Again theimage will be scanned
and stored into the database. Now two images of the same
candidatewill be stored into the database. The rst step is tofi
select desired images from the databasethen for comparisons them
the next step is to detect faces from each image. The next
stepis to recognize that images as of the same candidate or not.
3.2 METHODOLOGY AND ANALYSIS
1.Image acquisition: - Images used for facial expression
recognition are static images and image sequences.
Ideally a face acquisition stage features on automatic
face detector that allows locating faces in complex
scenes with cluttered background.
2.Preprocessing: - Image preprocessing often takes the
form of signal conditioning together with segmentation,
location or tracking of the face or its parts.
3.Feature Extraction: - Feature Extraction methods can be
categorized according to whether they focus on motion or
deformation of faces and facial features, respectively.
Whether they act locally or holistically.
24
4.Classification: - Expression categorization is performed
by classifiers. Covering parametric as well as non-
parametric techniques has been applied to the
automatic expression recognition problem.
5.Postprocessing: - it aims to improve recognition
Accuracy by exploiting
domain knowledge to correct classification errors.
3.3 DESIGN APPROACH
The system is designed with very simple approach. User need to
input images which has text to be recognized. The application will
process the image and will give the result which can be saved.
25
We shall design an algorithm that does the following :
Acquire an image from within the device’s storage or
should let the user click an image using the device
camera.
The application must perform required pre- processing on
the acquired image.
Once the image is preprocessed , comes the stage of feature
extraction where each character in the processed image is
extracted and separated from the entire image.
Later the extracted characters should be matched with the
training set of characters stored in the database .
Finally , the image can be displayed to the user , also
allowing him to access the system.
26
4. IMPLEMENTATION
4.1 RECOMMENDED REQUIREMENTS
Software:-
1) Processing: core 2 duo with processing speed 2.0 Ghz
2) Memory: 1GB RAM
50GB Hard Disk
4.2 FUNCTIONAL REQUIREMENTS
Image Acquisition: Importing image from Gallery or Capturing
image from camera.
Image Pre-Processing: Such Enhancing quality of image and
noise reduction.
Feature extraction: Focusing on characters of an
image.
Character Recognition & Display Result: Identifying the
extracted characters and and Exhibiting the result.
Storage of Converted File: Storing file in the
application itself.
Searching of Converted Image: Searching of Image.
27
4.3 NON – FUNCTIONAL REQUIREMENTS
Reliability: Application should face minimum failure and it
should not crash.
Availability: The application should be available as and
when the end-user demands.
Simplicity: The application should be user friendly.
Accuracy: The application should provide high accuracy as
compared to existing system.
Performance: It should have low latency time between input
and the first glimpse of output as quick performance (speed)
is concerned.
Portability: All android smart phones from version 2.3
should be capable of hosting this application.
28
5. FURTHER WORK
As we will initiate our application’s implementation the
further work that we endeavour to undertake is the designing of
the application then followed by its development.
During this implementation, we will try to incorporate some
commonly used file extensions while considering compatibility
with the application.
We also have envisioned our project to extend beyond the
explained herein. Any application should be updated from time to
time and thus we would work further to incorporate new
functionalities.
29
6. REFERENCES
[1] Perkins D. , “ A definition of caricature and recognition”,
Studies in the Anthropology of Visual Communication, Vol. 2,
pp. 1-24, 1975.
[2]Rupinder Saini , “Facial expression recognition
techniques,database & classifiers” ,International journal ,Vol.2
Issue(June 2014).
[3]Avinash Kaushal , “Face detection using neural network &
gabor wavelet”,IJCST ,
Vol 1,Issue(Sept 2010).
[4]Aruna bhadu , ”Facial expression using DCT”,International
journal, Vol 2,Issue(July 2012).
[5]Williwam Robson Schwartz , ”Face identification using large
feature sets”, IEEE transactions, Vol 2(Issue April 2012).
[6] Walaa Mohamed,” Face recognition using variance estimation
and feature extraction”,International Journal, Issue(April
30
2013).
ACKNOWLEDGEMENT
We take this opportunity to express our sincere thanks and
gratitude to Mrs. Sampada Pinge, Department of Information
Technology,Thadomal Shahani Engineering college for her constant
assistance as well as for being our internal project guide, for
the consistent motivation & inspiration, support and critical
review of the project. She has taken the pains to go through the
31
project and make the necessary corrections wherever required.
We thank our Head of the Department, Mr. Arun Kulkarni for his
excellent guidance and support. Also we would like to thank Dr.
G.T.Thampi, our principal, for providing the facilities and
infrastructure for the project and extending moral support.
We would also like to thank our institution- Thadomal Shahani
Engineering College and our faculty members for providing a
platform for improvement.
Lastly we would like to thank our colleagues for supporting and
encouraging us to move forward with such a simple but compelling
topic and providing valuable suggestions as feedback. We thank
our family for being there and always supporting us,
understanding our investment in the project and allowing us to
do whatever is needed.
32