FACE RECOGNITION AND GENDER CLASSIFICATION

USING LBP

A MINI PROJECT REPORT

Submitted by
T.S.DHARANIDEVI (15F113)
A.DIVYAPRIYA (15F115)
C.KOHILA (15F122)

in partial fulfillment for the award of the degree of

BACHELOR OF TECHNOLOGY

in

INFORMATION TECHNOLOGY

ANNA UNIVERSITY :: CHENNAI 600 025

MARCH 2020
 BONAFIDE CERTIFICATE
Certified that this project report “FACE RECOGNITION AND GENDER
CLASSIFICATION USING LBP” is the bonafide work of “T.S.DHARANIDEVI
(15P113), A.DIVYAPRIYA (15P115), C.KOHILA(15P122)” who carried out the project
work under my supervision. Certified further that to the best of my knowledge the work
reported here in does not form part of any other dissertation on the basis of which degree or
award was conferred on an earlier occasion this or any other candidate.

SIGNATURE SIGNATURE
Dr.P.MURUGESWARI Dr.XXXXXXXXXXXXX
HEAD OF THE DEPARTMENT SUPERVISOR

Certified that the candidate was examined in the viva-voce examination

held on

……………………….......
(Internal Examiner)
 ACKNOWLEDGEMENT

We express our sincere thanks to Karpagam educational and charitable

trust for providing necessary facilities to bring out the project successfully. We
felt greatness to record our thanks to the chairman
Dr.R.VASANTHAKUMAR, B.E.,(Hons), D.Sc for all his support and ray of
strengthening hope extended.

It is the moment of immense pride for us to reveal our profound thanks to

our respected principal Dr.P.VIJAYAKUMAR,M.E.,Ph.D. who happens to be
striving force in all our endeavors.

We express our sincere thanks to Dr.P.MURUGESWARI,

M.Tech.,Ph.D. Head of the Department of Information Technology for
providing an opportunity to work on this project. Her valuable suggestions
helped us a lot to do this project.
A word of thanks would not be sufficient for the work of our project
guide ____________________ Department of Information Technology whose
efforts and inspiration lead us through every trying circumstance.

We deeply express our gratitude to all the members of the faculty of the
department of Information Technology for the encouragement, which we
received throughout the semester.
 ABSTRACT

The identification of human beings based on their biometric body parts such as
face, fingerprint, gait, iris, and voice plays an important role in electronic applications andhas
become a popular area of research in image processing. It is also one of the most successful
applicationsofcomputer–humaninteractionandunderstanding.Outofalltheabovementioned
body parts, the face is one of most popular traits because of its unique features. In fact,
individuals can process a face in a variety of ways to classify it by its identity, along with a
number of other characteristics, such as gender, ethnicity, and age. Specifically, recognizing
human gender is important because people respond differently according to gender. In this
paper, we present a robust method that uses global geometry-based features to classify gender
and identify age and human beings from video sequences. The features are extracted based on
facedetectionusingskincoloursegmentationandthecomputedgeometricfeaturesoftheface
ellipseregion.Thesegeometricfeaturesarethenusedtoformthefacevectortrajectories,which are
inputted to a time delay neural network and are trained using the Broyden–Fletcher–
Goldfarb–Shanno (BFGS) function. Results show that using the suggested method with our
own dataset under an unconstrained condition achieves a 100% classification rate in the
training set for all application, as well as 91.2% for gender classification, 88% for age
identification, and 83% for human identification in the testing set. In addition, the proposed
method establishes the real-time system to be used in three applications with a simple
computation for feature extraction. Classification has emerged as a leading technique for
problem solution andoptimization.

Classification has been used extensively in several problems domains. Automated

genderclassificationisanareaofgreatsignificanceandhasgreatpotentialforfutureresearch. It
offers several industrial applications in near future such as monitoring, surveillance,
commercial profiling and human computer interaction. Different methods have beenproposed
for gender classification like gait, iris and hand shape. However, majority of techniques for
gender classification are based on facial information. The proposed system uses skin tone
extraction, facial feature exaction and feature extraction is done using LBP. Classification is
done using Artificial Neural Network from that male and female isrecognized.

i
 TABLE OF CONTENT
CHAPTER NO TITLE PAGE NO
ABSTRACT i

LIST OF FIGURES ii

LIST OF TABLES iii

LIST OF ABBREVIATIONS 1
1 INTRODUCTION
1.1 DEFINITION 1

1.2 OBJECTIVE 2

1.3 SOFTWARE DESCRIPTION 3

2 SYSTEM OVERVIEW 6

2.1 EXISTING SYSTEM 6

2.2 PROPOSED SYSTEM 8

2.3 RELATED WORK 12

3 SYSTEM REQUIREMENTS 18

3.1 HARDWARE REQUIREMENTS 18

3.2 SOFTWARE REQUIREMENTS 18

4 SYSTEM DESIGN 19

4.1 SYSTEM ARCHITECTURE DESIGN 19

4.2 DIAGRAM 19

4.3 MODULES DESCRIPTION 23

5 SYSTEM IMPLEMENTATION 25

6 SAMPLE OUTPUT 32

7 CONCLUSION 41

REFERENCES 42
 LIST OF FIGURES

S. No Description Page No
1 Fig No 4.1 System Architecture Design 19
2 Fig No 4.2A Use Case Diagram 19
3 Fig No 4.2B Proposed Diagram 20
4 Fig No 4.2C Data Flow Diagram 21
5 Fig No 4.2D Sequence Diagram 21
6 Fig No 4.2E Block Diagram 22

7 Fig No 4.2F Concept Main Idea 22

8 Figure 1: Input Image 32

9 Figure 2: Noisy Image 32

10 Figure 3: Noise Removal Image 33
11 Figure 4: Detected Face 33
12 Figure 5: Eye Detection 34
13 Figure 6: Noise Detection 34
14 Figure 7: Mouth Detection 34
15 Figure 8: Facial Regions 35
16 Figure 9: Pointing the Facial Features 35
17 Figure 10: Result After Classification 35

ii
 LIST OF ABBREVIATIONS

PID Proportional Integral Derivative

BFGS Broyden – Fletcher – Goldfarb – Shanno
LBP Local Binary Pattern
MATLAB Matrix Laboratory
AI Artificial Intelligence
RGB Red; Green;Blue
YCbCr Luminance; Chroma: Blue; Chroma: Red
HSV Hue; Saturation; value
PCA Principal Component Analysis
NNC Nearest Neighbours Classifier
SVMs Support Vector Machines
BPNNs Back Propagation NNs
TDNN Time Delay Neural Network
FACS Facial Action Coding System