ABSTRACT

The motivation behind this project is to break down the profiles of informal organization clients to
decide the gender of the profile proprietor. To this end, various AI apparatuses have been utilized
and utilized in the field of portrayal from a site clarifying client choices. This study concludes that
there is a plethora of features which can be mined from a Social Media profile and can be used in
identifying the gender of a profile’s owner The review depends on online media and presumes
that there are numerous things that can be utilized to decide the gender of the personality
proprietor. Also, subsequent to inspecting online media data, studies have shown that this sexual
orientation personality exercise can be performed proficiently utilizing AI procedures with 97.30%.

v
 TABLE OF CONTENTS

Chapter No. Title Page No.

ABSTRACT v
LIST OF FIGURES vii
LIST OF ABBREVATIONS viii

1 INTRODUCTION 1

2 LITERATURE SURVEY 2

3 AIM AND SCOPE OF THE PRESENT

INVESTIGATION 6

4 EXPERIMENTAL OR MATERIALS AND

METHODS; ALGORITHMS USED 10

5 RESULTS AND DISCUSSION,

PERFORMANCE ANALYSIS 14

6 SUMMARY AND CONCLUSION 20

REFERENCES 21

vi
 LIST OF FIGURES

FIGURE NO. FIGURE NAME PAGE NO.

1. ARCHITECTURE DIAGRAM 8
2. SUPPORT VECTOR MACHINE HYPER PLANE 11

vii
 LIST OF ABBREVIATIONS

ABBREVIATION EXPANSION

CNN CONVOLUTION NEURAL NETWORK

SVM SUPPORT VECTOR MACHINE

LDA LINEAR DISCRIMINANT ANALYSIS

ELM EXTREME LEARNING MACHINE

ANN ARTIFICIAL NEURAL NETWORK

KNN K-NEAREST NEIGHBOUR

ID3 ITERATIVE DICHOTOMISER 3

viii
 CHAPTER 1

INTRODUCTION

Gender identification can be very useful in many different cases and for plenty of
reasons. First of all, it can be a valuable piece of information in the area of marketing.
As it is known, some recommender systems depend on features such as users’ age or
gender in order to make proper suggestions. Undoubtedly, there are certain items that
aren’t aimed at both male and female users so predicting consumer’s gender is the key
to an astute recommendation. Sven Ewan Shepstone et al. show a new method of
using automatic age and gender recognition to recommend a sequence of multimedia
items to a home TV audience comprising multiple viewers. As gender identification is an
aspect that concerns lots of scientists several methods have been proposed. First of all,
computer vision is a way to discriminate males from females.

1
 CHAPTER 2

LITERATURE SURVEY

Literature survey is the most important step in software development process. Before
developing the tool it is necessary to determine the time factor, economy and company
strength. Once these things are satisfied, then the next step is to determine which
operating system and language can be used for developing the tool. Once the
programmers start building the tool the programmers need lot of external support. This
support can be obtained from senior programmers, from book or from websites. Before
building the system the above consideration are taken into account for developing the
proposed system. The major part of the project development sector considers and fully
survey all the required needs for developing the project. For every project Literature
survey is the most important sector in software development process. Before
developing the tools and the associated designing it is necessary to determine and
survey the time factor, resource requirement, man power, economy, and company
strength. Once these things are satisfied and fully surveyed, then the next step is to
determine about the software specifications in the respective system such as what type
of operating system the project would require, and what are all the necessary software
are needed to proceed with the next step such as developing the tools, and the
associated operations.

Title 1: Gender Prediction from Images Using Deep Learning Techniques

Author: Salma Fayaz Bhat, Ab Waheed Lone, Taniya Ashraf Dar
Mechanized human age estimation by means of facial pictures is a vital and testing
errand and has bunches of potential in certifiable applications, especially since the
ascent of social stages and online networking. Hearty face affirmation structures are in
unbelievable demand to help fight bad behavior and mental mistreatment. Distinctive
applications join giving customer affirmation to get the opportunity to control to physical
and virtual spaces to ensure higher security. In any case the issue of recognizing a man
by taking a data stand up to picture and organizing with the known face pictures in a

2
database is now an amazingly troublesome issue. This is a result of the variability of
human faces under different operational circumstance conditions. For instance
edification, insurgencies, appearances, camera see centers, developing, beauty care
products, and eyeglasses. In this paper, a significant increase in accuracy of Gender
prediction can be obtained through the use of convolution neural networks (CNN) for
extracting features. Making the use of Convolution neural network (CNN) encompassed
with deep learning methods, state-of the art performance has been achieved. The
image-based Gender estimation is determined by performing extensive experiments on
the largest public available datasets of face images with Gender labels -IMDB-WIKI
dataset.

Title 2: Human Gender Classification using Machine Learning

Author: Miss. Vaishnavi Y. Mali, Dr. Babasaheb G. Patil

Human Gender classification is one of the most interested and critical area of research.
Research contains interactions between computers and human which includes vast
information concerning difference in characteristics of males and females. In several
kind of pattern recognition, machine learning gives a relation between gender and face.
This paper proposes comparison between different techniques used for gender
classification. Face is a unique biometric feature of the individual. Facial images with
different combinations including frontal, aligned, smiling, non-smiling as well as
expression images make the system complicated. Various face recognition methods
such as Convolutional neural networks, Delaunay triangulations, geometry based
methods like SVM (Support vector machine), LDA (Linear discriminant analysis).For
human gender classification, SVM provides better accuracy as compared with existing
methods.

Title 3: The construction of Chinese microblog gender-specific thesauruses and

user gender classification

Author: Zhiliang Zhu, Zejun Ke, Jiayin Cui, Hai Yu and Guoqi Liu

3
Based on the statistical features, short text messages published by different gender
users are different in terms of the words and semantics used. In this paper, two new
features are constructed after constructing a gender-specific thesaurus. A new
classification model is constructed by combining the traditional statistical features and
the improved text implicitness feature. The experimental evaluation performed on the
Sina Weibo dataset demonstrated the effectiveness of gender-specific thesaurus-based
features, and the improved text implicitness feature improved the accuracy of gender
classification to 84.7%.

Title 4: Age and Gender Prediction From Face Images Using Attentional
Convolutional Network

Author: Amirali Abdolrashidi, Mehdi Minaei, Elham Azimi, Shervin Minaee

In this work, we propose a deep learning framework, based on the ensemble of

attentional and residual convolutional networks, to predict gender and age group of
facial images with high accuracy rate. Using attention mechanism enables our model to
focus on the important and informative parts of the face, which can help it to make a
more accurate prediction. We train our model in a multi-task learning fashion, and
augment the feature embedding of the age classifier, with the predicted gender, and
show that doing so can further increase the accuracy of age prediction. Our model is
trained on a popular face age and gender dataset, and achieved promising results.
Through visualization of the attention maps of the train model, we show that our model
has learned to become sensitive to the right regions of the face.

Title 5: A hybrid deep learning CNN–ELM for age and gender classification

Author: MingxingDuan, KenliLi, CanqunYang, KeqinLi

Automatic age and gender classification has been widely used in a large amount of
applications, particularly in human-computer interaction, biometrics, visual surveillance,
electronic customer, and commercial applications. In this paper, we introduce a hybrid

4
structure which includes Convolutional Neural Network (CNN) and Extreme Learning
Machine (ELM), and integrates the synergy of two classifiers to deal with age and
gender classification. The hybrid architecture makes the most of their advantages: CNN
is used to extract the features from the input images while ELM classifies the
intermediate results.

Title 6: Gender Prediction Methods Based on First Names with genderizer

Author: Kamil Wais

In this paper, the author recommends a set of tools (including one dedicated to gender
prediction, the R package called genderizeR), data sources (including the genderize.io
API), and metrics that could be fully reproduced and tested in order to choose the
optimal approach suitable for different gender analyses.

Title 7: Age Group Classification using Convolutional Neural Network (CNN)

Author: Muhammad Firdaus Mustapha, Nur Maisarah Mohamad, Ghazali

Osman and Siti Haslini Ab Hamid

Age group classification is a complex task that is used to classify facial images or
videos into predetermined age categories. The proposed age group classification model
achieved 84.90% accuracy for the training images and 85.12% accuracy for the test
images. The experimental results showed that CNN is capable of achieving competitive
classification accuracy throughout two age groups in the AAF dataset with unbalanced
data distribution.

Title 8: Automated Detection of Gender from Face Images

Author: Revathi Ramachandran Nair, Reshma Madhavankutty, Dr. Shikha Nema

The project identifies or detects the gender from the given face images. The tools used
involve Convolutional Neural Network along with programming language like Python.
5
The project has been motivated by problems like lack of security, frauds, child
molestation, robbery, criminal identification.

CHAPTER 3

AIM AND SCOPE OF THE PRESENT INVESTIGATION

EXISTING SYSTEM
We compare our methods with existing machine learning methods applied to gender
identification including ANN and C4.5. We use the female ratios of each community
together with some explicit user profile attributes on Sina Weibo as features. We
adopted 10-fold cross validation on our 1,039 samples and show the identification
results of the proposed and existing methods , where the best performers of proposed
methods/existing supervised methods/text-based approaches are highlighted as bold
underline, respectively. From the results. Existing works on gender identification focus
on selecting text-based features manually and applying machine learning algorithms on
sample data collection to train classifiers.

DISADVANTAGES OF EXISTING SYSTEM

 Limited understanding of the machinery of classifiers (Black Box)

 Requires significant amount of data
 May not work in cases where data collection is difficult or expensive
 Problem of over-fitting if model fitted on small dataset.

PROPOSED SYSTEM

The proposed methodology with the main function of each processing step is as follows:

1. Data Collection: In this step, a great amount of Social Media profiles with all the
useful information were chosen and studied.

6
2. Feature Extraction: This step includes the procedure of extracting the features that
seem to come in handy in discriminating men from women.

3. Feature Selection: In this part, a group of the features which seem to be more
representative is selected.

4. Machine Learning Model: Here, a machine learning model is applied to identify the
gender of a profile owner, based on the features of the preceding steps.

The experimental results justified the initial theoretical claims, since the gender of the
Social Media profiles owners’ was identified by a significant accuracy level up to
97.30%.

The proposed methodology was high accurate, there is still room for further
improvement of the identification accuracy. This improvement can be achieved by
collecting more data from more Social Media profiles using an automated procedure
and by applying deep learning models which are able to tackle more data.

ADVANTAGES OF PROPOSED SYSTEM

 Large scale deployments of Machine Learning beneficial in terms of improved

speed and accuracy.
 Understands non-linearity in the data and generates a function mapping input to
output (Supervised Learning).
 Recommended for solving classification and regression problems.