MSP

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 6

JNANAVIKAS INSTITUTE OF TECHNOLOGY

Vidya Soudha, Padmashree G.D. Goyalgi Campus, Bangalore-Mysore Highway


Bidadi Bangalore-562109

DEPARTMENT OF COMPUTER SCIENCE &


ENGINEERING

MINI PROJECT SYNOPSIS


ON
"Advanced Facial Analytics"

DOMAIN BASED ON MACHINE LEARNING

Submitted By:
Harshitha B (1JV21CS019)
Pooja L (1JV21CS034)
Sonupriya B (1JV21CS053)
SEM:6TH

Under the Guidance of:


Rashmi U B
Assisstant Professor
Dept. of CSE
ABSTRACT

Age and gender detection using digital image processing is a mini project aimed at developing a
system that can automatically estimate the age and gender of a person based on their facial
features extracted from images. This project leverages the power of computer vision and image
processing techniques to analyze and interpret facial characteristics for age and gender
prediction. For age estimation, the project utilizes machine learning algorithms or statistical
models trained on a large dataset of labeled facial images with corresponding age information.
These models learn patterns and correlations between facial features and age, enabling them to
predict the age of a person based on their extracted features.
LITERATURE SURVEY

PAPER 1: https://ieeexplore.ieee.org/document/9688503

From the past few years, much exertion has been carried out for age assessment & recognition of
gender through face images. The images of Human’s faces uncover different data like gender,
age, and nationality. Computer vision and pattern recognition in the discipline of computer
vision represent an ideal role in human beings through automatic detection of face, recognition
of gesture and face, and finding age and gender. Here through the paper describes a survey on
predicting age and gender using face images. Various research has been developed on age and
gender prediction using various features like face features, body pose, MRI brain images, giants,
and pam. The face features can give more features for age and gender identification.

PAPER 2: https://ieeexplore.ieee.org/document/9377041

The human species has advanced to the point where the twenty-first century marks the start of
previously unimaginable achievements. By observing at a person using a camera, picture, or
video, the aforementioned technologies can be utilized to establish their age and gender. Our
project will walk you through the entire process, including the many approaches and algorithms
that can be used, which one is the most accurate, and how everything works together. It will also
highlight its importance and how it may be implemented to better our daily life. The major
purpose of this project is to develop a detector gender and age that can determine a person's
gender and age based on their performance Keeping track of the projected numbers and carrying
out the calculations Analyzing stored data aids in determining model accuracy.
SYSTEM ANALYSIS

EXISTING SYSTEM

There are several existing systems for age and gender detection that use various
techniques and algorithms to achieve accurate results. A deep learning approach for age and
gender classification based on facial images. The methodology involves preprocessing the
images to normalize lighting and orientation. A Convolution Neural Network (CNN) architecture
is utilized for feature extraction, leveraging transfer learning from pre-trained models like VGG
or ResNet. The model is trained on a large dataset of annotated facial images to classify age into
predefined categories (e.g., child, adolescent, adult) and gender as male or female. Experimental
results demonstrate high accuracy in age and gender prediction, with robustness against
variations in facial expressions and lighting conditions.

LIMITATIONS
 The model is still lagging in the accuracy while prediction
 In some model, the accuracy of the age prediction is 76.3% and the gender prediction is
86.6%.

PROPOSED SYSTEM

The proposed system for age and gender detection using Python CNN is designed to
overcome the limitations of existing systems and achieve high accuracy and efficiency in real-
world scenarios. The purpose of real-time age and gender detection integrated with live selfie
detection using computer vision and deep learning techniques. It aims to accurately estimate age
and gender in live video streams while identifying and prioritizing selfie frames in real-time. The
methodology includes efficient face detection and specialized selfie classifiers to enhance system
responsiveness. Lightweight CNNs are employed for age and gender estimation from facial
features, trained on diverse datasets for accuracy. Experimental validation demonstrates high
performance in real-time prediction and selfie detection integration. Applications include
interactive digital experiences, personalized advertising, and robust security systems. This
research contributes to advancing real-time computer vision for rapid, precise facial analysis and
recognition.

ADVANTAGES
 This model has overcome the accuracy issue
 We have integrated real time age and gender detection along with automatic selfie
capture using machine learning
SYSTEM REQUIREMENTS

HARDWARE REQUIREMENTS

 System : Intel core i5

 Main memory : 512 MB RAM

 Hard Disk : 40 GB

SOFTWARE REQUIREMENTS

 Operating System : Windows 8

 Domain : Machine Learning

 Scripts : Python

 Tool : Visual Studio

 Libraries: OpenCV, Math, argpase, keras and tensorflow


IMPLEMENTATION

Choose appropriate deep learning models, such as convolution neural networks (CNNs), for age
and gender estimation. Consider the model architectures, network depths, and existing pre-
trained models that can be leveraged for transfer learning. Select suitable frameworks, libraries,
and programming languages, such as Tensor Flow, Py Torch, or Keras, to implement the models.
Split the dataset into training and validation subsets. Train the age estimation model and gender
detection model separately using the training subset. Combine the trained age estimation and
gender detection models into a single integrated system.

Below mentioned are the three modules implemented in the project,


 Face detection module: The face detection module on a variety of images with different
facial poses and illumination conditions. Even in real time using web cam face is detected
to predict age and gender.

 Facial feature extraction module: The facial feature extraction module on images with
faces that have been detected by the face detection module. And facial features are
extracted in real time also.

 Age and gender detection module: The age and gender detection modules on images
with faces that have been detected and have facial features extracted by the other
modules.

You might also like