GENDER AND

AGE
DETECTION
Using OpenCV
Team CSE A-4

Project Guide: Team Members:

Dr. S. Zahoor UI Huq, K Swarna Kanth Reddy

Professor, S Yaswanth Reddy
Department of CSE, A Sai Kiran
GPREC
Abstract
• For a machine to detect the age and gender of a person in an image/video is a
challenging task.
• Facial analysis from images has gained a lot of interest because it helps in
several different problems like better ad targeting for customers, better content
recommendation system, security surveillance, and other fields as well.
• The paramount objective of the project is to build a gender and age detector
that can approximately guess the gender and age of the face of an individual in
a picture/webcam using Deep Learning on the UTKFace dataset.
Literature Survey
Year of Evaluation
Publication Models Dataset Used Metric Results

Accuracy
Abhijit Das 2019 FaceNet UTKFace Accuracy for race
%
ResNet BEFA 84%, gender 94%
et al. Confusion
and age 72%.
(Version 1) Matrix
Mean
The best gender
Confusion
accuracy for
Gil Levi et Deep CNN Adience Matrix
2015 proposed method
Accuracy
al. %
86%
The age best
Standard accuracy for
error proposed method
85%
Nisha 2017
CNN with a single branch
Wild East- Confusion Accuracy results
architecture CNN with for age, gender,
Srinivas et Asian Face Matrix
multiple and exact
al. branches Dataset Accuracy
ethnicity are
architecture (WEAFD) %
38%, 88%, 33%.

2018 Lightweight Adience Training Showing age and

Jia-Hong Multi-task Validation gender accuracy
Lee et al. CNN Accuracy% of 44% and 85%
(LMTCNN)
Existing System
• Over the past years, a lot of methods have been proposed to solve the
classifications problem. Many of those methods are handcrafted which
perform unsatisfactorily on the age and gender predictions of
unconstrained in-the-wild images.
• Gender classification is a binary classification problem, which can be
stated as inferring female or male from a collection of facial images.
Although there exist different methods for gender classification, such as
gait, iris, hand shape and hair, yet the prominent methods to achieve
the goal is based on facial features.
Proposed System
• In light of the current works in age and gender classification and encouraging signs
of progress in deep learning and CNN, we therefore propose a novel end-to-end
deep learning-based classification model that predicts age group and gender of
unfiltered in-the-wild facial images.
• We formulate the age and gender classifications task as a classification problem in
which the CNN model learns to predict the age and gender from a face image.
Marketing Strategy | Fiscal Year 2020

06

Proposed System
 Hardware Requirements Software Requirements

• i3 or higher Processor • Sypder (Anaconda)

based Computer • Packages-
• 4GB
. - RAM Keras,Tensorflow,Numpy,
Sklearn,OpenCV,MatplotLib
• Dataset
Methods and Techniques
CNN Based Age and Gender Classification:
• A method for estimating gender and age of a face image based on deep learning is
developed by applying a CNN-based learning method composed of 6 layers of hidden
layers.
• The objective of the Convolution Operation is to extract the high-level features such
as edges, from the input image. ConvNets need not be limited to only one
Convolutional Layer.
• The architecture performs a better fitting to the image dataset due to the reduction in
the number of parameters involved and reusability of weights.
Convolution Neural Network
-Convolution layer
-Maxpooling
-Flatten
OpenCV
• It is an open-source Computer Vision and
Machine Learning library.
• This library is capable of processing real-time
image and video while also boasting
analytical capabilities.
• It supports the Deep Learning frameworks
TensorFlow, Caffe, and PyTorch.
Dataset
• UTKFace Dataset - Kaggle Website
 Features of the Datase

• UTKFace dataset is a large-scale face dataset with long age

span (range from 0 to 116 years old). The dataset consists of
over 20,000 face images with annotations of age, gender, and
ethnicity.
• The images cover large variation in pose, facial expression,
illumination, occlusion, resolution, etc.
• This dataset could be used on a variety of tasks, e.g., face
detection, age estimation, age progression/regression,
landmark localization, etc.
Required
Features of Dataset

The labels of each face image is embedded in the file name,

formated like [age]_[gender]_[race]_[date&time].jpg
• [age] is an integer from 0 to 116, indicating the age
• [gender] is either 0 (male) or 1 (female)
 SCREENSHOTS OF
PROJECT
IMPLEMENTATION
Thank you!