Scribd
Upload
80 views3 pages

Age and Gender Detection 2

The document proposes an algorithm to accurately identify gender and age from a single face image using deep learning models. It involves using pre-trained convolutional neural networks to perform feature extraction from the image, classify gender as male or female, and estimate age from 8 predefined ranges. The gender classifier returns 1 for male and 0 for female, while the age classifier returns an integer between 0-7 corresponding to the different age ranges. The proposed pipeline first detects the face, then predicts gender using one CNN model and age using another similar CNN model to analyze features and output classifications. It is evaluated on the public Adience dataset containing over 26,000 photos.

Uploaded by

Anurupa bharti
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
80 views3 pages

Age and Gender Detection 2

The document proposes an algorithm to accurately identify gender and age from a single face image using deep learning models. It involves using pre-trained convolutional neural networks to perform feature extraction from the image, classify gender as male or female, and estimate age from 8 predefined ranges. The gender classifier returns 1 for male and 0 for female, while the age classifier returns an integer between 0-7 corresponding to the different age ranges. The proposed pipeline first detects the face, then predicts gender using one CNN model and age using another similar CNN model to analyze features and output classifications. It is evaluated on the public Adience dataset containing over 26,000 photos.

Uploaded by

Anurupa bharti
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

INTRODUCTION

Age and gender, two key facial attributes, play a really foundational role in social
interactions, making age and gender estimation from one face image a very important task in
machine learning applications, like access control, human-computer interaction, law
enforcement, marketing intelligence and visual surveillance. It plays a very important role in
an exceedingly wide selection of the real-world applications like targeted advertisement,
forensic science, visual surveillance, content-based searching, human computer interaction
systems, etc. for instance we are able to use this method to display advertisement supported
different gender and different age bracket.

Human face may be a storehouse of various information about personal characteristics,


including identity, emotional expression, gender, age, etc. the looks of face is affected
considerably by aging. This plays a significant role in non verbal communication between
humans. Age and gender, twokey facial attributes, play a really foundational role in social
interactions, making age and gender estimation from one face image a very important task in
machine learning applications, like access control, human-computer interaction, law
enforcement, marketing intelligence and visual surveillance. Automatic gender classification
and age detection may be a fundamental task in computer vision, which has recently attracted
immense attention. It plays a very important role in an exceedingly wide selection of the real-
world applications like targeted advertisement, forensic science, visual surveillance, content-
based searching, human computer interaction systems, etc. for instance we are able to use this
method to display advertisement supported different gender and different age bracket. This
method may be employed in different mobile applications where there's some age restricted
content in order that only appropriate user can see this content. However, gender
classification and age approximation is still a difficult task. We propose a model which can
first perform feature extraction on the input image which can classify eyes, lips, beard, hair,
etc. Supported these features the model will classify the gender as male or female. We've
used Haar Cascade for feature extraction purpose. Age is estimated with the assistance of
Caffe Model. The age classifier takes an image of an individual's face of size 256x256 as an
input to the algorithm that's then cropped to 227x227. The age classifier returns a integer
representing the age range of the individual. There are 8 possible age ranges , that the age
classifier returns an integer between 0 and seven. The gender classifier returns a binary result
where 1 indicates male and 0 represents female.
PROPOSED ALGORITHM
In our Project, we had used Deep Learning to accurately identify the gender and age of a
person from a single image of a face. We used the models trained by Tal Hassner and Gil
Levi. The predicted gender may be one of ‘Male’ and ‘Female’, and the predicted age may be
one of the following ranges- (0 – 2), (4 – 6), (8 – 12), (15 – 20), (25 – 32), (38 – 43), (48 –
53), (60 – 100) (8 nodes in the final softmax layer). It is very difficult to accurately guess an
exact age from a single image because of factors like makeup, lighting, obstructions, and
facial expressions. And so, we made this a classification problem instead of making it one of
regression.

1. Gender and Age Classification using CNNs


1.1 The CNN Architecture

The network architecture used for age approximation in based on the paper of [2]G.Levi and
T.Hassner. This network is intended to be shallow to prevent over-fitting.

Fig 1 : Illustration of CNN architecture.

The convolutional neural network for this python project has 3 convolutional layers:

 Convolutional layer; 96 nodes, kernel size 7


 Convolutional layer; 256 nodes, kernel size 5
 Convolutional layer; 384 nodes, kernel size 3
 It has 2 fully connected layers, each with 512 nodes, and a final output layer of
softmax type.
2. To go about the python project, we’ll:
2.1. Detect Face

We will use the DNN Face Detector for face detection. The model is only 2.7MB and is
pretty fast even on the CPU

2.2. Predict Gender

We will load the gender network into memory and pass the detected face through the
network. The forward pass gives the probabilities or confidence of the two classes. We take
the max of the two outputs and use it as the final gender prediction.

2.3. Predict Age

We load the age network and use the forward pass to get the output. Since the network
architecture is similar to the Gender Network, we can take the max out of all the outputs to
get the predicted age group.

2.4. Display Output

We will display the output of the network on the input images and show them using the
imshow function.

3. The Dataset

For this python project, we’ll use the Adience dataset; the dataset is available in the public
domain and you can find it here. This dataset serves as a benchmark for face photos and is
inclusive of various real-world imaging conditions like noise, lighting, pose, and appearance.
The images have been collected from Flickr albums and distributed under the Creative
Commons (CC) license. It has a total of 26,580 photos of 2,284 subjects in eight age ranges
(as mentioned above) and is about 1GB in size. The models we will use have been trained on
this dataset.

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy