Scribd
Upload
164 views13 pages

Age & Gender Prediction

This document presents a project on using convolutional neural networks (CNNs) to predict age and gender from facial images. It discusses challenges with previous methods relying on manually designed features. The proposed model uses a CNN architecture trained on preprocessed images to classify age group and gender for applications like access control and surveillance. It aims to improve on state-of-the-art methods for unconstrained real-world images by designing robust preprocessing, pretraining the model on large datasets, and regularizing CNN parameters.

Uploaded by

priya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
164 views13 pages

Age & Gender Prediction

This document presents a project on using convolutional neural networks (CNNs) to predict age and gender from facial images. It discusses challenges with previous methods relying on manually designed features. The proposed model uses a CNN architecture trained on preprocessed images to classify age group and gender for applications like access control and surveillance. It aims to improve on state-of-the-art methods for unconstrained real-world images by designing robust preprocessing, pretraining the model on large datasets, and regularizing CNN parameters.

Uploaded by

priya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

AGE & GENDER

PREDICTION
PRESENTED BY
CH. DIVYA (18R11A0558)
A. KALYANI (18R11A0549)
G.GANESH (19R15A0508)
ABSTRACT

 Automatic prediction of age group and gender from face images acquired
in unconstrained conditions is an important and challenging task in many
real-world applications.
 Nevertheless, the conventional methods with manually-designed features
are unsatisfactory because of incompetency to tackle large variations in
unconstrained images.
 This difficulty is alleviated to some degree through Convolutional Neural
Networks (CNN) for its powerful feature representation.
 Age and gender, two of the key facial attributes, play a very foundational
role in social interactions.
 Making age and gender estimation from a single face image is an
important task in intelligent applications, such as access control, human-
computer interaction, law enforcement, marketing intelligence and visual
surveillance etc.
 The objective of the project is to build a gender and age predictor that can
approximately guess the gender and age of the person(face) in a picture.
REQUIREMENTS

 Hardware Requirements
● System : Intel core I3 or higher
● Hard disk : 1GB
● RAM : 4GB
 Software Requirements
● Operating System : Windows 7,8,10
● OpenCv-Python
● Numpy
EXISTING AND PROPOSED MODEL

 Age and gender classification techniques can improve computer’s


perceptional and interactional capabilities.
 Various applications for age and gender classification includes human-
computer interaction (HCI) can provide users appropriate and customized
services based on gender and age ground.
 Facial gender classification and age estimation have many challenges.
 Gender prediction is followed for two-class that can be male or female.
 It is easy for human but not for machine to classify gender easily.
 These conventional hand-engineered methods relied on the differences in
dimensions of facial features and face descriptors which do not have the
ability to handle the varying degrees of variation observed in these
challenging unconstrained imaging conditions.
 The images in these categories have some variations in appearance, noise,
pose, and lighting which may affect the ability of those manually designed
computer vision methods to accurately classify the age and gender of the
images.
 Recently, deep learning-based methods have shown encouraging
performance in this field especially on the age and gender classification of
unfiltered face images.
 we therefore propose a novel end-to-end deep learning-based classification
model that predicts age group and gender of unfiltered images using cnn
model.
 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. 
 We propose a model that uses CNN architecture to predict the age group
and gender of human’s faces from unfiltered real-world environments.
 The novel CNN approach addresses the age and gender labels as a set of
discrete annotations and train the classifiers that predict the human’s age
group and gender.
 We design a quality and robust image preprocessing algorithm that prepare
and preprocess the unfiltered images for the CNN model and this greatly
has a very strong impact on the performance accuracy of our age and
gender classifiers.
 Despite the very challenging nature of the images in the dataset, our
approach produces significant improvements in age group and gender
classification accuracy over the state-of-the-art methods; the result can
satisfy the requirements of several real-world applications.
LITERATURE SURVEY

 Almost all of the early methods in age and gender classifications were
handcrafted, focussing on manually engineering the facial features from
the face and mainly provides a study on constrained images that were
taken from controlled imaging conditions. 
 In 1999, Kwon and Lobo developed the very first method for age
estimation focusing on geometric features of the face that determine the
ratios among different dimensions of facial features.
 Hence, in 2004, Lanitis et al. [30] proposed an Active Appearance Model
(AAM) based method that included both the geometric and texture
features, for the estimation task. 
 This method is not suitable for the unconstrained imaging conditions
attributed to real-world face images which have different degrees of
variations in illumination, expression, poses, and so forth.
 From 2007, most of the approaches also employed manually designed
features for the estimation task
 However, it is still a challenging problem classifying unconstrained faces
with large variations in illumination, viewpoint, nonfrontal, etc.
 There is a need for a suitable and robust model that can improve the state-
of-the-art methods for its applicability in intelligent and real-world
applications.
 Here, we address those issues by designing a robust image preprocessing
algorithm, pretrain the model on large-scale facial aging benchmarks with
noisy age and gender labels, and also regularize the CNN parameters with
our novel CNN framework.
THANK YOU!!

You might also like