Scribd
Upload
88 views

Gender Recognition From Image

This document discusses gender recognition from images. It begins with an introduction explaining that gender estimation from face images is an important task for applications like access control and human-computer interaction. The document then provides a brief history of early work in facial recognition from the 1960s. It describes gender recognition as a classification problem involving measuring nodal points on faces like eye and nose width to classify images as male or female. Finally, it discusses some technologies, applications, pros, and cons of gender recognition.

Uploaded by

Pråshãnt Shärmã
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
88 views

Gender Recognition From Image

This document discusses gender recognition from images. It begins with an introduction explaining that gender estimation from face images is an important task for applications like access control and human-computer interaction. The document then provides a brief history of early work in facial recognition from the 1960s. It describes gender recognition as a classification problem involving measuring nodal points on faces like eye and nose width to classify images as male or female. Finally, it discusses some technologies, applications, pros, and cons of gender recognition.

Uploaded by

Pråshãnt Shärmã
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/ 22

GENDER RECOGNITION

FROM IMAGE
Introduction
 Gender is a key facial attribute, play a very
foundational role in social interactions, making
gender estimation from a face image an important
task in intelligent applications.

 Some applications are:


Access Control
Human-Computer Interaction
Marketing Intelligence
Visual Surveillance
History
 During 1964 and 1965, Bledsoe, along with Helen Chan and
Charles Bisson, worked on using the computer to recognize
human faces.
 It was revealed that the Bledsoe's initial approach involved the
manual marking of various landmarks on the face such as
the eye centers, mouth, etc., and these were mathematically
rotated by computer to compensate for pose variation. The
distances between landmarks were also automatically computed
and compared between images to determine identity.
Gender Recognition
 Gender Prediction is a classification problem. The
output layer in the gender prediction network is
consists of 2 nodes indicating the two classes “Male”
and “Female”.

 Male and Female faces has different nodal points.


Using these points we can easily classify male and
female faces.
Nodes In Face
Gender Recognition
Here are few nodal points that are measured by software -
 Distance between eyes.
 Width of nose
 Cheek Bones
 Chin
 Jaw Lines
 Facial hair
 Eyebrows
Age Prediction

Even humans cannot accurately predict the age based on


looking at a person. However, we have an idea of
whether they are in their 20s or in their 30s. Because of
this reason, it is wise to frame this problem as a
classification problem where we try to estimate the age
group the person is in. For example, age in the range of
0-2 is a single class, 4-6 is another class and so on.
Technologies Used

 Python

 Machine Learning

 Convolutional Neural Networks


Applications
 Social Media
 Marketing Intelligence
 ID Verification
 Access Control
 Biometric access
Pros
 The Improvement of Security Level
  High Accuracy Rates
 Forget the Time Fraud
  Easy Integration Process
 Full Automation
Cons

 Processing & Storing


 Image Size & Quality
 Surveillance Angle
HOW IT WORKS…
CAPTURE
Non-Face Object Removal
Connected Components
Component Separation
Separated Components
Finding Faces with Template
Matching
High threshold for
accurate centre location.

Thresholding is the simplest


method of image segmentation.
thresholding can be used to
create binary images. During the
thresholdingprocess, individual pixels
in an image are marked as "object“
pixels if their value is greater than some
threshold value (assuming an object to be
brighter than the background) and as
"background" pixels otherwise.
Gender Detection
 Mean intensity.
 Template matching using
average of each female face.
 Biased towards missing
female faces to avoid
false-positive penalty (9:1).
Result
References..
https://www.upwork.com/hiring/for-clients/pros-cons-fac
ial-recognition-technology-business/
https://gist.github.com/GilLevi/c9e99062283c719c03de
https://ieeexplore.ieee.org/document/5328100
http://www.healthtechsydney.com.au/wp-content/uploads
/2016/02/facial-recognition-data-points.jpg

You might also like