Scribd
Upload
35 views

First Progress Report

The document describes a face detection system created by Vineet Thakur for their university degree. It will use MATLAB for image processing and the Viola-Jones algorithm to detect faces, then nose, mouth, and eyes. It compares the system to Amazon Rekognition, which provides commercial facial recognition for objects, scenes, faces, text, and inappropriate content detection at scale. The student's system is designed for individual universities to identify students from photos rather than real-time detection or custom labeling like Amazon's system. Screenshots demonstrate running the face, nose, and eye detection algorithms on a sample image.

Uploaded by

Vineet Thakur
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
35 views

First Progress Report

The document describes a face detection system created by Vineet Thakur for their university degree. It will use MATLAB for image processing and the Viola-Jones algorithm to detect faces, then nose, mouth, and eyes. It compares the system to Amazon Rekognition, which provides commercial facial recognition for objects, scenes, faces, text, and inappropriate content detection at scale. The student's system is designed for individual universities to identify students from photos rather than real-time detection or custom labeling like Amazon's system. Screenshots demonstrate running the face, nose, and eye detection algorithms on a sample image.

Uploaded by

Vineet Thakur
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 12

FACE DETECTION SYSTEM

Submitted in partial fulfillment of the requirements for the award of degree of


BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE & ENGINEERING

Submitted to: Submitted by:


Er. KULVINDER SINGH​ ​VINEET THAKUR
18BCS2109

​DEPARTMENT OF COMPUTER SCIENCE & ENGINEERING


Chandigarh University, Gharuan
August 2020
PROJECT DESIGN
The main component of our software is that it is going to do the image processing. It is going to
capture the image then take it and then process it. After processing it then it will check it with the
database with whom it resembles. If it is a match then it will show the details of the person
otherwise it will say not found.

To do the image processing we are going to use a software MATLAB.


We are going to use it to do image processing because it has inbuilt tools for it, we can also
include other toolbox as per requirement.
Below I’m going to give the basic explanation of the steps that I’m going to perform do the
image processing.
We are going to use Computer vision system toolbox(image below)
We are going to Detect objects using Viola-Jones Algorithm.The Viola–Jones object detection
framework is the first object detection framework to provide competitive object detection rates in
real-time proposed in 2001 by Paul Viola and Michael Jones. Although it can be trained to detect
a variety of object classes, it was motivated primarily by the problem of face detection.

First we will choose an image to use


As we have selected an image we will detect faces in the image

Then we will detect the nose


After that we will detect the mouth

And in last we will detect the eyes


These are the basics of the face detection we are going to use. The step by step algorithm is
going to be used to detect the face.
Sometimes the image is not very clear then we are going to some options to clear the image by
improving contrast like below

When the code will be completed then we will convert it into an exe file. So that it can be used as
an application.

We already know that Amazon have a facial recognition system i.e


They provide video media and image facial detection.

What is Amazon Rekognition Image?

Rekognition Image is a deep learning powered image recognition service that detects objects,
scenes, and faces; extracts text; recognizes celebrities; and identifies inappropriate content in
images. It also allows you to search and compare faces. Rekognition Image is based on the same
proven, highly scalable, deep learning technology developed by Amazon’s computer vision
scientists to analyze billions of images daily for Prime Photos. The service returns a confidence
score for everything it identifies so that you can make informed decisions about how you want to
use the results. In addition, all detected faces are returned with bounding box coordinates, which
is a rectangular frame that fully encompasses the face that can be used to locate the position of
the face in the image.
Key features

● Object and Scene Detection


Rekognition Image identifies thousands of objects such as vehicles, pets, and furniture.
Rekognition also detects scenes within an image, such as a sunset or beach. This makes it
easy for you to search, filter, and curate large image libraries.

● Facial Recognition
Rekognition Image enables you to find similar faces in a large collection of images. You
can create an index of faces detected in your images. Rekognition Image’s fast and
accurate search returns faces that best match your reference face.

● Facial Analysis
With Rekognition Image, you can locate faces within images and analyze face attributes,
such as whether or not the face is smiling or the eyes are open. When analyzing an image,
Rekognition Image will return the position and a rectangular frame for each detected
face.

● Face Comparison
Rekognition Image lets you measure the likelihood that faces in two images are of the
same person. With Rekognition, you can use the similarity score to verify a user against a
reference photo in near real time.

● Unsafe Image Detection


Rekognition Image enables you to detect explicit and suggestive content so that you can
filter images based on your application requirements. Rekognition provides a hierarchical
list of labels with confidence scores to enable fine-grained control over what images you
want to allow.
● Celebrity Recognition
Rekognition Image detects and recognizes thousands of individuals who are famous,
noteworthy, or prominent in their field. This allows you to index and search digital image
libraries for celebrities based on your marketing and media needs.
● Text In Image
With Rekognition Image, you can easily locate and extract text within images, including
text in natural scenes such as road signs or license plates, text over objects such as t-shirts
or mugs, and text on screen such as captions or news. When analyzing an image, Text in
Image will return the detected text label, a rectangular frame, along with a confidence
score, for each detected word and line.

● Administration via API, Console, or Command Line


Amazon Rekognition can be accessed using the Amazon Rekognition API, AWS
Management Console, and the AWS command-line interface (CLI). The console, API,
and CLI provide the ability to use the Rekognition APIs to detect labels, analyze faces,
compare faces, and find a face. AWS Lambda has blueprints for Rekognition that make it
easy to initiate image analysis based on events in your AWS data stores such as Amazon
S3 and Amazon DynamoDB.

● Administrative Security
Amazon Rekognition is integrated with AWS Identity and Access Management (IAM).
IAM policies can be used to control access to the Amazon Rekognition API as well as
manage resource-level permissions for your account.
Innovation in model/design/solution
The most basic thing about this is that this model isn’t going to be used as a single corporation
like Amazon Facial Rekognition. We can sell this software to individual education institutes
because their database is not that big. Most of the universities have around 10000-15000 people
including staff members.

Their images can be stored by the university on their own server. We are not using real time face
detection because it requires more hardware and it can be hard to use and maintain by common
people.

If we compare our design from Amazon Facial Rekognition they provide a vast range like Image,
video and custom labeling. But we are going to use simple image processing to do it. Amazon
has different pricing for the images being processed. More images you process, the less you have
to pay. It is great marketing but they are using this to train their own models.
It will help them drastically to improve their technology. They have provided their Facial
Rekognition technology to US police and army to help find the criminals.

As we know that the Facial Recognition technology is still developing we have a lot to grow and
develop in this field.
Implementation (at least 40%)
Below are some screenshots of the implemented algorithm.
The command used

The image used


The output for detecting
Face

Nose

Eyes

You might also like