FACIAL RECOGITION SYSTEM

FACIAL RECOGITION SYSTEM

INTRODUCTION
A facial recognition system is a technology capable of identifying or verifying a person from a
digital image or a video frame from a video source. There are multiple methods in which facial
recognition systems work, but in general, they work by comparing selected facial features from
given image with faces within a database. It is also described as a Biometric Artificial
Intelligence based application that can uniquely identify a person by analyzing patterns based on
the person's facial textures and shape.

While initially a form of computer application, it has seen wider uses in recent times on mobile
platforms and in other forms of technology, such as robotics. It is typically used as access control
in security systems and can be compared to other biometrics such as fingerprint or eye iris
recognition systems. Although the accuracy of facial recognition system as a biometric
technology is lower than iris recognition and fingerprint recognition, it is widely adopted due to
its contactless and non-invasive process. Recently, it has also become popular as a commercial
identification and marketing tool. Other applications include advanced human-computer
interaction, video surveillance, automatic indexing of images, and video database, among others.

This project will act as an Attendance System in which the attendance of a person will be marked
by recognizing the person from a camera installed at the entry point of an organization. This will
eliminate the need of human interaction with the traditional attendance systems like hand written
attendance or even fingerprint based attendance system.

The project will have an interface, a web app, where the authorized person can view the
attendance logs and even train the system for a new person or remove the data of an existing
person who might have left the site permanently.

Tecnology Used - Computer Vision

Computer vision is an interdisciplinary scientific field that deals with how computers can be
made to gain high-level understanding from digital images or videos. From the perspective of
engineering, it seeks to automate tasks that the human visual system can do.

1
 FACIAL RECOGITION SYSTEM

Computer vision tasks include methods for acquiring, processing, analyzing and understanding
digital images, and extraction of high-dimensional data from the real world in order to produce
numerical or symbolic information, e.g. in the forms of decisions. Understanding in this context
means the transformation of visual images (the input of the retina) into descriptions of the world
that can interface with other thought processes and elicit appropriate action. This image
understanding can be seen as the disentangling of symbolic information from image data using
models constructed with the aid of geometry, physics, statistics, and learning theory.

The scientific discipline of computer vision is concerned with the theory behind artificial
systems that extract information from images. The image data can take many forms, such as
video sequences, views from multiple cameras, or multi-dimensional data from a medical
scanner. The technological discipline of computer vision seeks to apply its theories and models
to the construction of computer vision systems.

Sub-domains of computer vision include scene reconstruction, event detection, video tracking,
object recognition, 3D pose estimation, learning, indexing, motion estimation, and image
restoration

Computer Vision in Facial Recognition

Computer vision also plays an important role in facial recognition applications, the technology
that enables computers to match images of people’s faces to their identities. Computer vision
algorithms detect facial features in images and compare them with databases of face profiles.
Consumer devices use facial recognition to authenticate the identities of their owners. Social
media apps use facial recognition to detect and tag users. Law enforcement agencies also rely on
facial recognition technology to identify criminals in video feeds.

Technical Terms

 Histogram of Oriented Gradients (HOG)

HOG stands for Histograms of Oriented Gradients. HOG is a type of “feature descriptor”.
The intent of a feature descriptor is to generalize the object in such a way that the same
object (in this case a person) produces as close as possible to the same feature descriptor
when viewed under different conditions. This makes the classification task easier.

2
 FACIAL RECOGITION SYSTEM

 SIFT (Scale-Invariant Feature Transform)

SIFT: Scale-invariant feature transform (SIFT) feature descriptors describe keypoints in
an image. The image patch of the size 16 × 16 around the keypoint is taken. This patch is
divided in 16 distinct parts of the size 4 × 4. For each of those parts a histogram of 8
orientations is calculated similar as for HOG features. This results in a 128-dimensional
feature vector for each keypoint. It should be emphasized that SIFT is a global feature for
a complete image.

 Non-Maximum Suppression 
It is often used along with edge detection algorithms. The image is scanned along the
image gradient direction, and if pixels are not part of the local maxima they are set to zero.

FEASIBILTY STUDY
Need of Facial Recognition Systems

Faster processing

The process of recognizing a face takes a second or less — and this is incredibly beneficial for
the companies. In the era of constant cyber-attacks and advanced hacking tools, companies need
a technology that would be both secure and fast. Considering that facial recognition is almost
instant, it grants a quick and efficient verification of a person. In addition, it’s hard to fool this
technology so this is another bonus.

Seamless integration

This is probably one of the biggest benefits for companies. The facial recognition technology is
quite easily integrated so it’s a perfect choice. It does not require spending additional money on
its integration and most facial recognition solutions are compatible with the majority of security
software. A 100% win-win.

Automation of identification

Before, security guards had to perform manual identification of a person that took too much time
and did not boast high accuracy. But today, facial recognition is completely independent in the
identification process and not only takes seconds but is also incredibly accurate. The 3D facial

3
 FACIAL RECOGITION SYSTEM

recognition technology and the use of infrared cameras significantly boosted the level of
accuracy of facial recognition and made it really hard to fool.

Significance of Facial Recognition Systems

One of the major advantages of facial recognition technology is safety and security. Law
enforcement agencies use the technology to uncover criminals or to find missing children or
seniors. In New York, police were able to apprehend an accused rapist using facial recognition
technology within 24 hours of an incident where he threatened a woman with rape at knifepoint.
In cities where police don’t have time to help fight petty crime, business owners are installing
facial-recognition systems to watch people and identify subjects of interest when they come in
their stores.
Airports are increasingly adding facial recognition technology to security checkpoints; the U.S.
Department of Homeland Security predicts that it will be used on 97 percent of travelers by
2023. When people know they are being watched, they are less likely to commit crimes so the
possibility of facial recognition technology being used could deter crime.
Facial recognition can add conveniences. In addition to helping you tag photos in Facebook or
your cloud storage via Apple and Google, you will start to be able to check-out at stores without
pulling out money or credit cards—your face will be scanned. At the A.I. Bar, facial recognition
technology is used to add patrons who approach the bar to a running queue to get served their
drinks more efficiently.

OBJECTIVES

• To mark attendance automatically without any effort from the person.

• To understand how computer vision is implemented and how images can be used as a
training data.
• To explore the various use cases of computer vision and it can be used to make our lives
easier.
• To explore the various career paths in Computer Vision (Artificial Intelligence).

4
 FACIAL RECOGITION SYSTEM

METHODOLOGY

The Machine Learning Process

Setting up an architecture for machine learning systems and applications requires a good insight
in the various processes that play a crucial role.

So to develop a good architecture you should have a solid insight in:

 The business process in which your machine learning system or application is used.
 The way humans interact or act (or not) with the machine learning system.
 The development and maintenance process needed for the machine learning system.
 Crucial quality aspects, e.g. security, privacy and safety aspects.

In its core a machine learning process exist of a number of typical steps. These steps are:

 Determine the problem you want to solve using machine learning technology.
 Search and collect training data for your machine learning development process.
 Select a machine learning model.
 Prepare the collected data to train the machine learning model.
 Test your machine learning system using test data.
 Validate and improve the machine learning model. Most of the time you will need to
search for more training data within this iterative loop.

You will need to improve your machine learning model after a first test. Improving can be done
using more training data or by making model adjustments.

5
 FACIAL RECOGITION SYSTEM

Figure 1.2.3.1 - The Machine Learning Process

HARDWARE / SOFTWARE REQUIREMENTS

HARDWARE REQUIREMENTS
 Minimum 1 GB RAM
 2 GB free disk space

SOFTWARE REQUIREMENTS
 A Browser

BIBLIOGRAPHY
 https://www.forbes.com/sites/bernardmarr/2019/08/19/facial-recognition-technology-
here-are-the-important-pros-and-cons/#ab443f014d16
 https://electronics.howstuffworks.com/gadgets/high-tech-gadgets/facial-
recognition.htm
 https://arxiv.org/abs/1503.03832
 https://www.howtogeek.com/427897/how-does-facial-recognition-work/
 https://docs.opencv.org/2.4/
 https://www.tensorflow.org/guide
 https://www.tensorflow.org/tutorials