Face Recognition

FACE RECOGNITION

PRESENTED BY:

AYUSHI SAXENA

120271

1

Outline1. Introduction

2. Biometrics

3. How it works

4. Comparison

5. Stages of identification

6. Implementation

7. Strengths & Weaknesses

8. Applications

9. Conclusion

10. References

2

What is Face Recognition? 3

Introduction

• A Computer Application.

• Automatic identification or verification of a person or an object.

•Can be used on a digital image or a

video.

•Can be compared other biometrics such

as fingerprint.

4

WHAT IS BIOMETRICS ?• Biometrics refers to the identification of humans

by their characteristics or traits.

• In physiological:

Finger scan

Facial recognition

Retina-scan

Hand-scan

• Behavioural biometrics include:

Voice-scan

Signature-scan

5

HOW FACE RECOGNITION WORKS ?

6

Detection- When the system is attached to a video surveillance system, the recognition software searches the field of view of a video camera for faces.

Alignment- Once a face is detected, the system determines the head's size and position. A face needs to be turned at least 35 degrees toward the camera for the system to register it.

7

Normalization- Normalization is performed regardless of the head's location and distance from the camera. Light does not impact the normalization process.

Representation- The system translates the facial data into a unique code. This coding process allows for easier comparison of the newly acquired facial data to stored facial data.

8

Matching- The newly acquired facial data is compared to the stored data and (ideally) linked to at least one stored facial representation.

9

COMPARISON

1) IDENTFICATION

- figure out “Who is X?”

- accomplished by system performing a“one-to-many ”

search

10

2) VERIFICATION

- answer the question “Is this X?”- accomplished by the system

performing a “one-to-one” search

11

12STAGES OF IDENTIFICATION

Capture Extraction ComparisonMatch/Non

match

Accept/Project

Capture- Capture the behavioral sampleExtraction- Unique data is extracted from the sample and a template is created.Comparison- The template is compared with a new sample.Match/non match- The system decides whether the new samples are matched or not.

13

implement of face recognition

data acquisition

input processing

face image classification anddecision making

14

Data acquisition:

The input can be recorded video of thespeaker or a still image. A sample of 1 secduration consists of a 25 frame videosequence.

More than one camera can be used toproduce a 3D representation of the faceand to protect against the usage ofphotographs to gain unauthorized access

15

Input processing:

A pre-processing module locates the eyeposition and takes care of the surroundinglighting condition and colour variance.Firstly the scene is detected of faces orface in a scene must be detected. Oncethe face is detected, it must be localized.

Some facial recognition approaches use ofthe whole face while others concentrateon facial components and/or regions.

16

Face image classification and decision making

Synergetic computer are used to classify optical and audio features, respectively.

A synergetic computer is a set of algorithm that simulate synergetic phenomena.

A newly recorded pattern is preprocessed and compared with each faceprint stored in the database. As comparisons are made, the system assigns a value to the comparison using a scale of one to ten. If a score is above a predetermined threshold, a match is declared.

17

ADVANTAGES AND DISADVANTAGESADVANTAGES:

• Fast and convenient in identifying a person

• Social acceptability

• Inexpensive technique of identification

• Great use in society:

- crime detection

- security use

18

DISADVANTAGES:1) Problem with false rejection when people change their hair style, grow or shave a beard or wear glasses.2) Change of facial characteristics –wearing of glasses.3) Face recognition systems can’t tell the difference between identical twins.

19

APPLICATIONS

Commercial Use:a. Day Care: Verify identity of individuals picking up the children.b. Residential Security: Alert homeowners of approaching personnel.c. Voter verification: Where eligible politicians are required to verify their identity during a voting process.d. Banking using ATM: The software is able to quickly verify a customer.

20

Applications Available in Market

Face Recognition based Time Attendance System

• Fastest and safest method of tracking employee

time and attendance.

• Easy to install and use.

• Cost saving and convenient way of time tracking.

• Provide easy and efficient way of

recording attendance.

• Easily manage employee time and attendance profiles.

21

Facial Recognition PC Security

• Logon and a PC camera only provides access when a live-feed face image of an authorized user is detected, effectively preventing unauthorized access.

• Fast & Secured Login Process.

22

NameTag

NameTag lets strangers get a broad range of personal information—including a person’s name, photos, and dating website profiles—simply by looking at that person’s face with the Glass camera.

Using the NameTag smartphone or Google Glass app, simply snap a pic of someone you want to connect with and see their entire public online presence in one place.

23

24

25

ConclusionFace recognition technologies have been

associated generally with very costly top secure applications. Today the core technologies have evolved and the cost of equipments is going down dramatically due to the integration and the increasing processing power. Certain applications of face recognition technology are now cost effective, reliable and highly accurate.

26

References

http://www.face-rec.org/general-info/

http://www.nametag.ws/

http://www.dailymail.co.uk

http://electronics.howstuffworks.com

http://www.arcticstartup.com

27

28

29