Scribd
Upload
39 views29 pages

Final Presentation

Face recognition technology can be used to identify or verify individuals from images or video. It uses biometrics like distance between eyes, nose width, and jawline to measure unique physical characteristics. The basic processes involve detection, alignment, measurement, representation and matching of faces. Two main types of technologies are 2D and 3D. Facial recognition algorithms like Eigenfaces, Local Feature Analysis, Neural Networks and Automatic Face Processing are used to identify features. The system presented applies these techniques to applications like security access, attendance systems and law enforcement by detecting faces and matching them to stored images.

Uploaded by

Rashmita Gouda
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
39 views29 pages

Final Presentation

Face recognition technology can be used to identify or verify individuals from images or video. It uses biometrics like distance between eyes, nose width, and jawline to measure unique physical characteristics. The basic processes involve detection, alignment, measurement, representation and matching of faces. Two main types of technologies are 2D and 3D. Facial recognition algorithms like Eigenfaces, Local Feature Analysis, Neural Networks and Automatic Face Processing are used to identify features. The system presented applies these techniques to applications like security access, attendance systems and law enforcement by detecting faces and matching them to stored images.

Uploaded by

Rashmita Gouda
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 29

FACE RECOGNITION

TECHNOLOGY
PRESENTED BY

1
What is face recognition system?

A face recognition system is a


computer application for
automatically identifying or
verifying a person from a digital
image or video frame from a video
source

2
What is Biometrics?
Biometrics is a unique measurable
characteristics of human being that can be
used to recognize an individual or verify an
individuals identity.
It can measures both physical &
behavioral characteristics.

3
Basic processes:
Detection
Alignment
Measurement
Representation
Matching
Identification

4
Two types of technologies
are used
2-D technology
3-D technology

5
Features to be measured:
Distance between eyes
Width of the nose
Depth of eye socket
Cheek bones
Jaw line
chin

6
Facial Biometrics
Algorithms:

Eigen Face
Local Feature Analysis
Neural Network
Automatic Face Processing

7
1.Eigen Face
These are nothing less than the characteristic
features of the faces. These are a set of
standardized ingredients
One person’s face might be made up 10% of
face1,24% of face2 & so on. This means that if
you want to record someone’s face for use by
face recognition software you can use for less
space.
Face is then mapped to series of Eigen vectors

8
9
2.Local Feature Analysis:
We represent a face as a graph whose nodes
positioned in correspondence to the facial
fiducial points.
Better than the other in terms of rotation, light &
scale invariance.
Localizes the face & facial features, extracts the
facial fiducial points, determine the head pose &
thus the gallery to be used for comparision &
compares the face with the gallery image.

10
11
3.Neural Network
A Neural Network is a system of programs
and data structures that approximates the
operation of the human brain.
A program can then tell the network how
to behave in response to an external
stimulus or can initiate activity on its own.

12
MODEL OF NEURON

13
How Neural Network Works:
A neural network is used to create the face
database and recognize the face.
separate network for each person.
The input face is projected onto the eigenface
space first and get a new descriptor.
The new descriptor is used as network input and
applied to each person's network. The one with
maximum output is selected and reported as the
host if it passes predefined recognition
threshold.

14
Input layer
Hidden layer
Output layer

15
16
4. Automatic Face
Processing
This method involves scanning a person's
face and matching the image with a
database of known faces.

Input Color-space Morphological Matched Peak/Face Face


Based Image Estimates
Image Filtering Detector
Segmentation Processing

17
Correlation

Two images are superimposed and the correlation between


corresponding pixels is computed for different alignments.

18
Applications:
In ATM counters, cash points
In banks
In airports
Used to capture random faces in crowds
In corporation

19
Door locked system

20
Area for
Touch swiping
keypad RFID card

TFT
color
IR lights
LCD

Cameras
21
Back View

SD card
inserting
slot

Loud Door
speaker connection
terminal

22
Turning the device ON
Connect the power cable to the
power adaptor port at the back
side of the device

Connect the other end of the


power cable to AC supply

Now the device will turn ON


automatically
23
User Registration
Only admin can register, modify or delete users.
Press MENU for admin verification. After successful verification,
Functions Menu will appear. Now proceed in the following manner.

Input user number. It


Press 2 to select Press 1 to select can be in the range
user management register user 1-99999999

24
Input user name. It can
be up to 18 characters
long. Press ESC to toggle
between small & capital Select any one of the four
letters available verification options

Face: Normal user


Card: Temporary user
Pin and Face & Card
and Face: High
security level

After successful user registration, a confirmation message will be


displayed on the screen.
25
Device Performance

The device is highly accurate & dependable. Still, keeping in mind


the following points will aid in better device performance.

The system doesn’t have an inbuilt battery

>In cases of uneven light conditions or low light conditions


>In no light conditions

At the time of user registration if a user wears spectacles and if he


comes to the system without spectacles later, the system still
successfully recognizes him. But this doesn’t work with sun glasses.
26
data is stored in an SD card, which can be directly SD card
connected to PC via a card reader to export data directly
PC.

facility to connect with a USB storage


device.

27
28
29

You might also like