Docstoc

Roport on Facial recognition system

Document Sample
Roport on Facial recognition system Powered By Docstoc
					                           FACIAL RECOGNITION SYSTEM 1



                  SEMINAR REPORT

                           ON

        FACIAL RECOGNITION SYSTEM




SUBMITTED TO :                        SUBMITTED BY :
Er. Surender Kumar                    Lokesh Chadha

Lect. Deptt. Of I.T.                  ROLLNO:1705160 (3rd yr)




      DEPARTMENT OF INFORMATION TECHNOLOGY


   HARYANA COLLEGE OF TECHNOLOGY AND
                   MANAGEMENT, KAITHAL
             FACIAL RECOGNITION SYSTEM 2


      CONTENTS



 INTRODUCTION
 WORKING OF FRS
 FACE USAGE
 SOFTWARES USED
 TECHNOLOGIES
 GOTCHA
 DESCRIPTION
 ADVANTAGES
 SYSTEM COMPONENTS
    AND DESCRIPTION
 APPLICATIONS
                                             FACIAL RECOGNITION SYSTEM 3


                            INTRODUCTION


A facial recognition system is a computer-driven application for automatically identifying
a person from a digital image. It does that by comparing selected facial features in the live
image and a facial database.It is typically used for security systems and can be compared
to other biometrics such as fingerprint or eye iris recognition systems



The facial recognition process starts with a statistical analysis of a large number of facial
images. For this analysis, we use a technique called Principal Component Analysis (or
Eigenface Analysis) to determine the facial characteristics that are key to distinguishing
between people.



The result of this analysis is a set of Eigenfaces that capture the important variations that
distinguish one human face from another. Currently, we use 128 Eigenfaces to
characterize these variations.




How Facial Recognition System Works



A ticket to Super Bowl XXXV in Tampa Bay, Florida, didn't just get you a seat at
the biggest professional football game of the year. Those who attended the
January 2000 event were also part of the largest police lineup ever conducted,
although they may not have been aware of it at the time. The was testing out a
new technology, called FACEIT, that allows snapshots of faces from the crowd
to be compared to a database of criminal mugshots.
                                                   FACIAL RECOGNITION SYSTEM 4




                                    Photo courtesy Visionics
              Facial recognition software can be used to find criminals in a
                    crowd, turning a mass of people into a big lineup.

The $30,000 system was loaned to the Tampa Police Department for one year.
So far, no arrests have been made using the technology. However, the 36
cameras positioned in reas of downtown Tampa have allowed police to keep a
more watchful eye on general activities. This increased surveillance of city
residents and tourists has riled privacy rights groups.

People have an amazing ability to recognize and remember thousands of faces.
In this edition of how works you'll learn how computers are turning your face into
computer code so it can be compared to thousands, if not millions, of other
faces. We'll also look at how facial recognition software is being used in
elections, criminal investigations and to secure your personal computer.



The Face
Your face is an important part of who you are and how people identify you. Imagine how hard it
would be to recognize an individual if all faces looked the same. Except in the case of identical
twins, the face is arguably a person's most unique physical characteristic. While humans have
had the innate ability to recognize and distinguish different faces for millions of years, computers
are just now catching up.

Visionics, a company based in New Jersey, is one of many developers of facial recognition
technology. The twist to its particular software, FaceIt, is that it can pick someone's face out of a
crowd, extract that face from the rest of the scene and compare it to a database full of stored
images. In order for this software to work, it has to know what a basic face looks like. Facial
                                             FACIAL RECOGNITION SYSTEM 5


recognition software is based on the ability to first recognize faces, which is a technological feat in
itself, and then measure the various features of each face.

If you look in the mirror, you can see that your face has certain distinguishable landmarks.
These are the peaks and valleys that make up the different facial features. Visionics defines
these landmarks as nodal points. There are about 80 nodal points on a human face. Here are
a few of the nodal points that are measured by the software:

      Distance between eyes
      Width of nose
      Depth of eye sockets
      Cheekbones
      jaw line
      chin
These nodal points are measured to create a numerical code, a string of numbers, that
represents the face in a database. This code is called a faceprint. Only 14 to 22 nodal points
are needed for the FaceIt software to complete the recognition process. In the next section,
we'll look at how the system goes about detecting, capturing and storing faces

The Software

Facial recognition software falls into a larger group of technologies known as biometrics.
Biometrics uses biological information to verify identity. The basic idea behind biometrics
is that our bodies contain unique properties that can be used to distinguish us from
others. Besides facial recognition, biometric authentication methods also include:

      Fingerprint scan
      Retina scan
      Voice identification

Facial recognition methods may vary, but they generally involve a series of steps that serve to capt
analyze and compare your face to a database of stored images. Here is the basic process that is u
the FaceIt system to capture and compare images:




       Technology Behind The Facial Recognition System
                                            FACIAL RECOGNITION SYSTEM 6


    To identify someone, facial recognition software compares newly
             captured images to databases of stored images.

    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. If there
     is a face in the view, it is detected within a fraction of a second. A multi-scale
     algorithm is used to search for faces in low resolution. (An algorithm is a program
     that provides a set of instructions to accomplish a specific task). The system
     switches to a high-resolution search only after a head-like shape is detected.



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



    Normalization -The image of the head is scaled and rotated so that it can be
     registered and mapped into an appropriate size and pose. 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.



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

The heart of the FaceIt facial recognition system is the Local Feature Analysis (LFA)
algorithm. This is the mathematical technique the system uses to encode faces. The
system maps the face and creates a faceprint, a unique numerical code for that face.
Once the system has stored a faceprint, it can compare it to the thousands or millions of
faceprints stored in a database. Each faceprint is stored as an 84-byte file.
                                             FACIAL RECOGNITION SYSTEM 7




                    Using facial recognition software, police
                     can zoom in with cameras and take a
                              snapshot of a face.

The system can match multiple faceprints at a rate of 60 million per minute from memory
or 15 million per minute from hard disk As comparisons are made, the system assigns a
value to the comparison using a scale of one to 10. If a score is above a predetermined
threshold, a match is declared. The operator then views the two photos that have been
declared a match to be certain that the computer is accurate.

Facial recognition, like other forms of biometrics, is considered a technology that will have
many uses in the near future. In the next section, we will look how it is being used right
now.

Elements of a System's Security

A computer system can be considered as a set of resources which are available for
use by authorized users. A paper by Donn P outlines six elements of security that
must be addressed by a security administrator. It is worth evaluting any tool by
determining how it address these six elements.
                                           FACIAL RECOGNITION SYSTEM 8



   1. Availability - the system must be available for use when the        users need it.
      Similarly, critical data must be available at all times.

   2. Utility - the system, and data on the system, must be useful for a purpose.
   3. Integrity - the system and its data must be complete, whole, and in a readable
      condition.
   4. Authenticity - the system must be able to verify the identity of users, and the users
      should be able to verify the identity of the system.

   5. Confidentiality - private data should be known only to the owner of the data, or to
      a chosen chosen few with whom the owner shares the data.
   6. Possession - the owners of the system must be able to control it. Losing
      control of a system to a malicious user affects the security of the system for
      all other users.

                    The need for Intrusion Detection Systems


A computer system should provide confidentiality, integrity and assurance against denial
of service. However, due to increased connectivity (especially on the Internet), and the
vast spectrum of financial possibilities that are opening up, more and more systems are
subject to attack by intruders. These subversion attempts try to exploit flaws in the
operating system as well as in application programs and have resulted in spectacular
incidents like the Internet Worm incident of 1988.
                    There are two ways to handle subversion attempts. One way is to
prevent subversion itself by building a completely secure system. We could, for
example, require all users to identify and authenticate themselves; we could protect data
by various cryptographic methods and very tight access control mechanisms. However
this is not really feasible because:

   1. In practice, it is not possible to build a completely secure system because bug
      free software is still a dream, & no-one seems to want to make the effort to try to
      develop such software.Apart from the fact that we do not seem to be getting our
      money's worth when we buy software, there are also security implications when
      our E-mail software, for example, can be attacked. Designing and implementing
      a totally secure system is thus an extremely difficult task.
   2. The vast installed base of systems worldwide guarantees that any transition to a
      secure system, (if it is ever developed) will be long in coming.
   3. Cryptographic methods have their own problems. Passwords can be cracked,
      users can lose their passwords, and entire crypto-systems can be broken.
   4. Even a truly secure system is vulnerable to abuse by insiders who abuse their
      privileges.
                                              FACIAL RECOGNITION SYSTEM 9


   5. It has been seen that that the relationship between the level of access control and
      user efficiency is an inverse one, which means that the stricter the mechanisms,
      the lower the efficiency becomes.


We thus see that we are stuck with systems that have vulnerabilities for a while to
come. If there are attacks on a system, we would like to detect them as soon as
possible (preferably in real-time) and take appropriate action. This is essentially what
an Intrusion Detection System (IDS) does. An IDS does not usually take preventive
measures when an attack is detected; it is a reactive rather than pro-active agent. It
plays the role of an informant rather than a police officer.

The most popular way to detect intrusions has been by using the audit data generated by
the operating system. An audit trail is a record of activities on a system that are logged to
a file in chronologically sorted order. Since almost all activities are logged on a system, it
is possible that a manual inspection of these logs would allow intrusions to be detected.
However, the incredibly large sizes of audit data generated (on the order of 100
Megabytes a day) make manual analysis impossible. IDS automate the drudgery of
wading through the audit data jungle. Audit trails are particularly useful because they can
be used to establish guilt of attackers, and they are often the only way to detect
unauthorized but subversive user activity.
Many times, even after an attack has occurred, it is important to analyze the audit data
so that the extent of damage can be determined, the tracking down of the attackers is
facilitated, and steps may be taken to prevent such attacks in future. An IDS can also
be used to analyze audit data for such insights. This makes IDS valuable as real-time as
well as post-mortem analysis tools.

Anderson also classified intruders into two types, the external intruders who are
unauthorized users of the machines they attack, and internal intruders, who have
permission to access the system, but not some portions of it. He further divided internal
intruders into intruders who masquerade as another user, those with legitimate access
to sensitive data, and the most dangerous type, the clandestine

intruders, who have the power to turn off audit control for themselves.
Classification of Intrusion Detection Systems
Intrusions can be divided into 6 main types

   1. Attempted break-ins, which are detected by atypical behavior profiles or violations
      of security constraints.

   2. Masquerade attacks, which are detected by atypical behavior profiles or violations
      of security constraints.
                                           FACIAL RECOGNITION SYSTEM 10


   3. Penetration of the security control system, which are detected by
      monitoring for specific patterns of activity.

   4. Leakage, which is detected by atypical use of system resources.

   5. Denial of service, which is detected by atypical use of system resources.
   6. Malicious use, which is detected by atypical behavior profiles, violations of
      security constraints, or use of special privileges.




Gotcha!
The primary users of facial recognition software like FaceIt have been law enforcement
agencies, which use the system to capture random faces in crowds. These faces are
compared to a database of criminal mug shots. In addition to law enforcement and security
surveillance, facial recognition software has several other uses, including:



             Eliminating voter fraud

             cashing identity verification

             Computer security


One of the most innovative uses of facial recognition is being employed by the Mexican
government, which is using the technology to weed out duplicate voter registrations. To sway
an election, people will register several times under different names so they can vote more
than once. Conventional methods have not been very successful at catching these people.

Using the facial recognition technology, officials can search through facial images in the voter
database for duplicates at the time of registration. New images are compared to the records
already on file to catch those who attempt to register under aliases. The technology was
used in the country's 2000 presidential election and is expected to be used in local elections
soon.

 Potential applications even include ATM and check-cashing security. The software is
 able to quickly verify a customer's face. After the user consents, the ATM or check-
 cashing kiosk captures a digital photo of the customer. The FaceIt software then
                                                 FACIAL RECOGNITION SYSTEM 11


 generates a faceprint of the photograph to protect customers against identity theft and
 fraudulent transactions. Further analysis enables two pieces of information to be
 obtained: pitch information and the overall envelope of the sound.

      A key element in the morphing is the manipulation of the pitch information.
 If two signals with different pitches were simply cross-faded it is highly likely that two
 separate sounds will be heard. This occurs because the signal will have two distinct
 pitches causing the auditory system to perceive two different objects.

       A successful morph must exhibit a smoothly changing pitch throughout. The pitch
 information of each sound is compared to provide the best match between the
 two signals' pitches. To do this match, the signals are stretched and compressed so
 that important sections of each signal match in time. The interpolation of the two
 sounds can then be performed which creates the intermediate sounds in the morph.
 The final stage is then to convert the frames back into a normal waveform.

 By using facial recognition software, there's no need for a picture ID, bank card or personal
identification number (PIN) to verify a customer's identity.


                                          Photo courtesy Visionics
                     Many people who don't use banks use
                   check cashing machines. Facial recognition
                    could eliminate possible criminal activity.

This biometric technology could also be used to secure your computer files. By mounting a webcam to
your computer and installing the facial recognition software, your face can become the password you
use to get into your computer. IBM as incorporated the technology into a screensaver for its A,T and X
series Thinkpad laptops




Description

The facial recognition process starts with a statistical analysis of a large number of facial
images.

 For this analysis, we use a technique called Principal Component Analysis (or Eigenface
Analysis) to determine the facial characteristics that are key to distinguishing between
people.

The result of this analysis is a set of Eigenfaces that capture the important variations that
distinguish one human face from another. Currently, we use 128 Eigenfaces to
characterize these variations.

When a new picture is taken, we first find the location of the eyes. This gives us reference
points so that we can locate the head and rotate or scale the image so that the face is a
                                           FACIAL RECOGNITION SYSTEM 12


standard size. Next, we mask the image to concentrate on only the face, without hair and
clothing. We also take out any brightness or contrast variation that may be due to the
camera settings. Finally, we compare the masked image to all of the Eigenfaces.

       Each of these comparisons produces a number between -1.0 and +1.0. All 128 of
these numbers, or Eigen vector, constitute the "signature" of the face seen in that picture.
Discrimination is achieved by comparing the Euclidean distance between two Eigen
vectors.

      The threshold on the Euclidean vector provides the decision making step to
determine if two people are sufficiently close in appearance or not. The threshold is a
tunable parameter and can be adjusted to trade off the probability of falsely rejecting or
accepting an individual with the requirements of the application.

When a person is enrolled, a video stream or a picture is taken, and the system
determines the "facial signature" in the manner described above. This information is
stored in a database keyed by a unique identifier, such as the person’s number and card
number.

When a person wants access to the facility, the person's ID is submitted into a
checkpoint. The checkpoint uses the card number to look up the person’s unique identifier
and then uses that identifier to look up the facial signature that was determined during
enrollment. At the same time, the checkpoint takes a picture of the person and
determines the facial signature of the current photo. It then compares the two facial
signatures and provides a match or no match signal to the ACS.
                                         FACIAL RECOGNITION SYSTEM 13




How close the two facial signatures have to be to each other is
determined by a threshold that can be adjusted to control the
tradeoff between the probability of falsely rejecting a valid card
holder and the probability of falsely accepting an impostor.
Advantages of Facial Recognition

      Facial Recognition is a non-contact biometric. Nothing and no one is
       touched.
      Facial Recognition is non-invasive. Ordinary visible light is used for
       illumination.
      Facial Recognition is easy to use. A photo is taken.
      Facial Recognition can be trained to adapt to changes, thereby improving
       its performance.
      Facial Recognition is the only biometric allowing a guard to examine the
       match results (two photographs displayed on a computer monitor). No
       other biometric provides this capability.

ECSI has developed Facial Recognition products for various applications, such as
Access Control, Surveillance and Automated Facial Database Searches.

System Components and Description

The system consists of three major parts interconnected by a network:

             Access Control Unit (ACU)
             Guard Station Unit (GSU)
             Central Image Server (CIS)

To minimize costs and maximize maintainability, we constructed the system from
commercial off-the-shelf (COTS) hardware and software. For maximum
computational power at lowest cost, we chose Pentium based computers with
standard interface to perform all the computations and data management. For
maximum flexibility and adaptability, we designed the communications to use
standard Ethernet protocols. We chose Windows NT as the operating system
because of its security features and widespread support. To take advantage of
software reuse and rapid application development techniques developed
application software using object-oriented design methods with C++ and the
Microsoft Foundation Classes.

The system was designed to complete a recognition transaction in two seconds
after image capture. The ACU mounting height accommodates the full range of
human height.Facial recognition enrollment is defined as the process of preparing
a portrait image for facial searching or verification within the central database.
                                         FACIAL RECOGNITION SYSTEM 14


This process, which is performed by the ECSI's Facial Recognition enrollment
engine, involves the following steps:

      Finding Eyes
      Image Standardization
      Image Masking
      Eigen Coefficient Generation
      Distance between eyes

EXAMPLES




                                      Figure 1: ECSI's Facial Recognition Enrollment
                                                          Screen




Present an analyzed image to the system for "enrollment". The enrollment
process consists of specific operations based on the MIT patented "Eigenface"
calculations. Those images with the matching or similar statistics are considered
to be potential candidate duplicates. They can be reviewed on the operator
screen in real-time.
                                           FACIAL RECOGNITION SYSTEM 15




To minimize costs and maximize maintainability, we constructed the system from commercial
off-the-shelf (COTS) hardware and software. For maximum computational power at lowest
cost, we chose Pentium based computers with standard interface to perform all the
computations and data management. For maximum flexibility and adaptability, we designed
the communications to use standard Ethernet protocols. We chose Windows NT as the
operating system because of its security features and widespread support. To take
advantage of software reuse and rapid application development techniques developed
application software using object-oriented design methods with C++ and the Microsoft
Foundation Classes.

The system was designed to complete a recognition transaction in two seconds after image
capture. The ACU mounting height accommodates the full range of human height.Facial
recognition enrollment is defined as the process of preparing a portrait image for facial
searching or verification within the central database

People have an amazing ability to recognize and remember thousands of faces. In this
edition of how works you'll learn how computers are turning your face into computer code so
it can be compared to thousands, if not millions, of other faces. We'll also look at how facial
recognition software is being used in elections, criminal investigations and to secure your
personal computer.

The global distance is the overall difference between the two signals. Audio is a time-
dependent process. For example, two audio sequences may have different durations and
two sequences of the sound with the same duration are likely to differ in the middle due to
differences in sound production rate. Therefore, to produce a global distance measure, time
alignment must be performed - the matching of similar features and the stretching and
compressing, in time, of others. Instead of considering every possible match path which
would be very inefficient, a number of constraints are imposed upon the matching process.

       . For maximum computational power at lowest cost, we chose Pentium based
computers with standard interface to perform all the computations and data management.
For maximum flexibility and adaptability, we designed the communications to use standard
Ethernet protocols. We chose Windows NT as the operating system because of its security
features and widespread support.
                                              FACIAL RECOGNITION SYSTEM 16




                                         Photo courtesy Visionics
                   Facial recognition software can be used to lock your computer.




While facial recognition can be used to protect your private information, it can just as easily
be used to invade your privacy by taking you picture when you are entirely unaware of the
camera.
                                            FACIAL RECOGNITION SYSTEM 17




8. References:



      http://www.information4fun.com

      http://www.sciancetechmag.com

      http://www.instanteffects.com

      http://www.i4u.com/article2936.html

      http://macface.org

      http://www.nisecurity.com

      http://www.sciancetechmag.com

				
DOCUMENT INFO
Shared By:
Stats:
views:20
posted:4/18/2011
language:English
pages:17
Description: Report on Facial Recognition system, a technology. a nice report created by me.