1. By:Sunil Kumar Sharma

2. What is Biometrics?
 Biometrics refers to the automatic identification
of a person based on his or her physiological or
behavioural characteristics.
• BIO-Physical or Behavioral
• METRICS-To measure characteristics

3. Physical biometrics:
 Fingerprint
 Facial recognition/face location
 Hand geometry
 Iris scan
 Retinal scan

4. Behavioral biometrics:
Speaker/voicerecognization:
Analyzing vocal behavior
Signature/handwriting:
Analyzing signature dynamics
 Keystroke/patterning:
Measuring the time spacing of typed words

5. TWO MAIN USES
1) IDENTFICATION
-figure out “Who is X?”
-accomplished by system performing a “one-to-many”
search
2) VERIFICATION
-answer the question “Is this X?”
-accomplished by the system performing a “one-to-one”
search

6. Basic Elements
 Sensing Elements
 Processing Elements
 Storage Elements
 Interface Elements

8. Sensing Elements-The sensing element, or the input interface
element, is the hardware core of a biometrics system and converts
human biological data into digital form. This could be a
complimentary metal oxide semiconductor (CMOS) imager or a
charge coupled device (CCD) in the case of face recognition,
handprint recognition or iris/retinal recognition systems; a
CMOS or optical sensor in the case of fingerprint systems; or a
microphone in the case of voice recognition systems. These
sensors capture the biometric information and convert it into a
digital form that can be processed by the next stage - the
processing elements.

9. Processing Elements- The processing element is generally a
microprocessor, digital signal processor or computer that
processes the data captured from the sensors. The processing of
the biometric image generally involves image enhancement,
normalization, template extraction, and matching/comparison
of the biometric template during enrolment and authentication
of the users.
Storage Elements- The function of the storage element is to
store the enrolled template that is recalled to perform a match at
the time of authentication. For most identification solutions
(1:N), the storage element would be random access memory
(RAM) or flash EPROM or some other form of memory IC,
and in some other cases it could be a data server. In the case of
verification (1:1), a removable storage element like a contact or
contactless smart card can be used.

10. Interface Elements- Finally, there is the output interface
element, which will communicate the decision of the biometric
system to the interfaced asset to enable access to the user. This
can be a simple serial communication protocol like RS232, or the
higher bandwidth USB protocol. It could also be the TCP/IP
protocol via a wired medium like 10/100 Ethernet or through a
wireless medium using either the 802.11b protocol, ISM RF
band, RFID, Bluetooth, or one of the many cellular protocols.

12. Biometric sensor:-acquire images .
Preprocessing:-reference points extraction ,
contour spacing , binayrization.
Feature extraction:-removal of noise , convert data into
numeric feature template.
Matcher:-
- Compare extracted template with previously enrolled
templates.
- Determine degree of similarity & output matching score.
Decision:-matching score compare with threshold.

13. Biometrics – How do they work?
 Although biometric technologies
differ, they all work in a similar
fashion:
 The user submits a sample that
is an identifiable, unprocessed
image or recording of the
physiological or behavioral
biometric via an acquisition
device (for example, a scanner
or camera)
 This biometric is then processed
to extract information about
distinctive features to create a
trial template or verification
template
 Templates are large number
sequences. The trial template is
the user’s “password.”

14. An Example:
A Multi-model System
Sensors Extractors Classifiers Negotiator
ID Accept/
Reject
Face Face Face
Extractor Feature MLP
2D (bmp) AND
Voice Voice Voice
Extractor Feature MLP
1D (wav)
Objective: to build a hybrid and expandable biometric app. prototype
Potential: be a middleware and a research tool

15. A Few Definitions
Total False Acceptence
FAR =
Total False Attempts
Total False Rejection
FRR =
Total True Attempts
EER is where FAR=FRR

16. Threshold Analysis
Minimum
cost
FAR and FRR vs. Threshold

17. Practical Usages
✓ Government—Passports, national identification (ID) cards,
voter cards, driver’s licenses, social services.
✓ Transportation—Airport security, boarding passes, and
commercial driver’s licenses
✓ Healthcare—Medical insurance cards, patient/employee identity
cards
✓ Financial—Bankcards, ATM cards, credit cards, and debit cards
✓ Retail and gaming—Retail programs, such as check cashing,
loyalty rewards and promotional cards, and gaming systems for
access management and VIP programs
✓ Security—Access control and identity verifications, including
time and attendance

18. Conclusion
1. All authentication methods are prone to errors.
Nevertheless, reliable user authentication must
ensure that an attacker cannot masquerade as a
legitimate user
2. Biometrics is uniquely bound to individuals and
may offer organizations a stronger method of
authentication.
3. Possibly in the near future, you will not have to
remember PINs and passwords and keys in your
bags or pockets will be things of the past.