Scribd
Upload
8 views38 pages

Lecture - 08908

Uploaded by

libex28436
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views38 pages

Lecture - 08908

Uploaded by

libex28436
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 38

Face Recognition

Lecture 04
Acknowledgements

 http://biometrics.cse.msu.edu/
 https://ieeexplore.ieee.org/Xplore/home.jsp
 https://link.springer.com/
 https://www.cse.iitk.ac.in/users/biometrics/
Introduction to face recognition
Introduction to face recognition
 Human face images are useful not only for person recognition, but for also revealing other
attributes like gender, age, ethnicity, genetic disorder and emotional state of a person.
 Humans are good in perceiving familiar faces as cognitive processes help humans to
recognize faces in difficult situations.
 Therefore, training a machine to recognize faces as humans do is a challenging task.
 General methods used in object recognition such as appearance-based, model-based, and
texture-based approaches are also applicable to the specific problem of face detection and
recognition.
 The face is the frontal portion of the human head, extending from the forehead to the chin and
includes the mouth, nose, cheeks, and eyes.
 The face is considered to be the most commonly used biometric trait by humans; we
recognize each other and, in many cases, establish our identities based on faces. Hence, it
has become a standard practice to incorporate face photographs in various tokens of
authentication such as ID cards, passports, and driver’s licenses.
History face recognition
Year Authors Methods
1965-66 Bledsoe, et al. Manual measurement of
facial features
1970-71 Goldstein, Harmon, and Lesk 21 facial features
1973 Kanade First automated system
1987 Sirovich and Kirby Principal Component
Analysis
1991 Turk and Pentland Eigenface
1996 Etemad and Chellapa Fisherface
1999 Wiskott, Fellous, Kruger and Malsburg EBGM
1993-2000 DARPA FERET Program
2001 Viola and Jones AdaBoost and Haar cascade
Facial Features
 Facial characteristics can be organized into the following three levels:
 Level 1 consists of gross facial characteristics that are easily observable. Examples
include the general geometry of the face and global skin color. Such features can be
used to quickly discriminate between (a) a short round face and an elongated thin face;
(b) faces exhibiting predominantly male and female characteristics; or (c) faces from
different races.
 Level 2 consists of localized face information such as the structure of the face
components (e.g., eyes), the relationship between facial components, and the precise
shape of the face. These features are essential for accurate face recognition, and they
require a higher resolution face image. The characteristics of local regions of the face
can be represented using geometric or texture descriptors.
 Level 3 consists of unstructured, micro level features on the face, which includes scars,
freckles, skin discoloration, and moles. One challenging face recognition problem where
Level 3 details may be critical is the discrimination of identical twins.
Face Recognition Techniques
Advantages of Face Recognition
 Unlike fingerprints, face can be captured at a longer standoff distance using non-
contact sensors.
 The face conveys not only the identity, but also the emotions of a person (e.g.,
happiness or anger) as well as biographic information (e.g., gender, ethnicity, and
age).
 There are large legacy face databases, which enable large scale analysis of the face
modality in terms of individuality or scalability.
 Compared to other biometric traits like fingerprint and iris, people are generally more
willing to share their face images in the public domain as exhibited by the increasing
interest in social media applications (e.g., Facebook) with functionalities like face
tagging. Due to the above reasons, face recognition has a wide range of applications in
law enforcement, civilian identification, surveillance systems, and entertainment /
amusement systems.
Introduction to face recognition

 Source of face image


 Webcam
 CCTV camera
 Thermal/infrared camera
 Normal DLSR camera
 Mobile phones
 Different ID cards and forms
Why face recognition?

 Natural place in next-generation


smart environments
 able to recognize at a distance
without requiring a `pause and
present' interaction
 do not require generating special
electro-magnetic illumination
 do not restrict user movement
 low-power and inexpensive
 Humans identify other people by their face, therefore are likely to be comfortable with systems
that use face recognition.
Global face recognition market
 Global Facial Recognition Market, By Type
 Two-dimensional (2D) Facial Recognition
 Three-dimensional (3D) Facial Recognition
 Facial Analytics
 Global Facial Recognition Market, By Industry
 Government & Defense
 Banks, Financial Services and Insurance (BFSI)
 Retail Industry
 Automotive, Web Applications, Electronic Devices
 Healthcare services
 Market driver
 Increasing instances of identity threats
 Market challenge
 High cost of deployment
 Market trend
 Integration of facial recognition in video surveillance
Face Recognition in Movies:
 Star Trek (1966)
 Face scans are used to enter the archives in Star Trek Into
Darkness

 2001: A Space Odyssey (1968)


 Robocop (1987)
 Robocop uploads the face image of a villain into the computer
which is able to identify the person using a database

 The Fifth Element (1997)


 The police vehicles have face recognition software

 Terminator Renaissance (2009)


 Skynet uses face recognition

 Ex Machina (2015)
 Cell phone and humanoid robot, both use face recognition
Challenges
How face recognition system works?
Face verification, identification and
matching
Verification: 1 to 1 comparison

Same Person? What is the matching proximity?


Identification: 1 to N comparison
State-of-the-art: Verification
Applications:

International Border Crossing


Locating Intruders
Passenger Verification
Video Surveillance
Identifying Suspects
Age and Gender
Estimation
Detecting Genetic Disorder from Face Image

You might also like