Scribd
Upload
25 views

EP494 PowerpointFa

This document provides an overview of face recognition technology. It discusses why face recognition is useful, the challenges in face recognition due to variations in pose and illumination, and early and modern approaches. Some key approaches discussed include Eigenface technology, which projects faces into a "facespace", and Probabilistic Decision-Based Neural Networks. The document also covers evaluating face recognition systems using databases and protocols, as well as the Face Recognition Grand Challenge efforts.

Uploaded by

Bharath Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
25 views

EP494 PowerpointFa

This document provides an overview of face recognition technology. It discusses why face recognition is useful, the challenges in face recognition due to variations in pose and illumination, and early and modern approaches. Some key approaches discussed include Eigenface technology, which projects faces into a "facespace", and Probabilistic Decision-Based Neural Networks. The document also covers evaluating face recognition systems using databases and protocols, as well as the Face Recognition Grand Challenge efforts.

Uploaded by

Bharath Kumar
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 30

FACE RECOGNITION:

A LITERATURE SURVEY

By
CONTENTS
 Introduction
 Why do we need face recognition?
 Biometrics
 Face Recognition by Humans
 Challenge in Face Recognition
 Variation in pose
 Variation in illumination
 Early Work/Modern Work
 Aspects of face recognition
 Approaches use for recognition
 EIGENFACE TECHNOLOGY
 PDBNN
 Video-based Face Recognition
 Evaluation of face recognition systems
 Face Recognition Grand Challenge
WHY DO WE NEED IT?
 Easy way to discover criminals
 Video Surveillance
 Portal Control
 Investigations
 Smart Cards
 Devices log-on
 ATM cards
 Entertainment
 Video Games
 Human-robot/computer-interaction
BIOMETRICS
 Consists of methods for uniquely recognizing
humans based upon one or more intrinsic
physical or behavioral traits. In computer science,
in particular, biometrics is used as a form of
identity access management and access control. It
is also used to identify individuals in groups that
are under surveillance.
FACE RECOGNITION BY HUMANS
 Relevant studies in psychophysics and
neuroscience that will help with the design of
face recognition systems:
 People remember faces more easy than other objects.
 People focus in odd features (eg. Hears).
 People rank facial features.
CHALLENGE IN FACE RECOGNITION
 Illumination variation
 Images of the same face look different because the
change of the light.
 Pose Variation
 Same face in different angles could give a different
output.
EARLY WORK
 Use techniques base on 2D pattern recognition.
 Use measured attributes of features (distance-
measuring algorithms). These determined the
distances between important features like eyes and
compared these distances to the distances on
known faces in the database.
 Performance is poor with variations of the same
face and size, is not accurate.
 Does well with variations in intensity.
MODERN WORK
 Appearance-based model, heavily tested with
large databases, with positive outcomes.
 Feature-based models has been successful as
well, and more accurate in the two
challenges( light and pose variation)
 Techniques for feature extraction are not
adequate, for example, it won’t detect if an eye is
close or not.
ASPECTS OF FACE RECOGNITION
ASPECTS OF FACE RECOGNITION, CONTINUED

 Face detection: Locating the faces in an image or


video sequence.
 Feature extraction: Finding the location of eyes,
nose, mouth, etc.
 Face recognition: Identifying the face(s) in the
input image or video.
 Identification/Verification: The system needs to
confirm or reject the claimed identity of the input
face.
FACE DETECTION
 First step of any system.
 Two statistics are important: positives (also referred to
as detection rate) and false positives (reported
detections in non-face regions).
 Multiview-based methods for face detection are better
than invariant feature methods when is used for head
rotations.
 Appearance-based methods have achieved the best
results in face detection, compared to feature-based and
template-matching methods.
FEATURE EXTRACTION
 Three types of approaches:
 Generic methods based on edges, lines, and curves.
 Feature-template-based methods that are used to detect facial
features such as eyes.
 Structural matching methods that take into consideration
geometric constraints on features.
 Is the most important step for face recognition, even the
most complete methods need to know the exact location of
the feature for normalization.
 First methods use template model that emphasized in some
features.
EIGENFACE
 The first successful method for facial recognition.
 Take an input image and then projecting into a
new dimension called “facespace”.
EIGENFACE CONTINUED
 To identify a face, the algorithms do:
 Registration: Transformed the input image to “facespace”, then is saved in a new
representation.
 Eigenpresentation: Every face in the database is encoded into a representation call
template. principal component analysis (PCA) is used to encode face images and
capture face features.
 Identification: this last step is done by comparing the input image with the ones in
the database using the templates, and then selecting the best match
NEURAL NETWORK

 What is it?
 Is a mathematical model or computational model that is
inspired by the structure and/or functional aspects of
biological neural networks.
 NN technology gives computer systems an amazing
capacity to actually learn from input data.
 It’s easy to train a neural network with samples which
contain faces, but it is much harder to train a neural
network with samples which do not, and the number of
“non-faces” is too large.
NN ON FACE RECOGNITION
 It has a filter at the beginning of the process that
scan the whole image, and take each portion to
see if the face exist in each window.
 Merging all this pieces after the filter help the NN
to eliminate false detections.
 NN has a high level of accuracy when the images
has lighting conditions.
EXAMPLE OF NN
PDBNN
 A fully automatic face detection recognition system based on a neural
network.
 A proposed fully automatic face detection and recognition system based
on Probabilistic Decision-Based Neural Networks has been proposed.
 It consists of three modules: A face detector, eye localizer, and face
recognizer.
 The PDBNN uses only the up side of the face; the reason to not use the
mouth is to avoid the expressions that cause motion around the mouth.
PDBNN CONTINUED
 Advantages of this implementation are that it
converges quickly and is easily implemented on
distributed computing platforms.
 Has a lower false acceptance/rejection rate
because it uses the full density description for
each class.
 The system could have problems when the
number of classes grows exponentially.
 Main Feature: Each class is
designed to recognize one
person
VIDEO-BASED FACE RECOGNITION
 Three Challenge:
 The quality of video is low. Usually, video acquisition
occurs outdoors (or indoors but with bad conditions for
video capture).
 Face image are small: Make the recognition task more
difficult, because affect the accuracy of face segmentation,
as well as the accurate detection of the crucial
points/landmarks that are often needed in recognition
methods.
 The characteristics of faces/human body parts: It is easier to
localized a face, but not recognize an specific one.
BASIC STEPS OF VIDEO-BASED FACE RECOGNITION

 Face Segmentation and Pose Estimation: For


segmentation motion and/or color information is used
and locations of feature points can be used for pose
estimation. Multiview face with different angles can be
used to do pose and segmentation at the same time.
 Face and feature tracking: The goal of this step is to
analyzed the 3D depth of points of the image sequence.
 Face Modeling: Using a 3D model to match frontal
views of the face.
EVALUATION OF FACE RECOGNITION SYSTEMS

 Since the topic become so important for society available face databases have
been collected and corresponding testing protocols have been designed.
 The FERET protocol (1994).
 Free database
 Consists of 14,126 images of 1199 individuals.
 Three evaluation tests had been administered in 1994, 1996, and 1997.
 Sets of 5 to 11 images of each individual
 were acquired under relatively unconstrained
 conditions
EVALUATION OF FACE RECOGNITION SYSTEMS CONTINUE

 The XM2VTS protocol (1999).


 This protocol was defined for the task of verification
 Expansion of previous M2VTS program (5 shots of
each of 37 subjects).
 Now consists 295 subjects.
 The results of M2VTS/XM2VTS can be used in wide
range of applications.
FACE RECOGNITION GRAND CHALLENGE
 FRGC ran from May 2004 to March 2006.
 The primary goal of the FRGC was to promote and advance face
recognition technology designed to support existing face recognition
efforts in the U.S. Government.
 Sponsors: Intelligence Advanced Research Projects Agency (IARPA)
Department of Homeland Security (DHS) FBI Criminal Justice
Information Services Division Technical Support Working Group
(TSWG) National Institute of Justice.
 The FRGC consisted of progressively difficult challenge problems.
 The Face Recognition Grand Challenge (FRGC) was designed to
achieve this performance goal by presenting to researchers a six-
experiment challenge problem.
FACE RECOGNITION GRAND CHALLENGE CONT.

 FRGC provide data corpus of 50,000 images. The


data consists of 3D scans and high resolution still
imagery taken under controlled and uncontrolled
conditions.
FRGC RESULTS
 The results indicated that the new algorithms are 10 times more accurate
than the face recognition algorithms of 2002 and 100 times more
accurate than those of 1995.
 Some of the algorithms were able to outperform human participants in
recognizing faces and could uniquely identify identical twins.
ETICS ISSUES WITH FACE RECOGNITION
 The use of facial recognition in public places is
unethical ?
 Who gets to add pictures to the database of wanted
faces?
 Who has access to the database, internally and
externally?
 What recourse do people have if they are entered
into the database incorrectly?
 Should we trust the software?
REFERENCES
 W. Zhao, R. Chellappa, A. Rosenfeld, and P.J.
Phillips, Face Recognition: A Literature Survey.
 P. Jonathon Phillips, Patrick J. Flynn, Todd
Scruggs, Kevin W. Bowyer, William Worek,
Preliminary Face Recognition Grand Challenge
Results.
 Wikipedia
QUESTIONS

You might also like