Scribd
Upload
42 views

1.1) Background

The document discusses human and machine face recognition. It defines an image and digital image, and discusses how face recognition works for both humans and machines. It also outlines some of the challenges in machine face recognition, such as segmentation and feature extraction. Finally, it discusses applications of face recognition technology and the different types of problems that can arise, including matching, similarity detection, and image transformation.

Uploaded by

Vishwas Shetty
Copyright
© © All Rights Reserved
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
42 views

1.1) Background

The document discusses human and machine face recognition. It defines an image and digital image, and discusses how face recognition works for both humans and machines. It also outlines some of the challenges in machine face recognition, such as segmentation and feature extraction. Finally, it discusses applications of face recognition technology and the different types of problems that can arise, including matching, similarity detection, and image transformation.

Uploaded by

Vishwas Shetty
Copyright
© © All Rights Reserved
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 3

Introduction

1.1) BACKGROUND
The word image is defined as “an exact or analogous representation of a being or a
thing “. An image can therefore, be thought of as anything, which represents something else.
The image or monochrome image or single color image such as black and white paragraph, is
represented as a two dimensional light intensity function f(x, y), where x and y denote spatial
co-ordinates and the value of “f” at any point (x, y) is proportional to the brightness (or gray
level) of the image at that point.
A digital image is an image of f(x, y) that has been digitized both in spatial co-
ordinates and brightness. The elements of such a digital array are called image elements,
picture elements and pixels. Face identification, both by humans and machines, is developing
as an active research area. This chapter presents a critical survey of existing literature on
human and machine identification of faces.
In order to better design machine based face identification, it is necessary to
understand how humans perceive faces.

1.1.1) Face Recognition


Face recognition, both by humans and machines, is developing as an active research
area. This chapter presence a critical survey of existing literature on human and machine
recognition of faces [3].In order to better design machine based face recognition, it is
necessary to understand how humans perceive faces. The primary task at hand, given still or
video images, requires the identification of one or more persons using a database of stored
face images. To do this the face must be segmented and extracted from the scene, where upon
it can be identified and matched.

1.1.2) Human and Machine Recognition of Faces


Machine recognition of faces from still and video images is emerging as an active
research area spanning several disciplines such as image processing, pattern recognition,
computer vision and neural networks. In addition, face recognition technology (FRT) has
numerous commercial and law enforcement applications. These applications range from
static matching of controlled format photographs such as passports, credit cards, photo ID's,
driver's licenses, and mug shots to real time matching of surveillance video images presenting
different constraints in terms of processing requirements. Although humans seem to

A.I.E.T, Gunthapally 1
Introduction

recognize faces in cluttered scenes with relative ease, machine recognition is a much more
daunting task. A general statement of the problem can be formulated as follows: Given still or
video images of a scene, identify one or more persons in the scene using a stored database of
faces. Available collateral information such as race, age and gender may be used in
narrowing the search. The solution of the problem involves segmentation of faces from
cluttered scenes, extraction of features from the face region, identification, and matching, The
generic face recognition task thus posed is a central issue in problems such as electronic line
up and browsing through a database of faces.
Over the past 20 years extensive research has been conducted by psychophysicists,
neuroscientists and engineers on various aspects of face recognition by humans and
machines. Psychophysicists and neuroscientists have been concerned with issues such as:
Uniqueness of faces; whether face recognition is done holistically or by local feature
analysis: analysis and use of facial expressions for recognition: how infacts perceive faces:
organization of memory for faces: inability to accurately recognize: existence of a
grandmother neuron for face recognition: role of the right hemisphere of the brain in face
perception: and inability to recognize faces due to conditions such as prosopagnosia. Some of
the theories put forward to explain the observed experimental results are contradictory. Many
of the hypothesis and theories put forward by researches in these disciplines have been based
on rather small sets of images. Nevertheless, several of the findings have important
consequences for engineers who design algorithms and systems for machine recognition of
human faces.

1.1.3) Applications
Commercial and law enforcement applications of FRT range from static, controlled
format photographs to uncontrolled video images posing a wide range of different technical
challenges and requiring an equally wide range of technical challenges and requiring an
equally wide range of techniques from image processing, analysis, understanding and pattern
recognition. One can broadly classify challenges and techniques into two groups: static(no
video) and dynamic(video) matching. The applications of FRT are listed below:
1. Credit card, Driver's License, Passport, and Personal Identification.
2. Bank/Store Security
3. Crowd Surveillance
4. Expert Identification

A.I.E.T, Gunthapally 2
Introduction

5. Witness Face Reconstruction


6. Electronic Mug Shots Book
7. Electronic Lineup
8. Reconstruction of Face from Remains
9. Computerized Aging

Three different kinds of problems arise in the applications listed above.


These are matching, similarity detection and transformation. Applications 1, 2, and 3
involve matching one face image to another face image. Applications 4-7 involve finding or
creating a face image which is similar to the human recollection of a face. Finally,
applications 8 and 9 involve generating an image of a face from input data that is useful in
other applications by using other information to perform modifications of a face image. Each
of these applications imposes different requirements on the recognition process.
Matching requires that the candidate matching face image be in some set of face
images selected by the system. Similarity detection requires, in addition to matching, that
images of faces be found which are similar to a recalled face: this requires that the similarity
measure used by the recognition system close match the similarity measures used by humans.
Transformation applications require that the new images created by the systems be similar to
human recollections of a face.

1.2) PROBLEM DESCRIPTION

The problem with the present system is same as problems encountered in


any manual file processing system. The existing system does not support the cropped
images of criminals. The existing system is not suitable in some cases such as if a
witness can identify only a part of the criminal. Present system uses some algorithms
for identifying criminal faces which are difficult to process. Finally the existing system
does not always produce better results in identifying the criminals by their images.

A.I.E.T, Gunthapally 3

You might also like