CHAPTER ONE

INTRODUCTION

1.1     Background of Study

With the growing importance of applications requiring human identification, the demand for adequate security measures has increased dramatically in response to this demand; new technologies are being introduced aimed to ensure that the requisite level of security can be achieved. One of these technologies is often referred to as biometrics. Biometric recognition or, simply, biometrics refers to the automatic recognition of individuals based on their physiological and/or behavioral characteristics. By using biometrics, it is possible to confirm or establish an individual’s identity based on “who she is,” rather than by “what she possesses” (e.g., an ID card) or “what she remembers” (e.g., a password). An important advantage of biometrics lies in the fact that physical or behavioral traits cannot be transferred to other individuals. Examples of biological characteristics that have been explored for their potential as biometrics so far are Face, Fingerprints, DNA, Hand Geometry, Iris and Retinal Patterns, Signature, Voice, Gait and Ear (Kale et al, 2002).

People often feel that they can identify a familiar person from afar simply by recognizing the way the person walks. This common experience, combined with recent interest biometrics, has led to the development of gait recognition as a form of biometric identification. As a biometric, gait has several attractive properties. Acquisition of images portraying an individual’s gait can be done easily in public areas, with simple instrumentation, and does not require the cooperation or even awareness of the individual under observation. In fact, it seems that it is the possibility that a subject may not be aware of the surveillance and identification that raises public concerns about gait biometrics (McGrath, 2003).

Biometric systems for human identification at distance have ever been an increasing demand in various significant applications. Many biometric resources, for instance iris, fingerprint, palm print, hand geometry have been systematically studied and employed in many systems. In spite of their widespread applications, these resources suffer from two main disadvantages: 1) Failure to match in low resolution images, pictures taken at a distance and 2) Necessitates user cooperation for accurate results (Dacheng et al, 2007). For these reasons, innovative biometric recognition methods for human identification at a distance have been an urgent need for surveillance applications and gained immense attention among the computer vision community researchers in recent years. In this modern era, the integration of human motion analysis and biometrics has fascinated several security-sensitive environments such as military, banks, parks and airports etc. and has turned out to be a popular research direction.

Gait recognition according to Nixon et al (2006) is the identification of individuals in video sequences by the way they walk. It is strongly motivated by the need for automated person identification system at a distance in visual surveillance and monitoring applications in security sensitive environments, such as banks, parking lots, museums, malls, and transportation hubs such as airports and train stations, where other biometrics such as fingerprint, face or iris information are not available at high enough resolution for recognition (Chellappa et al, 2005). Furthermore, night vision capability (an important component in surveillance) is usually not possible with other biometrics due to the limited biometric details in an IR image at large distance (Kale, 2003).

Gait is a behavioral (habitual) biometric, in contrast with those physiological biometrics such as face and iris, and it is viewed as the only true remote biometric. Capturing of gait is unobtrusive, which means that it can be captured without requiring the prior consent of the observed subject, and gait can be recognized at a distance (in low resolution video) (Wang et al, 2004). In contrast, other biometrics either require physical contact (e.g., fingerprint) or sufficient proximity (e.g., iris). Also, gait is harder to disguise than static appearance features such as face.

1.2     Statement of the Problem

It is quite evident that security in various organizations today is nothing to write home about. It is however based on the fact that as technology improves, intruders as well improve their techniques of bypassing security mechanisms. Currently, many organizations face the threat of unauthorized access due to the hidden problem facing their security systems. This has however caused them damages to their reputation. As a matter of fact, individuals now feel unsafe when patronizing such organizations.

Consequently, methods of security verification applied by most organizations today include fingerprint biometric verifications, Smart cards, face recognitions, and so many others. These methods have been working efficiently over the years. However, there are some problems attached to them such as poor imaging resolution, misplacement of smart cards, face painting and makeups, dirty fingers and so many more. These problems can cause the systems to misbehave thereby defeating the major aim of security. For this purpose, these problems are being made known to researchers in order to develop a system that will still work correctly under the condition of the above problems, thereby improving the security verification system of organizations.  

1.3     Aim and Objectives of the Study

The main aim of this project work is to design and implement a gait recognition system that will solve the problems encountered by most security verification systems.

The specific objectives of the system include;

1. To develop a system that will recognize human gesture and use it as a means of validating individuals for security purposes.
2. To review related literatures pointing to the area of gait recognition using different techniques.
3. To develop a security system that will function under certain unfriendly conditions.
4. To improve security by capturing and saving the gestures of individuals without their knowledge in order to avoid faking
5. To analyze the impact of gait recognition systems if implemented by organizations.

1.4     Significance of the Study

This research work will aid in tackling the problems existing in other methods of security verification, most especially those methods related to biometric verification systems.

The gait recognition software is significant in the following ways

1. It will provide a means of recognizing individuals based on movement.
2. It will also serve as a mechanism for monitoring office places.
3. This system will be immensely beneficial to security agencies in a way that if attached with alarming feature, it will be able to alert security agents on recognizing the gesture of a wanted suspect or criminal.

1.5     Scope of the Study

This research work and the system it proposes will only cover the area of gait recognition. It will be able to recognize the gesture of individuals that exist in the gait database. The gestures are captured through computer webcams for registration and verifications.

1.6     Definition of Terms

BIOMECHANICS: Science of movement of a living body, including how muscles, bones, tendons, and ligaments work together to produce movement biomechanics is part of the larger field of kinesiology, specifically focusing on the mechanics of movement.

BIOMETRIC VERIFICATION: This is any means by which a person can be uniquely identified by evaluating one or more distinguishing biological traits.

BIOMETRICS: Technical term for body measurements and calculations. It refers to metrics related to human characteristics. Biometrics authentication (or realistic authentication) is used in computer science as a form of identification and control access.

CONCEALMENT: The action of hiding something or preventing it from being known.

FACE RECOGNITION: This is a biometric software application capable of uniquely identifying or verifying a person by comparing and analyzing patterns based on the person's facial contours.

FINGERPRINT VERIFICATION: This refers to the automated method of identifying or confirming the identity of an individual based on the comparison of the fingerprints.

FORENSIC: is the application of science to criminal and civil laws, mainly—on the criminal side—during criminal investigation, as governed by the legal standards of admissible evidence and criminal procedure.

GAIT RECOGNITION: This is a process of identifying humans based on their gait features.

GAIT: A way of walking, running, or moving along on foot.

KINEMATICS: Branch of classical mechanics that describes the motion of points, bodies (objects), and systems of bodies (groups of objects) without considering the forces that cause them to move.

PHYSIOLOGICAL: Relating to the branch of biology that deals with the normal functions of living organisms and their parts.

SECURITY SYSTEM: A hardware system that detects monitors or prevents unauthorized intrusion into premises.

SMART CARD: Typically a type of chip card, is a plastic card that contains an embedded computer chip–either a memory or microprocessor type–that stores and transacts data.

SURVEILLANCE: Monitoring of behavior, activities, or other changing information for the purpose of influencing, managing, directing, or protecting people.

SYNCHRONIZED: Cause to occur or operate at the same time or rate. e.g soldiers used watches to synchronize movements.

WEBCAM: A video camera connected to a computer, allowing its images to be seen by Internet users.