International Journal of Computer Applications (0975 – 8887) Volume 120 – No.17, June 2015 1 Human Recognition Methods based on Biometric Technologies Annu Sharma Research Scholar Department of Computer Science & Technology, GKV, Haridwar, Uttarakhand, India Praveena Chaturvedi, Ph.D Associate Professor Department of Computer Science & Technology, KGC, Dehradun, Uttarakhand, India Shwetank Arya, Ph.D Assistant Professor Department of Computer Science & Technology, GKV, Haridwar, Uttarakhand, India ABSTRACT Biometric has revolutionized the Human Recognition Technology .The base and reach of human recognition system has been expanded by the innovative uses of Biometric devices .Human recognition have becomes one of the most well-off fields in the past ten years. Biometrics is the science of establishing the identity of an individual based on physical, chemical or behavioural attributes of the person; it deals with the automated recognition of individuals based on biological and behavioural characteristics. Biometrics spread its wings in a wide range of applications and found itself as a reliable source in fields such as electronic data security, ecommerce, internet access, physical access control, PDA, Government applications such as national ID card, social security, welfare- disbursement, border control, military surveillance, etc As the application areas are emerging, the implementation of biometric systems in both commercial and government sectors is increasing and therefore leading to enormous security breaches in the installed systems. Currently, the most effective means of Human Recognition is to use biometric system. So while designing biometric system, security of the system is one of the factors which have to be considered along with the increasing performance at reasonable costs. The objective of this paper is to explore the potential of fast developing Biometric systems such as fingerprints, face recognition, iris recognition for human identification. This paper discusses the main features of the biometric system: architecture, evaluation methodology used in these system and also various issues related to security of the biometric system. Keywords Biometric, Face Recognition, Iris Recognitions, template matching 1. INTRODUCTION The human recognition system is now a desired requirement of our security and surveillance systems. Biometric recognition is a crucial tool being used in commercial, government and forensic applications .The term biometrics is derived from the Greek words bios and metron which literally translates as life measurement. The national Institute of Standards and Technology defines ‘biometric’ as the automatic recognition of a person based on physiological or behavioral characteristics [5]. Biometrics is the use of physical or behavioral traits to verify personal identity. It is defined as the automated use of physiological or behavioral characteristics to determine or verify an individual’s identity. The above characteristics include visual images like fingerprints, face, iris and other human phenomena such as speech, gait, DNA, and indeed anything at all which might help to uniquely identify the individual [2][3]. In general terms, a biometric is observed data of a human that allows the identity of that person to be determined. Traditional personal authentication systems are either knowledge based (e.g., password) or possession based (e.g., ID card) they are not able to meet strict security performance requirements of a number of modern applications. The traditional approaches are unable to differentiate between an authorized person and an impostor (person pretending to be somebody he/she is not) Biometric systems are good alternatives to traditional methods because the traits used in these systems are not easily changed or imitated, and they cannot be forgotten as in the case for passwords, nor can they be lost in the same manner as identification cards. These biometric systems are more reliable as the data cannot be lost and are more user-friendly as the person has nothing to remember or carry. Every biometric system has its own strengths and weaknesses; however, for a biometric to be effective it should have the following requisite properties: (1) Universality (every person should have that characteristic) (2) Uniqueness (no two people should be exactly the same in terms of that characteristic) (3) Permanent (invariant with time) (4) Collectable (can be measured quantitatively) (5) Reliable (must be safe and operate at a satisfactory performance level) (6) Acceptable (non-invasive and socially tolerable) (7) Non-circumvent able (how easily the system is fooled into granting access to impostors) [1] [4]. 2. ARCHITECTURE OF BIOMETRIC SYSTEM The system working of biometric system can be explained with the help of the following units which describes the architecture of the system 2.1 Data Capturing Device: it is a sensing device comprising of camera required to acquire the raw image of individual biometric data and this data is submitted to Feature extraction unit .The quality of the raw data is impacted by the characteristics of the sensing device. 2.2 Feature Extraction Unit: To improve the quality of acquired data it is subjected to image enhancement algorithm in order to improve its quality. The data is processed and a set of salient discriminatory features are extracted to represent the underlying trait. The feature set extracted is stored in database in form of template.