International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 05 | May -2017
p-ISSN: 2395-0072
www.irjet.net
INTEGRATING FACE AND IRIS BIOMETRICS FOR SECURITY MOTIVE BY CHANGE DETECTION MECHANISM K.Suganthi1, D.Beulah David2 1Student,
Department of Computer Science and Engineering, Jeppiaar Engineering College, Chennai, India Department of Computer Science and Engineering, Jeppiaar Engineering College, Chennai, India
2AssistantProfessor,
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Security is predominant and prerogative to everybody who deserves it. Biometric authentication plays a pivotal role in security systems in the fields of commercial, banking, social and law enforcement area. In order to extirpate disorders and chaos, it is mandatory to have a strong biometric security system. Face and Iris recognition have been employed in various security systems. Besides improving performances, the fusion of both biometrics has several other advantages such as increasing user population coverage and reducing enrolment failure. Face and iris recognition is a challenging and interesting research topic in the field of pattern recognition. The thoroughgoing process of recognition is involved in three stages detection, feature extraction, recognition. Various techniques are required in these three stages so as to deal with the surrounding factors. The main notion of this project is to increase the performance of the face and iris recognition system by providing strong algorithm. This work is based on the concept of Change detection in order to handle the rare cases. Keywords: Face recognition, Iris recognition, Change detection, classifiers
1. INTRODUCTION Whenever people log onto computers, access an ATM, pass through airport security, use credit cards, or enter highsecurity areas, they need to verify their identities. People typically use user names, passwords, and identification cards to prove that they are who they claim to be. However, passwords can be forgotten, and identification cards `can be lost or stolen. Thus, there is tremendous interest in improved methods of reliable and secure identification of people. Biometric methods, which identify people based on physical or behavioral characteristics, are of interest because people cannot forget or lose their physical characteristics in the way that they can lose passwords or identity cards. Biometric methods based on the spatial pattern of face and the iris is believed to allow very high accuracy, and there has been an explosion of interest in iris biometrics in recent years. This paper justifies the novelty of combining face and
Š 2017, IRJET
|
Impact Factor value: 5.181
|
iris recognition based on several techniques used in different processes. Due to physical obscures such as hair growth or loss, age, scares, lighting, glasses, masks and injury at the iris or face may lead to the security system failure. As the user population increases the demand of storing all the data also increases that require large memory space. In order to address these two limitations the Change detection method can be used. Change detection is a statistical analysis used for comparing two images taken in different period of time. Classification is the process of identifying to which of a set of categories a new observation is belonged to. There are several algorithms used in classification process. Classifiers play a pivotal role in recognition process. The process of incorporating change detection into classifiers is expected to increase the reliability and performance likely. 2. PROBLEM DEFINITION Change is the only thing constant. Due to that fact everything in the atmosphere changes with respect to time. The biometric systems that employ a vital role in security systems relied and respond if and only if the input image is convincible. But in general, irrespective of any biometric security process the system gets confused by many physical obscures such as hair, age, scars, lighting, glasses, masks, background, and injury at the iris or at the face. If In case the input image is not matching with the image already stored in the database due some minor physical changes the permission is not provided even for the person who deserve it. This is the fascination behind this the work. To address this problem Change detection method is being used. Change detection is the statistical analysis used for comparing a pair of images of the same area taken at different time instances to measure the change by defining the basic thresholding method. Also as the rate of usage is increasing it is mandatory to provide a huge memory system. These are the two main problems to be focused on.
ISO 9001:2008 Certified Journal
|
Page 283