International Research Journal of Engineering and Technology (IRJET) Volume: 04 Issue: 04 | Apr -2017
www.irjet.net
e-ISSN: 2395 -0056 p-ISSN: 2395-0072
A Multimodal Biometric Authentication for Speech Controlled Automobile System Akshay Ramesh1, Sayantan Chakraborty2, Jaykumar Chaudhary3 1,2,3Department of Electronics & Telecommunication Engineering Patel School of Technology Management & Engineering,NMIMS(Deemed-to-be University),Mumbai,Maharashtra,India ---------------------------------------------------------------------***--------------------------------------------------------------------1,2,3Mukesh
Abstract - Biometrics has been a subject of research by many scholars throughout these years. A biometric system consisting of only on a single biometric identifier in making a personal identification does not meet the desired performance requirements. Personal Identification Numbers (PIN) and key devices are not reliable and accurate techniques in secure environments. We introduce a multimodal biometric system on JAVA platform, which integrates face recognition, fingerprint verification, and speech recognition in making a personal identification. This system takes advantage of the capabilities of each individual biometrics. The processed information from all these three module is combined with the help of fusion algorithm in context switching in which feature vectors are made independently for query images and are then compared to the enrolment templates which are stored during database preparation for each biometric trait. Further, this paper is to propose the integration of Biometric technology with Automobile system and controlling the system using Speech input once the authentication is done through Android and Arduino, thus visualizing the future possibilities of Biometric Authentication and its applications in vehicular world. Key Words: JAVA, Face Recognition, Speech Recognition, Fingerprint Recognition, Fusion, Bluetooth Technology, Arduino, Android, Automobile.
1. INTRODUCTION
1.1 Face Recognition Image processing is a field that deals with manipulation of image with intent to carry out to enhance image and to extract some useful information from it. In this work we used JAVA programming language in our |
1.2 Speech Recognition Speech recognition is also known as automatic speech recognition (ASR) or computer speech recognition which means understanding voice of the computer and performing any required task or the ability to match a voice against a provided or acquired vocabulary [2]. A speech recognition system consists of a microphone, for the person to speak into, and a speech recognition software. The software being described here uses Google voice and speech APIs. The voice command from the user is captured by microphone .this is then converted to text by using Google voice API. The text is then compared with the other previously defined commands inside the command configuration file. If it matches with any of them, then bash command associated with it will be executed.
1.3 Fingerprint Recognition
Biometric face, fingerprint and voice recognition are particularly attractive biometric approaches, since these three focuses on the same identifier that humans use primarily to distinguish one person from another: their “faces” and fingerprint is also around in criminal investigation since late 19th century[1]. One of the main goals of this system is to understand the complex human visual system as well as to use the knowledge of distinguishing one person’s fingerprint from others and how humans represent faces in order to discriminate different identities with high accuracy with the use of the two most universally accepted biometric mechanisms.
© 2017, IRJET
aim to develop successful face recognition with a high recognition rate. The Haar cascade classifier is used to detect faces on a Java application. The classifier uses data stored in an XML file to decide how to classify each image location. Classification assumes a fixed scale for the face, say 50x50 pixels. The algorithm runs a series of feature detecting filters over the examples and generates data based on the shape of the object. Once it has gathered this data, it can be used in the detection phase. In this phase a new object is introduced, and the same series of filters is passed over the object.
Impact Factor value: 5.181
|
The fingerprint biometrics system is considered as one of the most efficient and trusted security system. The main reason for its reliability is that a fingerprint cannot have a positive match with someone else who is an unauthorized user. Each and every individual has a unique fingerprint and making it impossible to hack it [3]. We have used Fingerprint Module-R305, which is a serial fingerprint scanner that can be directly connected to the PC’s com port, and to any controller via MAX232 IC. This Fingerprint scanner is capable of storing and comparing the fingerprint and accordingly giving the desired output. The scanner makes a copy of the fingerprint and compares its characteristics (such as branches and loops) to the ones stored beforehand.
ISO 9001:2008 Certified Journal
|
Page 1003