A Secure Boot Loader System for Loading an Operating System with Fingerprint Authentication

Abstract

In today’s world, people are constantly on move and portable systems are in demand. With technology advancement, people exploit different types of memory devices for a portable system. For any external boot medium, the BIOS boot order setting change is required. The dynamic boot loader successfully eliminated this dependency and allowed the user to directly boot from any portable USB. The usage of USB has grown exponentially in recent years and securing it has become a major concern. In this paper, the USB is devised as a highly secured portable boot medium with fingerprint authentication to ensure data security. It performs feature extraction by combining both Local Directional Pattern (LDP) and Histograms of Oriented Gradients (HOG) which improves the accuracy rate. The classification is performed by random forest classifier, such that the intended users alone are granted access to the private storage area of the USB drive.

Biometrically Authenticated Boot Loading System from USB Drive by Exploiting the Fingerprint and Finger Vein

“…USB is devised as a highly secured portable boot medium with fingerprint authentication to ensure data security in [8]. The features database is constructed by extracting features using Local Directional Pattern (LDP) and Histograms of Oriented Gradients (HOG) features and classification and recognition is performed using random forest classifier.…”

“…Additionally, the basic concept is simple when the recorded biometric is matched with the current one, then the access is granted to the legitimate user. In the previous work [8], fingerprint alone is utilized to ensure authentication. Though the performance of the work is satisfactory, the False Positive (FP) and False Negative (FN) rates are planned to be minimized further.…”

“…The fingerprint is processed as in the case of the previously proposed work [8]. The fingerprint is processed to extract the Local Directional Pattern (LDP) and the Histograms of Oriented Gradients (HOG) features.…”

“…The collected features are reduced by means of IGR [8]. Now, the features of finger print and finger vein are combined together for forming the final feature set of this work.…”

“…The final FS is built by concatenating the features of both the biometrics being utilized by this work. The final FS is utilized for training the random forest classifier [8] for granting access to the USB drive. Hence, this section is completely meant for providing biometric security to attain secure boot load.…”