Smart Device Authentication Based on Online Handwritten Script Identification and Word Recognition in Indic Scripts Using Zone-Wise Features

Smart Device Authentication Based on Online Handwritten Script Identification and Word Recognition in Indic Scripts Using Zone-Wise Features

Rajib Ghosh (Department of Computer Science and Engineering, National Institute of Technology, Patna, India), Partha Pratim Roy (Department of Computer Science and Engineering, Indian Institute of Technology Roorkee, Roorkee, India) and Prabhat Kumar (Department of Computer Science and Engineering, National Institute of Technology, Patna, India)
Copyright: © 2018 |Pages: 35
DOI: 10.4018/IJISMD.2018010102
OnDemand PDF Download:
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Secure authentication is a vital component for device security. The most basic form of authentication is by using passwords. With the evolution of smart devices, selecting stronger and unbreakable passwords have become a challenging task. Such passwords if written in native languages tend to offer improved security since attackers having no knowledge of such scripts finding it hard to crack. This article proposes two zone-wise feature extraction approaches - zone-wise structural and directional (ZSD) and zone-wise slopes of dominant points (ZSDP), to recognize online handwritten script and word in four major Indic scripts - Devanagari, Bengali, Telugu and Tamil. These features have been used separately and in combination in HMM-based platform for recognition purpose. The dimension reduction of the ZSD-ZSDP combination with factor analysis has shown the best performance in all the four scripts. This work can be utilized for setting up the authentication schemes with the Indic scripts' passwords thus rendering it difficult to crack by hackers having no knowledge of such scripts.
Article Preview
Top

1. Introduction

Recent growth in the field of Information Technology has led to development of smaller and smarter hand-held devices. Owing to their usage and benefits, these smart devices would become an indispensable part of our daily lives. However, although such smart devices would be of great use to the mankind, it should be kept in mind that they would eventually be the storehouses of our personal information of various kinds. This makes them highly susceptible to potential security breaches and attacks (Khari, Shrivastava, Gupta, & Gupta, 2017; Saxena, Shrivastava, & Sharma, 2012). In order to avoid any catastrophic situation, these smart devices would require proper user authentication mechanism (Ledru et al., 2015). User authentication is the essential component of a secure system and encompasses multiple aspects of security; viz. identification, verification and authorization. The elementary form of user authentication is by the use of passwords (Abhishek, Roshan, Kumar, & Ranjan, 2013). However, being only a series of characters (numeric, alphanumeric, and special characters), selecting a strong, unbreakable password becomes challenging sometimes. Generally, users tend to choose passwords that are short and easy to remember. Moreover, most of the devices provide supports for passwords in either Latin or other well-known scripts that are supported by their input keyboards. This renders the chosen password to be guessable and easy to crack using dictionary attacks. In order to counter such situations, use of handwritten texts as passwords can be a solution. Such passwords must be written in any native scripts only. Using such a mechanism of securing smart devices would provide an improved and enhanced security since intruding such devices would require identifying the script in which the password has been set, as well as the knowledge about that script (Malempati & Mogalla, 2011). This mechanism would, however, require efficient techniques for recognizing the handwritten scripts as well as the words. Moreover, the recognition techniques need to be online rather than offline.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 12: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing