eCite Digital Repository

HandiText: handwriting recognition based on dynamic characteristics with incremental LSTM

Citation

Fang, L and Zhu, H and Lv, B and Liu, Z and Meng, W and Yu, Y and Ji, S and Cao, Z, HandiText: handwriting recognition based on dynamic characteristics with incremental LSTM, Journal of the Association for Computing Machinery, 37, (4) Article 111. ISSN 0004-5411 (2019) [Refereed Article]

Copyright Statement

Copyright 2019 Association for Computing Machinery

DOI: doi:10.1145/3385189

Abstract

The Internet of Things (IoT) is is a new manifestation of data science. In order to ensure the credibility of data about IoT devices, authentication has gradually become an important research topic in IoT ecosystem. However, traditional graphical passwords and text passwords can cause serious memory burdens. Therefore, a convenient method for determining user identity is needed. In this paper, we propose a handwriting recognition authentication scheme named HandiText based on behavior and biometrics features. When people write a word by hand, HandiText capture their static biological features and dynamic behavior features during the writing process (writing speed, pressure, etc.). The features are related to habits, which make it difficult for attackers to imitate. We also carry out algorithms comparisons and experiments evaluation to prove the reliability of our scheme. The experiment results show that the Long Short-Term Memory (LSTM) has best classification accuracy, reaching 99%, while keeping relatively low false positive rate and false negative rate. We also test other dataset, the average accuracy of HandiText reach 98%, with strong generalization ability. In addition, the 324 users we investigated indicated that they are willing to use this scheme on IoT devices.

Item Details

Item Type:Refereed Article
Keywords:security and privacy, biometrics, data science, Internet of Things, authentication, handwriting, LSTM, handtext
Research Division:Information and Computing Sciences
Research Group:Machine learning
Research Field:Neural networks
Objective Division:Defence
Objective Group:Defence
Objective Field:Intelligence, surveillance and space
UTAS Author:Cao, Z (Dr Zehong Cao)
ID Code:138995
Year Published:2019
Deposited By:Information and Communication Technology
Deposited On:2020-05-18
Last Modified:2020-07-29
Downloads:0

Repository Staff Only: item control page