Citation

Azlin, Azra Izni Anis and Pang, Ying Han and Khoh, Wee How and Ooi, Shih Yin (2023) Hand Gesture Signature Recognition with Machine Learning Algorithms. Lecture Notes in Electrical Engineering, 983. pp. 389-398. ISSN 1876-1100

Full text not available from this repository.

Abstract

Hand gesture recognition is regarded as an imperative Human–Computer Interaction technology for non-verbal communication and interaction between human and computers. Inspired by hand gesture recognition systems, hand gesture signature recognition is proposed to replace the existing online handwritten signature recognition which requires a stylus pen and tablet as middleware between users and the systems. The possibility of germs contamination on these shared devices alerts public concerns, especially during this COVID-19 pandemic. Hence, an in-air signature recognition, termed as iSign, that utilizes hand gesture signing movement is proposed in this paper. In iSign, a Kinect Sensor is adopted to detect and capture the hand movement of the users while signing. This mode of data acquisition does not require users for any direct touch on any devices. Next, the captured video data is transformed into feature template. Various machine learning algorithms, i.e. Bayesian network, Naïve Bayes, Decision Tree, Random Forest etc., are examined to classify the hand gesture signatures. Empirical results demonstrate that Random Forest performs the best among the machine learning algorithms with accuracy of 93%.

Item Type:	Article
Uncontrolled Keywords:	Hand gesture, Signature recognition, Machine learning, Random forest
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	04 Jul 2023 01:54
Last Modified:	04 Jul 2023 01:54
URII:	http://shdl.mmu.edu.my/id/eprint/11502

Downloads

Edit (login required)