A new framework for sign language alphabet hand posture recognition using geometrical features through artificial neural
- PDF / 4,763,166 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 95 Downloads / 179 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
A new framework for sign language alphabet hand posture recognition using geometrical features through artificial neural network (part 1) Hoshang Kolivand1,2
•
Saba Joudaki3 • Mohd Shahrizal Sunar1 • David Tully4
Received: 8 January 2020 / Accepted: 5 August 2020 The Author(s) 2020
Abstract Hand pose tracking is essential in sign languages. An automatic recognition of performed hand signs facilitates a number of applications, especially for people with speech impairment to communication with normal people. This framework which is called ASLNN proposes a new hand posture recognition technique for the American sign language alphabet based on the neural network which works on the geometrical feature extraction of hands. A user’s hand is captured by a threedimensional depth-based sensor camera; consequently, the hand is segmented according to the depth analysis features. The proposed system is called depth-based geometrical sign language recognition as named DGSLR. The DGSLR adopted in easier hand segmentation approach, which is further used in segmentation applications. The proposed geometrical feature extraction framework improves the accuracy of recognition due to unchangeable features against hand orientation compared to discrete cosine transform and moment invariant. The findings of the iterations demonstrate the combination of the extracted features resulted to improved accuracy rates. Then, an artificial neural network is used to drive desired outcomes. ASLNN is proficient to hand posture recognition and provides accuracy up to 96.78% which will be discussed on the additional paper of this authors in this journal. Keywords Sign language alphabet Hand posture recognition Depth-based geometrical sign language Geometrical features sign language
1 Introduction
This work is prepared in two separated papers due to the complexity of prepared materials and needs of much discussion on the obtained results. Both papers are submitted at the same time in Neural Computing and Applications. & Hoshang Kolivand [email protected] 1
MaGIC-X (Media and Games Innovation Centre of Excellence), Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia
2
Department of Computer Science, Liverpool John Moores University, Liverpool L3 3AF, UK
3
Department of Computer Engineering, Khorramabad Branch, Islamic Azad University, Khorramabad, Iran
4
Scenegraph Studios, 4St Pauls Square, Liverpool L3 9SJ, UK
Hand posture recognition is applicable to many different domains. Even though various wearable instruments like gloves have been used recently, vision-based approaches are capable of capturing the actual hand postures without the need of a physical device. The recent mentioned methods make it possible for a more natural relationship between computers or other employed devices and users. Vision-based methods are increasingly becoming popular due to the considerable range of application fields, as reported in many recent surveys [1]. It should be note
Data Loading...
