Investigation of 3-D Relational Geometric Features for Kernel-Based 3-D Sign Language Recognition

• Published in: 2019 IEEE International Conference on Intelligent Systems and Green Technology (ICISGT) pp. 31 - 313
• Main Authors: Kiran, P. Sasi, Kumar, D. Anil, Kishore, P.V.V., Kumar, E. Kiran, Kumar, M. Teja Kiran, Sastry, A.S.C.S.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-06-2019
• Subjects: 3D Motion Capture; 3D Sign Language Recognition; Assistive technology; Feature extraction; Gesture recognition; Global Alignment Kernel; Kernel; Relational Joint Features; Sensors; Skeleton; Three-dimensional displays
• DOI: 10.1109/ICISGT44072.2019.00022

Extraction and recognition of human gestures in 3D sign language is a challenging task. 3D sign language gestures are a set of hand and finger movements with respect to face, head and body. 3D motion capture technology involves capturing 3D sign gesture videos that are often affected by background, self-occlusions and lighting. This paper investigates the relation between joints on 3D skeleton. Kernel based methods can be remarkably effective for recognizing 2D and 3D signs. This work explores the potential of global alignment kernels, we use 3D motion capture data for 3D sign language recognition. Accordingly, this paper encodes five 3D relational geometric features (distance, angle, surface, area and perimeter) into global alignment kernel based on similarities between query and database sequence. The proposed framework has been tested on 800 gestures captured by five subject (i.e., 5 × 800 = 4000) sign language dataset and three other publicly available action datasets, namely, CMU, HDM05 and NTU RGB-D. The proposed method outperforms when compared to other state-of-the-art methods on the above datasets.