Superresolution Reconstruction in Automatic Thai Sign Language Feature Extraction Using Adaptive Triangulation Interpolation

Authors

  • Eakbodin Gedkhaw Faculty of Information Technology and Digital Innovation. King's Mongkut University of Technology North Bangkok.
  • Mahasak Ketcham Faculty of Information Technology and Digital Innovation. King's Mongkut University of Technology North Bangkok.

DOI:

https://doi.org/10.3991/ijoe.v18i02.28147

Keywords:

Superresolution, Triangulation Interpolation, Thai Sign Language

Abstract


Superresolution is an image processing technique for improving image quality and enhancing low-resolution images. This paper presents a novel interpolation method for increasing superresolution reconstruction effectiveness using a triangulation interpolation algorithm for automatic Thai sign language feature extraction. This approach uses three neighboring pixels for estimation. The experiment compared the superresolution reconstruction performance using the triangulation interpolation algorithm and the nearest-neighbor, SRCNN, bilinear, bicubic, GPR, and NEDI methods. The super-resolution reconstruction using the triangulation-improved interpolation technique provided the best PSNR measurements of image quality between the original and superresolution-reconstructed images. The PSNR value of the sign language image was 40.608, improving performance by 13.15%. The Thai sign language gesture recognition using 2D convolutional neural networks showed that the designed model increased the gesture recognition effectiveness with an accuracy of 0.95 and loss of 0.14. Thus, this study provides state-of-the-art superresolution reconstruction for automatic Thai sign language gesture recognition.

Downloads

Published

2022-02-16

How to Cite

Gedkhaw, E., & Ketcham, M. (2022). Superresolution Reconstruction in Automatic Thai Sign Language Feature Extraction Using Adaptive Triangulation Interpolation. International Journal of Online and Biomedical Engineering (iJOE), 18(02), pp. 4–25. https://doi.org/10.3991/ijoe.v18i02.28147

Issue

Section

Papers