Glove-Based Classification of Hand Gestures for Arabic Sign Language Using Faster-CNN



Abstract Views
103

Downloads
100

Citations

Share

##plugins.themes.bootstrap3.article.sidebar##

Submitted Aug 3, 2023
Published Sep 29, 2023
10.24018/ejeng.2023.8.5.3092

Abstract viewed = 103 times

Table of Contents

##plugins.themes.bootstrap3.article.main##

Recently, American Sign Language has been widely researched to help disabled people to communicate with others. However; the Arabic Sign Language “ASL” has received much less attention. This paper has proposed a smart glove which has been designed using flex sensors to collect a dataset about hand gestures applying ASL. The dataset is composed of resistance and voltage measurements for the bending of the fingers to represent alpha-numeric characters. The measurements are manipulated using normalization and zero referencing methods to create the dataset. A Convolutional Neural Network ‘CNN’ composed of twenty-one layers is proposed. The dataset is used to train the CNN, and the Accuracy and Loss parameters are used to characterize its success. The dataset is classified with an average success rate of 95% based on the classification accuracy. Loss has decreased from 3 to less than 0.5. The proposed CNN layers have classified ASL characters with a reasonable degree of accuracy.

Keywords: Arabic Sign Language Batch Normalization Layer Convolution Neural Network reLU Layer

Downloads

Download data is not yet available.

References

  1. Cruz PJ, Vásconez JP, Romero R, Chico A, Benalcázar ME, Álvarez R, Barona López LI, Valdivieso Caraguay ÁL. A Deep Q-Network based hand gesture recognition system for control of robotic platforms. Scientific Reports. 2023;13(1):2045-2322. doi: 10.1038/s41598-023-34540-x
    DOI  |   Google Scholar
  2. Cabrera, Maria & Bogado, Juan & Fermín, Leonardo & Acuña, Raul & Ralev, Dimitar. Glove-Based Gesture Recognition System. Book: Adaptive Mobile Robotics (pp.747-753). 2012. Doi: 10.1142/9789814415958_0095.
    DOI  |   Google Scholar
  3. Abhishek KS, Qubeley LCF, Ho D. Glove-based hand gesture recognition sign language translator using capacitive touch sensor. 2016 IEEE International Conference on Electron Devices and Solid-State Circuits (EDSSC), Hong Kong, China, 2016, pp. 334-337, doi: 10.1109/EDSSC.2016.7785276.
    DOI  |   Google Scholar
  4. Zanghieri M. sEMG-based Hand gesture recognition with deep learning. arXiv:2306.10954v1 [10eess.SP]. 2023. https://doi.org/10.48550/arXiv.2306.10954.
     Google Scholar
  5. Bello H, Suh S, Geigler D, Ray L, Zhou B, Lukowicz P. CaptAinGlove: Capacitive and inertial fusion-based glove for real-time on edge hand gesture recognition for drone control; arXiv:2306.04319v1 [10cs.LG]. 2023. https://doi.org/10.48550/arXiv.2306.04319.
     Google Scholar
  6. Al-Saedi AKH, Al-Asadi AHH. Survey of hand gesture recognition systems. Journal Physics: Conf. Ser. 2019:1294 042003.
    DOI  |   Google Scholar
  7. FLEX SENSOR. https://www.sensorprod.com/pdf/flex-sensor.pdf, visited on first of April 2023.
     Google Scholar
  8. Ogundokun RO, Maskeliunas R, Misra S, Damaševičius R. Improved CNN based on batch normalization and adam optimizer. In: Gervasi O, Murgante B, Misra S, Rocha AMAC, Garau C. (eds). Computational Science and Its Applications – ICCSA 2022 Workshops. ICCSA 2022. Lecture Notes in Computer Science, 2022;13381. Springer, Cham. https://doi.org/10.1007/978-3-031-10548-7_43.
    DOI  |   Google Scholar
  9. Nair V and Hinton G. Rectified linear units improve restricted Boltzmann machines vinod nair. Proceedings of ICML. 2010;27:807-814.
     Google Scholar
  10. Zreik, Majd & Leiner, Tim & De Vos, Bob & van Hamersvelt, Robbert & Viergever, Max & Isgum, Ivana. Automatic segmentation of the left ventricle in cardiac CT angiography using convolutional neural networks. 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI 2016). p:40-43. DOI: 10.1109/ISBI.2016.7493206.
    DOI  |   Google Scholar
  11. Liu Y, Gao Y, Yin W. An improved analysis of stochastic gradient descent with momentum. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada, 2020.
     Google Scholar
  12. Latif G, Mohammad N, Alghazo J, AlKhalaf R, AlKhalaf R. ArASL: Arabic alphabets sign language dataset. Open Access. 2021. DOI:https://doi.org/10.1016/j.dib.2019.103777.
    DOI  |   Google Scholar
  13. Glorot X and Bengio Y. Understanding the difficulty of training deep feedforward neural networks. Journal of Machine Learning Research - Proceedings Track. 2010;9:249-256.
     Google Scholar
  14. Gomes D and Saif S. Robust Underwater fish detection using an enhanced convolutional neural network. International Journal of Image Graphics and Signal Processing. 2021;13:44-54. 10.5815/ijigsp.2021.03.04.
    DOI  |   Google Scholar