CFP last date
20 December 2024
Call for Paper
January Edition
IJCA solicits high quality original research papers for the upcoming January edition of the journal. The last date of research paper submission is 20 December 2024

Submit your paper
Know more
The week's pick
Responsive image
Improved Shuffled Frog Leaping Algorithm with Self-Adaptive Shuffling for Fuzzy Logic PD+G Controller Optimization in Robotic Manipulators

Duc Hoang Nguyen
Random Articles
Reseach Article

Performance Evaluation of Resnet Model on Sign Language Recognition

by Millicent Agangiba, Ezekiel M. Martey, William A. Agangiba, Obed Appiah
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 184 - Number 43
Year of Publication: 2023
Authors: Millicent Agangiba, Ezekiel M. Martey, William A. Agangiba, Obed Appiah
10.5120/ijca2023922534

Millicent Agangiba, Ezekiel M. Martey, William A. Agangiba, Obed Appiah . Performance Evaluation of Resnet Model on Sign Language Recognition. International Journal of Computer Applications. 184, 43 ( Jan 2023), 22-27. DOI=10.5120/ijca2023922534

@article{ 10.5120/ijca2023922534,
author = { Millicent Agangiba, Ezekiel M. Martey, William A. Agangiba, Obed Appiah },
title = { Performance Evaluation of Resnet Model on Sign Language Recognition },
journal = { International Journal of Computer Applications },
issue_date = { Jan 2023 },
volume = { 184 },
number = { 43 },
month = { Jan },
year = { 2023 },
issn = { 0975-8887 },
pages = { 22-27 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume184/number43/32597-2023922534/ },
doi = { 10.5120/ijca2023922534 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T01:23:53.185900+05:30
%A Millicent Agangiba
%A Ezekiel M. Martey
%A William A. Agangiba
%A Obed Appiah
%T Performance Evaluation of Resnet Model on Sign Language Recognition
%J International Journal of Computer Applications
%@ 0975-8887
%V 184
%N 43
%P 22-27
%D 2023
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Communication is an important tool for sharing one’s ideas and thoughts and as such its role in our everyday lives cannot be over emphasised. Sign language is a form of communication used by the deaf and those hard-of-hearing. However, a challenge arises when deaf people have to communicate their ideas to those in the mainstream population. An automatic translator can be an effective way to address this problem. In this study, the performance of the ResNet model and its variants are evaluated on two different datasets. The first dataset contains images of American Sign language (ASL) data and the second dataset consists of images of Indian Sign language (ISL). The is a one-handed sign language, while ISL is mainly a two-handed sign language with complex shapes. ResNet variants such as Resnet18, ResNet34, ResNet50, ResNet101 and ResNet152 have been tested on these standard datasets. We conducted experiments by using deep neural networks to make recommendations and predictions in sign language. Experimental results using a standard dataset demonstrate that the model with 152 layers achieves the highest accuracy.

References
  1. Bickenbach, J.E., Cieza, A. and Sabariego, C., (2016), “Disability and Public Health” Int. J. Environ. Res. Public Health, Vol. 13, pp. 123-132.
  2. Groce, N.E., 2018. Global disability: an emerging issue. The Lancet Global Health, 6(7), pp.e724-e725.
  3. Agangiba, M., “Accessibility of E-government Services for Persons with Disabilities in Developing Countries- The Case of Ghana ”, Unpublished Doctoral Thesis, Department of Information Systems, University of Cape Town, South Africa, 290pp.
  4. Gedam, S. and Shrawankar, U. (2017), "Challenges and opportunities in fingerspelling recognition in the air", In International Conference on Innovative Mechanisms for Industry Applications, Bengaluru, India, pp. 60 – 65.
  5. Nair, A.V. and Bindu, V., (2013), “A review on Indian sign language recognition”, International journal of computer applications, Vol. 73, No. 22, pp. 33-38.
  6. Mahesh, M., Jayaprakash, A. and Geetha, M., 2017, September. Sign language translator for mobile platforms. In 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI) (pp. 1176-1181). IEEE.
  7. Brown, L. D., Hua, H., and Gao, C. 2003. A widget framework for augmented interaction in SCAPE.
  8. Bousbai, K. and Merah, M., (2019), “A Comparative Study of Hand Gestures Recognition Based on MobileNetV2 and ConvNet Models”, In International Conference on Image and Signal Processing and their Applications (ISPA), Mostaganem, Algeria, pp. 1-6.
  9. Kusters, A., De Meulder, M., and O’Brien, D. (2017), Innovations in deaf studies: The role of deaf scholars, Oxford University Press, 416 pp.
  10. Bhujbal, V.P., and Warhade, K.K., (2018), “Hand sign recognition-based communication system for speech disable people", ICICCS 2018, In Proceedings of the 2nd International Conference on Intelligent Computing and Control Systems, Madurai, India, pp. 348 – 352.
  11. Singleton, J. L., Remillard, E. T., Mitzner, T. L., and Rogers, W. A. (2019), “Everyday technology use among older deaf adults” Disability and Rehabilitation: Assistive Technology, Vol. 14, No. 4, pp. 325-332.
  12. Dhiman, R., Joshi, G. and Krishna, C.R., (2021), “A deep learning approach for Indian sign language gestures classification with different backgrounds” In Journal of Physics: Conference Series, Vol. 1950, No. 1, pp. 1-15
  13. Mannan, A., Abbasi, A., Javed, A. R., Ahsan, A., Gadekallu, T. R., & Xin, Q. (2022). Hypertuned deep convolutional neural network for sign language recognition. Computational Intelligence and Neuroscience.
  14. Lum, K.Y., Goh, Y.H. and Lee, Y.B., 2020. American Sign Language recognition based on MobileNetV2. Adv. Sci. Technol. Eng. Syst., 5(6), pp.481-488.
  15. Agrawal, M., Ainapure, R., Agrawal, S., Bhosale, S., & Desai, S. (2020, October). Models for hand gesture recognition using deep learning. In 2020 IEEE 5th International Conference on Computing Communication and Automation (ICCCA) (pp. 589-594). IEEE.
  16. He, K., Zhang, X., Ren, S. and Sun, J. (2016), “Deep residual learning for image recognition", In Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 770 – 778.
  17. Rathi, P., Kuwar Gupta, R., Agarwal, S. and Shukla, A., 2020, February. Sign language recognition using resnet50 deep neural network architecture. In 5th International Conference on Next Generation Computing Technologies (NGCT-2019).
  18. Saleh, Y. & Issa, G. (2020). “Arabic Sign Language Recognition through Deep Neural Networks Fine-Tuning”. International Association of Online Engineering. https://www.learntechlib.org/p/217934/. Accessed: 21 June 2022
  19. Alleema, N., & Chandrasekaran, S. (2022). Recognition of American Sign Language Using Modified Deep Residual CNN with Modified Canny Edge Segmentation.
  20. Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q. (2016), “Deep networks with stochastic depth”, In Conference on Computer Vision, Amsterdam, The Netherlands, pp. 646–661.
  21. Veit, A.; Wilber, M.J.; Belongie, S. (2016), “Residual networks behave like ensembles of relatively shallow networks”, In Advances in Neural Information Processing Systems; NIPS, Montreal, QC, Canada, pp. 550–558.
  22. Wu, Z., Shen, C., Van Den Hengel, A. (2019), “Wider or deeper: Revisiting the resnet model for visual recognition”, Pattern Recognition, Vol. 90, 119-133.
  23. Glorot, X.; Bordes, A.; Bengio, Y, (2011), “Deep sparse rectifier neural networks”, In International Conference on Artificial Intelligence and Statistics, Lauderdale, FL, USA, pp. 315–323.
  24. Ioffe, S., Szegedy, C. (2015), “Batch normalization: Accelerating deep network training by reducing internal covariate shift”, www.arxiv.org. Accessed: September 15, 2021.
  25. Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K. (2017), “Aggregated residual transformations for deep neural networks”, In Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, pp. 1492–1500.
  26. Akash, K., (2016), “Image data set for alphabets in the American Sign Language”, www.kaggle.com. Accessed: August 4, 2021.
  27. Sonawane V. (2018), Indian Sign Language Dataset. www.kaggle.com. Accessed: August 20, 2021.
  28. Khun, M. and Johnson, K. (2013), Applied Predictive Modeling, Springer, Basel, 600pp.
  29. Krizhevsky, A., Sutskever, I. and Hinton, G. E. (2012), “ImageNet Classification with Deep Convolutional Neural Networks”, In Advances in Neural Information Processing Systems, Lake Tahoe, Nevada, USA, pp. 1097 – 1105.
  30. Rumelhart, D. E., Hinton, G. E. and Williams, R. J. (1986), “Learning representations by back-propagating errors", Nature, Vol. 323, pp. 533 – 536.
  31. Loshchilov, I. and Hutter, F. (2019), “Decoupled Weight Decay Regularization”, In International Conference on Learning Representations (ICLR), New Orleans, Louisiana, USA, pp. 1-19.
  32. Kingma, D. P. and Ba, J. (2015), “Adam: A Method for Stochastic Optimization" In International Conference on Learning Representations (ICLR), San Diego, CA, USA, pp. 1-15.
  33. Wilson, A. C., Roelofs, R., Stern, M., Srebro, N. and Recht, B. (2017), “The Marginal Value of Adaptive Gradient Methods in Machine Learning”, In Conference on Neural Information Processing System, Long Beach, CA, USA, pp. 1-14.
  34. Smith, L. N. (2018), A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay, US Naval, 21pp.
Index Terms

Computer Science
Information Sciences

Keywords

Deep Neural Network ResNet American Sign Language Indian Sign Language Image Recognition

Powered by PhDFocusTM