A Survey of Machine Learning Techniques for Sign  Language Translation

Manish Kumar; Ayush Kumar; Aditi Patni; Gourav Mishra; Sridevi G M

A Survey of Machine Learning Techniques for Sign Language Translation

March 2024

Vol-10, Issue-2

Paper ID: 22722

ISSN: 2395-4396

Downloads: 0

Abstract & Details

Research Area

Computer Engineering

Keywords

Sign language recognition Machine learning algorithms Convolutional Neural Network (CNN) K-Nearest Neighbor (KNN) Random Forest Support Vector Machine (SVM) American Sign Language (ASL) Accessibility Communication Inclusivity Training tool Real-time recognition Gesture recognition Image processing Computer vision Keypoint detection Accuracy Social inclusion Semantic understanding.

Abstract

Bridging the communication gap between deaf and non-verbal communities has long been a vital objective, with sign language recognition playing a crucial role. This research delves into the realm of automated sign language recognition, specifically focusing on American Sign Language (ASL) and leveraging the prominent ASL pickle data. Employing various machine learning algorithms, including Random Forest, Support Vector Machines, Convolutional Neural Network and K Nearest Neighbors, this study investigates key-point detection-based approaches to ASL recognition. The model's performance is analyzed in great detail through exhaustive testing, utilizing metrics such as F1 score, precision, and recall to determine the most effective approach. To improve user interaction, a user friendly graphical user interface (GUI) is implemented, allowing for effortless interaction and prediction generation using the best machine learning model. Additionally, this paper provides a thorough review of the various techniques used for sign language translation.

License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author Information

#	Name	Institute / Affiliation
1	Manish Kumar	Dayananda Sagar Academy of Technology and Management (DSATM)
2	Ayush Kumar	Dayananda Sagar Academy of Technology and Management (DSATM)
3	Aditi Patni	Dayananda Sagar Academy of Technology and Management (DSATM)
4	Gourav Mishra	Dayananda Sagar Academy of Technology and Management (DSATM)
5	Sridevi G M	Dayananda Sagar Academy of Technology and Management (DSATM)

How to Cite

Use the following formats to cite this article in your research.

APA Style

Kumar, Manish, Kumar, Ayush, Patni, Aditi, Mishra, Gourav, & M, Sridevi G (2024). A Survey of Machine Learning Techniques for Sign Language Translation. International Journal of Advance Research and Innovative Ideas In Education, 10(2), 191-200.

MLA Style

Kumar, Manish, et al. "A Survey of Machine Learning Techniques for Sign Language Translation." International Journal of Advance Research and Innovative Ideas In Education, vol. 10, no. 2, 2024, pp. 191-200.

IEEE Style

Manish Kumar, Ayush Kumar, Aditi Patni, Gourav Mishra, and Sridevi G M, "A Survey of Machine Learning Techniques for Sign Language Translation," International Journal of Advance Research and Innovative Ideas In Education, vol. 10, no. 2, pp. 191-200, 2024.

Vancouver Style

Kumar Manish, Kumar Ayush, Patni Aditi, Mishra Gourav, M Sridevi G. A Survey of Machine Learning Techniques for Sign Language Translation. International Journal of Advance Research and Innovative Ideas In Education. 2024;10(2):191-200.

Harvard Style

Kumar, Manish, Kumar, Ayush, Patni, Aditi, Mishra, Gourav, & M, Sridevi G (2024) 'A Survey of Machine Learning Techniques for Sign Language Translation', International Journal of Advance Research and Innovative Ideas In Education, 10(2), pp. 191-200.

Chicago Style

Kumar, Manish, et al. "A Survey of Machine Learning Techniques for Sign Language Translation." International Journal of Advance Research and Innovative Ideas In Education 10, no. 2 (2024): 191-200.

Turabian Style

Kumar, Manish, et al. "A Survey of Machine Learning Techniques for Sign Language Translation." International Journal of Advance Research and Innovative Ideas In Education 10, no. 2 (2024): 191-200.