IJCT Current Issue IJCT Policy Indexing Low Cost Publication Publication Guidelines

International Journal of Computer Techniques Volume 12 Issue 3 | CONTINUOUS SIGN LANGUAGE RECOGNITION USING DEEP LEARNING: A CNN-BASED APPROACH

International Journal of Computer Techniques – Volume 12 Issue 3, May – June 2025

ISSN: 2394-2231 | https://ijctjournal.org/ | Page 1

Monalisha Aggarwal1, Ram Kumar Sharma2
1Information Technology, Noida Institute of Engineering and Technology (NIET), AKTU, Greater Noida, India. Email: monalisha.yes@gmail.com
2Information Technology, Noida Institute of Engineering and Technology (NIET), AKTU, Greater Noida, India. Email: ramkumar.sharma@niet.co.in

Abstract

The Sign Language, a visual language constructed mainly for the deaf, has emerged as an important mode of interaction for individuals unable to hear or speak. In the absence of supportive technologies, deaf individuals continue to face significant communication barriers. This paper proposes a dual-system model to address this challenge. The first component leverages a Convolutional Neural Network (CNN) developed using Keras to detect 44 hand gestures and convert them into alphanumeric text, aiding speech-impaired users. The second component integrates Django, JavaScript’s Speech API, and the Natural Language Toolkit (NLTK) to convert spoken language into animated sign language, facilitating communication for hearing-impaired users. This comprehensive system is real-time, affordable, and user-friendly, offering scalable inclusivity across various scenarios.

Keywords

CNN, Python, Speech Recognition, Sign Language, Real-time Communication

References

  1. Oliveira, T. et al. (2019). Automatic sign language translation to improve communication. IEEE EDUCON.
  2. Escudeiro, P. et al. (2014). Automatic sign language translator model. Advanced Science Letters, 20(2), 531–533.
  3. Zhang, J. et al. (2002). A PDA-based sign translator. IEEE Int. Conf. on Multimodal Interfaces.
  4. Sanaullah, M. et al. (2022). Real-time automatic translation of text to sign language. Computers, Materials & Continua, 70(2).
  5. Sinha, K. et al. (2022). Real-time sign language translator. CISC 2021, Springer.
  6. Luqman, H., & Mahmoud, S. A. (2019). Arabic text-to-sign language translation. Universal Access in the Information Society, 18(4), 939–951.
  7. Latif, G. et al. (2021). Arabic sign language translator. J. of Physics: Conf. Series, 1962(1), 012055.
  8. Hou, J. et al. (2019). SignSpeaker: smartwatch-based sign language translator. ACM Mobicom.
  9. Escudeiro, P. et al. (2013). Virtual sign translator. ICCNCE 2013, Atlantis Press.
  10. Mohammed, R. M., & Kadhem, S. M. (2021). Review on Arabic sign language systems. J. of Physics: Conf. Series, 1818(1), 012033.
  11. Ahmed, A. M. et al. (2016). ATASAT: Arabic sign to Arabic text system. J. of Computer Science and IT, 6, 109–122.
  12. Kahlon, N. K., & Singh, W. (2023). Machine translation from text to sign language: review. Universal Access in the Information Society, 22(1), 1–35.

How to Cite

Monalisha Aggarwal, Ram Kumar Sharma, “Continuous Sign Language Recognition Using Deep Learning: A CNN-Based Approach,” International Journal of Computer Techniques, Volume 12, Issue 3, May-June 2025. ISSN: 2394-2231

CONTINUOUS SIGN LANGUAGE RECOGNITION USING DEEP LEARNING A CNN-BASED APPROACHDownload

Tag

IJCT Latest News

Post Comment

Reviewer Board