CNN-Based Real-Time Indian Sign Language Recognition System

  • Alakesh SarkarEmail author
  • Anjan Kumar Talukdar
  • Kandarpa Kumar Sarma
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 119)


Sign language is a way by which deaf and dumb people can express their thoughts and feelings. Deaf and dumb people use hand shape, body movements, and facial expressions for communication. In this work, a vision-based Indian Sign Language Recognition system using a convolutional neural network (CNN) is implemented. The sign images are captured by a USB camera. To segment the hand region, background subtraction method is used. Two databases have been created for ISL. Each of the databases contains 26 alphabets having a total of 52,000 images. The system has been also tested in real time, where the sign alphabets by four signers in front of the camera are captured and it correctly recognized almost all of the signs. Accuracy of around 99.40% is obtained.


Indian sign language Convolutional neural network Real time 


  1. 1.
    Adithya V, Vinod PR, Gopalakrishnan U (2013) Artificial neural network based method for Indian sign language recognition. In: 2013 IEEE conference on information & communication technologies. IEEE, pp 1080–1085Google Scholar
  2. 2.
    Lokhande P, Prajapati R, Pansare S (2015) Data gloves for sign language recognition system. Int J Comput Appl 975:8887Google Scholar
  3. 3.
    Grobel K, Assan M (1997) Isolated sign language recognition using hidden Markov models. In: International conference on systems, man, and cybernetics. computational cybernetics and simulation, vol 1. IEEE, pp 162–167Google Scholar
  4. 4.
    Yi Z, Liangzhong F (2010) Moving object detection based on running average background and temporal difference. In: 2010 IEEE international conference on intelligent systems and knowledge engineering. IEEE, pp 270–272Google Scholar
  5. 5.
    Choudhury A, Talukdar AK, Sarma KK (2014) A conditional random field based Indian sign language recognition system under complex background. In: 2014 fourth international conference on communication systems and network technologies. IEEE, pp 900–904Google Scholar
  6. 6.
    Ghotkar AS, Khatal R, Khupase S, Asati S, Hadap M (2012) Hand gesture recognition for Indian sign language. In: 2012 international conference on computer communication and informatics. IEEE, pp 1–4Google Scholar
  7. 7.
    Singha J, Das K (2013) Recognition of Indian sign language in live video. arXiv preprint. arXiv:1306.1301
  8. 8.
    Sharma M, Pal R, Sahoo AK (2014) Indian sign language recognition using neural networks and KNN classifiers. ARPN J Eng Appl Sci 9(8)Google Scholar
  9. 9.
    Tavari NV, Deorankar AV (2014) Indian sign language recognition based on histograms of oriented gradient. Int J Comput Sci Inf Technol 5(3):3657–3660Google Scholar
  10. 10.

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Alakesh Sarkar
    • 1
    Email author
  • Anjan Kumar Talukdar
    • 1
  • Kandarpa Kumar Sarma
    • 1
  1. 1.Department of Electronics and Communication EngineeringGauhati UniversityJalukbariIndia

Personalised recommendations