The International Arab Journal of Information Technology (IAJIT)


Real-Time Sign Language Fingerspelling Recognition using Convolutional Neural Network

Sign language allows mute people to communicate, problem occurs when a conversationalist fails to understand it. Despite efforts to address this problem, an effective solution is not yet found. In this work, Convolutional Neural Network (CNN) was trained on two different datasets separately- binary and Red Blue Green (RGB), each contains 25,900 images of Nigerian Sign Language. A deep neural pre-trained module was used to detect hand gestures in the video feed which tackled the issue of complex backgrounds, also showed excellent detection in dimly lit areas. The accuracies of (98.95%, 76%) and (98.87%, 98.85%) were obtained respectively on the training and the validation sets. The real time system developed implemented both models as a single system which makes it a unique one.

[1] Akansha T. and Bansal S., “Hybrid FiST_CNN Approach for Feature Extraction for Vision- Based Indian Sign Language Recognition,” The International Arab Journal of Information Technology, vol. 19, no. 3, pp. 403-411, 2022.

[2] Albawi S., Bayat O., Al-Azawi S., and Ucan O., “Social Touch Gesture Recognition Using Convolutional Neural Network,” Computational Intelligence and Neuroscience, pp. 1-10, 2018,

[3] Alonso D., Teyseyre A., Soria A., and Berdun L., “Hand Gesture Recognition in Real World Scenarios Using Approximate String Matching,” Multimedia Tools and Applications, vol. 79, pp. 20773-20794, 2020.

[4] Alzubaidi L., Zhang J., Humaidi A., Al-Dujaili A., and Duan Y., “Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions,” Journal of Big Data, Springers, vol. 8, no. 53, 2021.

[5] Amal H., Reny R., and Prathap B., “Hand Kinesis in Indian Sign Language Using NLP Techniques with SVM Based Polarity,” International Journal of Engineering and Advanced Technology, vol. 9, no. 4, pp. 2044- 2050, 2020. https//doi: 10.35940/ijeat. D8483.049420

[6] Ayachi R., Said Y., and Atri M., Study and Implementation of Deep Learning Algorithms for Object Detection, M.Sc Physics Thesis, University of Monastir, 2018.

[7] Baumgartner L., Jauss S., Maucher J., and Zimmermann G., “Automated Sign Language Translation: The Role of Artificial Intelligence Now and in Future,” in Proceedings of the 4th International Conference on Computer-Human Interaction Research and Applications, Budapest, pp. 170-177, 2020. /101438/101438.pdf

[8] Bhatt L., Patel C., Taisania H., Patel J., and Vashela R., “CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope,” Electronics, vol. 10, no. 20, pp. 1-28, 2021.

[9] Chourasia N., Kanchan D., and Supratim S., “Analysis on Hand Gesture Spotting Using Sign Language Through Computer Interfacing,” International Journal of Engineering Science and Innovative Technology, vol. 3, no. 3, pp. 132- 139, 2014. Doi: 018-1121-3

[10] Google, Mediapipe,, Last Visited, 2023.

[11] Kang B., Tripathi S., and Nguyen T., “Real-Time Sign Language Fingerspelling Recognition Using Convolutional Neural Networks from Depth Map,” in Proceedings of the 3rd Asian Conference on Pattern Recognition, Kuala Lumpur, pp. 1-5, 2015.

[12] Ketkar N., Deep Learning with Python- A Hand on Introduction, India, 2017. Doi: 10.1007/978- 1-4842-27 66-4

[13] Kour K. and Mathew L., “Literature Survey on Hand Posture Techniques for Sign Language Recognition,” International Journal of Technical 164 The International Arab Journal of Information Technology, Vol. 21, No. 1, January 2024 Research and Science, vol. 2, pp. 431-433, 2017. %20Survey%20on%20Hand%20Gesture%201.p df

[14] Lin J. and Ding Y., “A Temporal Hand Gesture Recognition System Based on Hog and Motion Trajectory,” Optik-International Journal for Light and Electron Optics, vol. 124, pp. 6795- 6798, 2013, https//doi:10.1016/j.ijleo.2013.05.097

[15] Liwicki S. and Everingham M., “Automatic Recognition of Fingerspelled Words in British Sign Language,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Miami, pp. 50-57, 2009, https//doi:10.1109/cvprw.2009.5204291

[16] Lopez I., Hand Gesture Recognition for Sign Language Transcription, M.Sc Computer Science Thesis, Boise State University, 2017. nt.cgi?article=2322&context=td

[17] Oguntimilehin A., Olatunji K., Abiodun A., Adeyemo A., and Balogun A., “A Review of Sign Language Recognition Techniques,” International Journal of Information Systems and Computer Sciences, vol. 10, no. 6, pp. 1-8, 2021.

[18] Palacios J., Sagüés C., Montijano E. and Llorente S., “Human-Computer Interaction Based on Hand Gestures Using RGB-D Sensors,” Sensors, vol. 13, no. 9, pp. 11842-11860, 2013.

[19] Rao K., Rajpal B., Prasad N., Pradeep N., and Shatri R., “A Survey on the Techniques Applied to The Recognition and Conversion of Indian Sign Language,” Journal of Applied Research on Industrial Engineering, vol. 8, pp. 399-411, 2020. https// .1214

[20] Roller O., Zargarian S., Ney H., and Bowden R., “Deep Sign: Enabling Robust Statistical Continuous Sign Language Recognition Via Hybrid CNN-Hmms,” International Journal of Computer Vision, vol. 126, pp. 1311-1325, 2018.

[21] Rumana R., Rani R., and Prema R., “A Review Paper on Sign Language Recognition for the Deaf and Dumb,” International Journal of Engineering Research and Technology, vol. 10, no. 10, pp. 329-332, 2021.

[22] Saleem M., Senan N., Wahid F., Aamir M., and Samad A., “Comparative Analysis of Recent Architecture of Convolutional Neural Network,” Mathematical Problems in Engineering, pp. 1-9, 2022. 2022/7313612

[23] Schönström K., “Sign Languages and Second Language Acquisition Research: An Introduction,” Journal of European 2nd Language Association, vol. 5, no. 1, pp. 30-43, 2021. https//doi:

[24] Sharma S., Saxena V., and Satish K., “Comparative Analysis on Sign Language Recognition System,” International Journal Scientific and Technology Research, vol. 8, pp. 981-990, 2019.

[25] Shivashankara S. and Srinath S., “American Sign Language Recognition System: An Optimal Approach,” International Journal of Image Graphics and Signal Processing, vol. 8, pp. 18- 30, 2018. https//doi: 10:5815 /ijigsp.2018.08.03

[26] Singh S., Gupta A., and Singh T., “Sign Language Recognition Using Hybrid Neural Networks,” International Journal of Innovative Technology and Exploring Engineering, vol. 9, no. 2, pp. 1092-1098, 2009. item/L33491081219/

[27] Tolentino L., Serfajuan R., Thio-ac A., Pamaboy M., and Forteza J., “Static Sign Language Recognition using Deep Learning,” International Journal of Machine Learning and Computing, vol. 9, pp. 821-827, 2019. DOI:10.18178/ijmlc.2019.9.6.879

[28] Tukhtaev S. and Whangbo T., “A Combined Method of Skin-and Depth-Based Hand Gesture Recognition,” The International Arab Journal of Information Technology, vol. 17, vo. 1, pp. 137- 145, 2020. doi:10.34028/iajit/17/1/16.

[29] Yildiz A., Adar N., and Mert A., “Convolutional Neural Network Network Based Hand Recognition in Sophisticated Background for Humanoid Robot Control,” The International Arab Journal of Information Technology, vol. 20, no. 3, pp. 368-375, 2023, doi.10.34028/iajit/20/3/9

[30] Zahid H., Rashid M., Hussain S., Azim F., and Syed S., “Recognition of Urdu Sign Language: A Systematic Review of the Machine Learning Classification,” Peej Computer Science, vol. 8, pp. 1-25, 2022. https//doi: 10,7717/peej-cs.833

[31] Ziaie P., Muller T., and Knoll A., “A Novel Approach to Hand-Gesture Recognition in A Human-Robot Dialog System,” in Proceedings of the 1st Workshops on Image Processing Theory, Tools and Applications, Sousse, pp. 1-8, 2008. DOI: 10.1109/IPTA.2008.4743760