Abstract In this paper, we propose an efficient trajectories analysis solution for the recognition of Isolated Word Sign Language (IWSL). The key technique innovation in this work is the shape trajectories analysis based on the deep learning method and achieved impressive results on different IWSL data sets: German: Rheinisch Westfälische Technische Hochschule(RWTH): RWTH-Boston-50 and RWTH-Boston-104(95.83%), Signer-Independent Continuous Sign Language Recognition for Large Vocabulary Using Subunit Models (SIGNUM: 98.21%) and new Tunisian Sign Language database (TunSigns: 98%).

References

[1] Agrawal S., Jalal A., Tripathi R., “A Survey on Manual and Non-Manual Sign Language Recognition for Isolated and Continuous Sign,” International Journal of Applied Pattern Recognition, vol. 3, pp. 137-145, 2016.

[2] Balaji S. and Karthikeyan S., “A Survey on Moving Object Tracking Using Image Processing,” in Proceedings of International Conference on Intelligent Systems and Control, Coimbatore, pp. 469-474, 2017.

[3] Ben-Tanfous A., Drira H., and Ben-Amor B., “Coding Kendall’s Shape Trajectories for 3D Action Recognition,” in Proceedings of IEEE Computer Vision and Pattern Recognition, Salt Lake City, pp. 2840-2849, 2018.

[4] Bhuyan M., Bora P., and Ghosh D., “Trajectory Guided Recognition of Hand Gestures Having Only Global Motions,” World Academy of 666 The International Arab Journal of Information Technology, Vol. 19, No. 4, July 2022 Science, Engineering and Technology, vol. 21, pp.753-764, 2008.

[5] Boulares M. and Jemni M., “3d Motion Trajectory Analysis Approach to Improve Sign Language 3dbased Content Recognition” Procedia Computer Science, vol. 13, pp. 133- 143, 2012.

[6] Fakhfakh S. and Ben-Jemaa Y., “Hand and Wrist Localization Approach for Features Extraction in Arabic Sign Language Recognition,” in Proceedings of IEEE/ACS 14th International Conference on Computer Systems and Applications, Hammamet, pp. 774-780, 2017.

[7] Fakhfakh S. and Ben-Jemaa Y., “Gesture Recognition System for Isolated Word Sign Language Based on Key-Point Trajectory Matrix,” Computación y Sistemas, vol. 22, no. 4, pp. 1415-1430, 2018.

[8] Gopura R., Bandara D., Gunasekera N., Hapuarachchi V., and Ariyarathna B., “A Prosthetic Hand with Self-Adaptive Fingers,” in Proceedings of 3rd International Conference on Control, Automation and Robotics, Nagoya, pp. 269- 274, 2017.

[9] Li G., Wu H., Jiang G., Xu S., and Liu H., “Dynamic Gesture Recognition in the Internet of Things,” IEEE Access, vol. 7, pp. 23713-23724, 2019.

[10] Lim K., Tan A., Lee C., and Tan S., “Isolated Sign Language Recognition using Convolutional Neural Network Hand Modeling and Hand Energy Image,” Multimedia Tools and Applications, vol. 78, no. 14, pp. 19917-19944, 2019.

[11] Lin W. and Hsieh C., “Kernel-Based Representation for 2d/3d Motion Trajectory Retrieval and Classification,” Pattern Recognition, vol. 46, pp. 662- 670, 2013.

[12] Mohandes M. and Deriche M., “Arabic Sign Language Recognition by Decisions Fusion using Dempster-Shafer Theory of Evidence,” in Proceedings of Computing, Communications and IT Applications Conference, Hong Kong, pp. 90- 94, 2013.

[13] Noubigh Z. and Kherallah M., “A Survey on Handwriting Recognition Based on the Trajectory Recovery Technique,” in Proceedings of 1st International Workshop on Arabic Script Analysis and Recognition, Nancy, pp. 69-73, 2017.

[14] Sidig A. and Mahmoud S., “Trajectory based Arabic Sign Language Recognition,” International Journal of Advanced Computer Science and Applications, vol. 9, no. 4, pp. 283- 291, 2018.

[15] Singh K., David N., Hsiao C., Jacob M., Patel K., and Magerko B., “Recognizing Actions in Motion Trajectories Using Deep Neural Networks,” in Proceedings of AAAI Conferenceon Artificial Intelligence and Interactive Digital Entertainment, pp. 211-217, 2016.

[16] Teow M., “Understanding Convolutional Neural Networks using A Minimal Model for Handwritten Digit Recognition,” in Proceedings IEEE 2nd International Conference on Automatic Control and Intelligent Systems, Kota Kinabalu, pp. 167-172, 2017.

[17] 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, no. 1, pp. 99- 134, 2020.

[18] Von-Agris U. and Kraiss K., “Towards a Video Corpus for Signer-Independent Continuous Sign Language Recognition,” in Proceedings of International Workshop on Gesture in Human- Computer Interaction and Simulation, Lisbon, pp. 10-11, 2007.

[19] Wang H., Stefan A., Moradi S., Athitsos V., Neidle C., and Kamangar F., “A System for Large Vocabulary Sign Search,” in Proceedings of European Conference on Computer Vision, Berlin, pp. 342-353, 2012.

[20] Zhang Q., Wu Y., and Zhu S., “Interpretable Convolutional Neural Networks,” in Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, pp. 8827-8836, 2018. Sana Fakhfakh She obtained the Master in computer science and multimedia from Institute of Computer Science and Multimedia of Sfax (ISIMS) in 2013 and Ph.D. degree in computer systems engineering in February 2020 from the National Engineers School of Sfax (ENIS). His research interests include signal processing, image and video processing, and machine learning. Yousra Ben Jemaa She obtained the engineering degree from Tunisia Polytechnic School in 1997 and the Master in signal processing from SUPELEC in France in 1998 She received the Ph.D degree in Electrical Engineering in February 2003 and the HDR in Telecommunications in June 2012 from the National Engineers School of Tunis (ENIT). She joined National Engineers School of Sfax (ENIS) in 2000 where she is actually a full professor. Yousra Ben Jemaa: She obtained the engineering degree from Tunisia Polytechnic School in 1997 and the Master in signal processing from SUPELEC in France in 1998 She received the Ph.D degree in Electrical Engineering in February 2003