ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Analysis On Different Methods For Sign Language Identification


Affiliations
1 Department of Computer Science, P.K.R. Arts College for Women, India
     

   Subscribe/Renew Journal


Sign language (SL) is the most organized and structured type of hand/arm gesture in the communicative hand/arm gesture taxonomies. The ability of machines to comprehend human actions and meanings has numerous uses. SL identification is one area of focus. SL is employed by the deaf and hard-of-hearing communities to communicate. Hearing-impaired persons communicate via visual indicators instead of vocal communication and sound patterns. SL also uses facial expressions and body postures as a medium of communication. Pattern matching, computer vision, natural language processing are the key factors in SL identification. This study reviews state-of-the-art methodologies employed in current SL identification research, comparing the various algorithms at each stage. Discuss the challenges and limitations of gesture identification research in general, as well as SL identification in particular. Overall, this paper gives a thorough introduction to the topic of automated SL identification, paving the way for future research.

Keywords

SL, Gesture Taxonomies, Deaf Community, Computer Vision, Pattern Matching, Natural Language Processing
Subscription Login to verify subscription
User
Notifications
Font Size

  • L. Pigou, S. Dieleman, P.J. Kindermans and B. Schrauwen, “SL Identification using Convolutional Neural Netstudys”, Proceedings of European Conference on Computer Vision, pp. 572-578, 2014.

  • P.V.V. Kishore, D.A. Kumar and E.K. Kumar, “Motionlets Matching with Adaptive Kernels for 3-D Indian SL Identification”, IEEE Sensors Journal, Vol. 18, No. 8, pp. 3327-3337, 2018.

  • D. Naglot and M. Kulkarni, “Real-Time SL Identification using the Leap Motion Controller”, Proceedings of International Conference on Inventive Computation Technologies, pp. 1-5, 2016.

  • Y. Liao, P. Xiong, W. Min and J. Lu, “Dynamic SL Identification based on Video Sequence with BLSTM-3D Residual Netstudys”, IEEE Access, Vol. 7, pp. 3804438054, 2019.

  • L. Geng, X. Ma, B. Xue and Y. Li, “Combining Features for Chinese SL Identification with Kinect”, Proceedings of IEEE International Conference on Control and Automation, pp. 1393-1398, 2014.

  • K.M. Lim, A.W. Tan and S.C. Tan, “Block-Based Histogram of Optical Flow for Isolated SL Identification”, Journal of Visual Communication and Image Representation, Vol. 40, pp. 538-545, 2016.

  • A. Mittal, P. Kumar, P.P. Roy and B.B. Chaudhuri, “A Modified LSTM Procedure for Continuous SL Identification using Leap Motion”, IEEE Sensors Journal, Vol. 19, No. 16, pp. 7056-7063, 2019.

  • X. Yang, X. Chen, X. Cao and X. Zhang, “Chinese SL Identification based on an Optimized Tree-Structure Framestudy”, IEEE Journal of Biomedical and Health Informatics, Vol. 21, No. 4, pp. 994-1004, 2016.

  • P.V.V. Kishore, M.V. Prasad and R. Rahul, “4-Camera Procedure for SL Identification using Elliptical Fourier Descriptors and ANN”, Proceedings of International Conference on Signal Processing and Communication Engineering Systems, pp. 34-38, 2015.

  • S. Jiang, B. Sun, L. Wang and Y. Fu, “Skeleton Aware Multi-Modal SL Identification”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Identification, pp. 3413-3423, 2021.

  • N. Tubaiz, T. Shanableh and K. Assaleh, “Glove-Based Continuous Arabic SL Identification in User-Dependent Mode”, IEEE Transactions on Human-Machine Systems, Vol. 45, No. 4, pp. 526-533, 2015.

  • J.L. Raheja, A. Mishra and A. Chaudhary, “Indian SL identification using SVM”, Pattern Identification and Image Analysis, Vol. 26, No. 2, pp. 434-441, 2016.

  • U. Patel and A.G. Ambekar, “Moment-based SL Identification for Indian Languages”, Proceedings of International Conference on Computing, Communication, Control and Automation, pp. 1-6, 2017.

  • S.T. Hassan, J.A. Abolarinwa and C.O. Alenoghena, “Intelligent SL Identification using Enhanced Fourier Descriptor: A Case of Hausa SL”, Proceedings of IEEE International Conference on Automatic Control and Intelligent Systems, pp. 104-109, 2017.

  • T. Liu, W. Zhou and H. Li, “SL Identification with Long Short-Term Memory”, Proceedings of IEEE International Conference on Image Processing, pp. 2871-2875, 2016.

  • M. Zadghorban and M. Nahvi, “An Algorithm on Sign Words Extraction and Identification of Continuous Persian SL based on Motion and Shape Features of Hands”, Pattern Analysis and Applications, Vol. 21, No. 2, pp. 323-335, 2018.

  • S.N. Sawant and M.S. Kumbhar, “Real-Time SL Identification using PCA”, Proceedings of IEEE International Conference on Advanced Communications, Control and Computing Technologies, pp. 1412-1415, 2014.

  • X. Li, C. Mao, S. Huang and Z. Ye, “Chinese SL Identification based on SHS Descriptor and EncoderDecoder LSTM Procedure”, Proceedings of Chinese Conference on Biometric Identification, pp. 719-728, 2017.

  • N.B. Ibrahim, M.M. Selim and H.H. Zayed, “An Automatic Arabic SL Identification System (ArSLRS)”, Journal of King Saud University-Computer and Information Sciences, Vol. 30, No. 4, pp. 470-477, 2018.

  • J. Zhang, W. Zhou and H. Li, “Chinese SL Identification with Adaptive HMM”, Proceedings of IEEE International Conference on Multimedia and Expo, pp. 1-6, 2016.

  • S. Hore, S. Chatterjee, V. Santhi and F. Shi, “Indian SL Identification using Optimized Neural Netstudys”, Proceedings of IEEE International Conference on Information Technology and Intelligent Transportation Systems, pp. 553-563, 2017.

  • A. Tharwat, T. Gaber and B. Refaat, “Sift-based Arabic SL Identification System”, Proceedings of Afro-European Conference for Industrial Advancement, pp. 359-370, 2015.

  • W. Yang, J. Tao and Z. Ye, “Continuous SL Identification using Level Building based on Fast Hidden Markov Procedure”, Pattern Identification Letters, Vol. 78, pp. 28-35, 2016.

  • H. Luqman and S.A. Mahmoud, “A Machine Translation System from Arabic SL to Arabic”, Universal Access in the Information Society, Vol. 19, No. 4, pp. 891-904, 2020.

  • S. Stoll, N.C. Camgoz and R. Bowden, “Text2Sign: Towards SL Production using Neural Machine Translation and Generative Adversarial Netstudys”, International Journal of Computer Vision, Vol. 128, No. 4, pp. 891-908, 2020.


Abstract Views: 132

PDF Views: 1




  • Analysis On Different Methods For Sign Language Identification

Abstract Views: 132  |  PDF Views: 1

Authors

M. Prema
Department of Computer Science, P.K.R. Arts College for Women, India
P.M. Gomathi
Department of Computer Science, P.K.R. Arts College for Women, India

Abstract


Sign language (SL) is the most organized and structured type of hand/arm gesture in the communicative hand/arm gesture taxonomies. The ability of machines to comprehend human actions and meanings has numerous uses. SL identification is one area of focus. SL is employed by the deaf and hard-of-hearing communities to communicate. Hearing-impaired persons communicate via visual indicators instead of vocal communication and sound patterns. SL also uses facial expressions and body postures as a medium of communication. Pattern matching, computer vision, natural language processing are the key factors in SL identification. This study reviews state-of-the-art methodologies employed in current SL identification research, comparing the various algorithms at each stage. Discuss the challenges and limitations of gesture identification research in general, as well as SL identification in particular. Overall, this paper gives a thorough introduction to the topic of automated SL identification, paving the way for future research.

Keywords


SL, Gesture Taxonomies, Deaf Community, Computer Vision, Pattern Matching, Natural Language Processing

References