Abstract
Sign language is a natural language mostly used by persons with hearing- and speech-based impairments to communicate with other people. In these modern times, sign language guides are used to eliminate the communication gap between people having hearing impairments and those with or without hearing impairments; however, they are very limited in number. To solve this challenge, automatic sign language recognition systems are developed to better reduce the communication gap for people with hearing disabilities. This paper presents the development of an automatic Amharic sign language translator which translates Amharic alphabet signs into their corresponding text using digital image processing and machine learning algorithms. The proposed system has four major developmental stages which include preprocessing, segmentation, feature extraction and classification. A total number of thirty-four features were extracted from shape, motion and color of hand gestures to represent both the base and derived class of Amharic sign characters. Classification models were built using artificial neural network (ANN) and multi-class support vector machine (SVM). The results show that the recognition system is capable of recognizing the Amharic alphabet signs with an average accuracy of 80.82% and 98.06% using the ANN and SVM classifiers, respectively.
Similar content being viewed by others
Data availability
The authors declare that all data presented in this work was generated during the course of the work and any other source has been appropriately reference within the manuscript.
References
Choudhury, N.N., Kayas, G.: Automatic recognition of Bangla sign language. Bachelor's Project, Department of Computer Science and Engineering, BRAC University, Knoxville—USA (2012)
Belay, B., Habtegebrial, T., Meshesha, M., Liwicki, M., Belay, G., Stricker, D.: Amharic OCR: an end-to-end learning. Appl. Sci. 10(3), 1–13 (2020). https://doi.org/10.3390/app10031117
Ethiopian National Association for Deaf. BERTAT, Yearly Magazine, Ethiopia (1997)
Kumar, B.P.P., Manjunatha, M.B.: Performance analysis of KNN, SVM and ANN techniques for gesture recognition system. Indian J. Sci. Technol. 9(1), 1–8 (2016). https://doi.org/10.17485/ijst/2017/v9iS1/111145
Ekbote, J., Joshi, M.: Indian sign language recognition using ANN and SVM classifiers. In: International Conference on Innovations in Information, Embedded and Communication Systems (ICIIECS) (2017). https://doi.org/10.1109/iciiecs.2017.8276111
Chen, Y., Zhang, W.: Research and implementation of sign language recognition method based on Kinect. In: 2nd IEEE International Conference on Computer and Communications (ICCC) (2016). https://doi.org/10.1109/compcomm.2016.7925041
Nagarajan, S., Subashini, T.S., Balasubramanian, M.: Visual interpretation of ASL finger spelling using hough transform and support vector machine. Int. J. Adv. Res. Comput. Commun. Eng. 4(6), 28–39 (2015)
Tavari, V., Deorankar, I.: Implementation of neural network based hand gesture recognition system. Int. J. Eng. Comput. Sci. 3(6), 364–386 (2014)
Quan, Y., Jinye, P.: Chinese sign language recognition for a vision-based multi-features classifier. In: International Symposium on Computer Science and Computational Technology, Shaanxi Xi‟an, China (2008). https://doi.org/10.1109/ISCSCT.2008.374
Admasu, Y.F., Raimond, K.: Ethiopian sign language recognition using Artificial Neural Network. In: 10th IEEE International Conference on Intelligent Systems Design and Applications, pp. 995–1000 (2010). https://doi.org/10.1109/isda.2010.5687057
Gimbi, T.: Recognition of isolated signs in Ethiopian sign language. Master's thesis, Addis Ababa University (2014)
Tesfaye, M.: Machine translation approach to translate Amharic text to Ethiopian sign language. In: 2nd Proceedings of IEEE International Conference, pp. 252–273 (2010)
Zerubabel, L.: Ethiopian finger spelling classification: a study to automate Ethiopian sign language. Master's thesis, Addis Ababa University, Addis Ababa, Ethiopia (2008)
Tsegaye, A.: Offline candidate hand gesture selection and trajectory determination for continuous Ethiopian sign language. Master's thesis, Addis Ababa University, Addis Ababa, Ethiopia (2011)
Pugeault, N., Bowden, R.: Spelling it out: real-time ASL fingerspelling recognition. In: IEEE Work-Shop on Consumer Depth Cameras for Computer Vision, Barcelona, Spain (2011)
Ricco, S., Tomasi, C.: Finger spelling recognition through classification of letter-to-letter transitions. Proc. ACC 3, 214–225 (2010)
Singha, J.: Indian sign language recognition using Eigen value weighted Euclidean distance based classification technique 4(2) (2013)
Salau, A.O., Jain, S.: Feature extraction: a survey of the types, techniques, and applications. In: 5th IEEE International Conference on Signal Processing and Communication (ICSC), Noida, India, pp. 158–164 (2019). https://doi.org/10.1109/ICSC45622.2019.8938371
Chimdi, W.: Ethiopian sign language and educational accessibility for the deaf community: a case study on Jimma, Nekemte, Addis Ababa and Hawasa towns. J. Lang. Cult. 6(2), 9–17 (2015). https://doi.org/10.5897/jlc2014.0298
Rupe, J.: Vision-based hand shape identification for sign language recognition. Master's thesis, Rochester Institute of Technology (2005)
Hammouda, G., Sellami, D., Hammouda, A.: Pattern recognition based on compound complex shape-invariant Radon transform. Vis. Comput. 36, 279–290 (2020). https://doi.org/10.1007/s00371-018-1604-9
Sharma, S., Saxena, V.P., Satish, K.: Comparative analysis on sign language recognition system. Int. J. Sci. Technol. Res. 8(8), 981–990 (2019)
Yusnita, L., Hadisukmana, N., Wahyu, R. B., Roestam, R., Wahyu, Y.: Implementation of real-time static hand gesture recognition using artificial neural network. In: 4th International Conference on Computer Applications and Information Processing Technology (CAIPT) (2017). https://doi.org/10.1109/caipt.2017.8320692
Funding
The authors declare no funding for this research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interest of any sort on this research.
Ethical approval
Authors affirm that the submitted material is ours and original.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Tamiru, N.K., Tekeba, M. & Salau, A.O. Recognition of Amharic sign language with Amharic alphabet signs using ANN and SVM. Vis Comput 38, 1703–1718 (2022). https://doi.org/10.1007/s00371-021-02099-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-021-02099-1