Computational Model for Sign Language Recognition in a Colombian Context

Keywords: Deaf people, Machine Learning, computational model, sign language

Abstract

This document presents the implementation of a Colombian sign language recognition software for deaf people. For this purpose, Machine Learning will be used as the basis of the specific system. Today there is no public repository of images or video that contains these signs or the information necessary to achieve this goal, being one of the main obstacles to undertake the task. For this reason, the construction of a repository was started. Despite the time constraints of the participants, five people carried out the signs in front of a video camera, from which the images that would make up the repository were obtained.Once this was done, the images were used as training data for an optimal computer model that can predict the meaning of a new image presented. We evaluated the performance of the method using classification measures and comparing different models. The measurement known as Accuracy was an important factor in measuring the different models obtained and thus choosing the one most suitable. Results show that it is possible to provide new tools to deaf people to improve communication with others who do not know sign language. Once the best models have been chosen, they are tested with new images, similar to those in the training, where it can be seen that the best model achieves a success rate of around 68 % of the 22 classes used in the system.

Author Biographies

Nelson Ortiz-Farfán, Universidad Nacional de Colombia, Colombia

MSc en Ingeniería de Sistemas y Computación, Departamento de Ingeniería de Sistemas e Industrial, Universidad Nacional de Colombia, Bogotá-Colombia, nmortizf@unal.edu.co

Jorge E. Camargo-Mendoza*, Universidad Nacional de Colombia, Colombia

PhD. en Ingeniería de Sistemas y Computación, Departamento de Ingeniería de Sistemas e Industrial, Universidad Nacional de Colombia, Bogotá-Colombia, jecamargom@unal.edu.co

References

L. M. Rojas-Rojas, N. Arboleda-Toro, y L. J. Pinzón-Jaime, “Caracterización de población con discapacidad visual, auditiva, de habla y motora para su vinculación a programas de pregrado a distancia de una universidad de Colombia”, Rev. Electrónica Educ., vol. 22, no. 1, pp. 1-28, Jan. 2018. https://doi.org/10.15359/ree.22-1.6

Y. M. Cortés Bello, A. G. Barreto Muñoz, “Variación sociolingüística en la lengua de señas colombiana: observaciones sobre el vocabulario deportivo, en el marco de la planificación lingüística” Forma y Función, vol. 26, no. 2 pp. 149-170. Disponible en: http://www.scielo.org.co/pdf/fyf/v26n2/v26n2a07.pdf

Centro de relevo Colombia, Ministerio de Tecnologías de la Información y las Comunicaciones “Servicio de Interpretación en línea SIEL” (s/f). Disponible en: https://centroderelevo.gov.co/632/w3-propertyvalue-15254.html

Centro de relevo Colombia, “Instructivo para la implementación de los servicios de centro de relevo,” (s/f) Google Docs. [En línea]. Disponible en: https://drive.google.com/file/d/1swrQp_skuDd_fBbVHI0Vu7EWwp4C9UZp/view

H. Ziady, CNN Business “Google's AI system can beat doctors at detecting breast cancer,” Jan. 2020. Accedido: 07-mar-2020. Disponible en: https://edition.cnn.com/2020/01/02/tech/google-health-breast-cancer/index.html

G. Eryiğit, et al. “Building the first comprehensive machine-readable Turkish sign language resource: methods, challenges and solutions”, Lang Resources & Evaluation. Vol. 54. pp. 97–121, Apr. 2019. http://doi.org/10.1007/s10579-019-09465-5

R.E.O. Costa, et al. “Towards an open platform for machine translation of spoken languages into sign languages”. Machine Translation, vol. 33, pp. 315–348, Aug. 2019. https://doi.org/10.1007/s10590-019-09238-5

V. Kumar Vivek, y S. Srivastava, “Toward Machine Translation Linguistic Issues of Indian Sign Language”. En: Agrawal S., Devi A., Wason R., Bansal P. (eds) Speech and Language Processing for Human-Machine Communications. Advances in Intelligent Systems and Computing, vol. 664. Springer, Singapore. https://doi.org/10.1007/978-981-10-6626-9_14

L. Quesada, G. López, y L. Guerrero, “Automatic recognition of the American sign language fingerspelling alphabet to assist people living with speech or hearing impairments”, J. Ambient Intell. Humaniz. Comput., vol. 8, no. 4, pp. 625-635, Mar. 2017. https://doi.org/10.1007/s12652-017-0475-7

J. L. Raheja, A. Mishra, y A. Chaudhary, «Indian sign language recognition using SVM», Pattern Recognit. Image Anal., vol. 26, no. 2, pp. 434-441, Jun. 2016.https://doi.org/10.1134/S1054661816020164

D. C. García Cortes, “Reconocimiento de Gestos de Manos como Mecanismo de Interacción Humano – Computador” (Tesis de Maestría), Facultad de Ingeniería, Universidad Nacional de Colombia, 2014. Disponible en: http://bdigital.unal.edu.co/46239/1/300497.2014.pdf

P. Nakjai y T. Katanyukul, “Hand Sign Recognition for Thai Finger Spelling: An Application of Convolution Neural Network”, J. Signal Process. Syst., vol. 91, no. 2, pp. 131-146, Apr. 2018. https://doi.org/10.1007/s11265-018-1375-6

F. Ronchetti, “Reconocimiento de gestos dinámicos y su aplicación al lenguaje de señas”, (Tesis Doctoral), Facultad de Informática, Universidad Nacional de la Plata, Argentina, 2017. Disponible en: http://sedici.unlp.edu.ar/handle/10915/59330

O. Koller, H. Ney and R. Bowden, "Deep Hand: How to Train a CNN on 1 Million Hand Images When Your Data is Continuous and Weakly Labelled," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016, pp. 3793-3802. http://dx.doi.org/10.1109/CVPR.2016.412

M. Mustafa. “A Study on Arabic Sign Language Recognition for Differently Abled Using Advanced Machine Learning Classifiers”. Journal of Ambient Intelligence and Humanized Computing, Mar. 2020. https://doi.org/10.1007/s12652-020-01790-w

S. K. Mishra, S. Sinha, S. Sinha, y S. Bilgaiyan, “Recognition of Hand Gestures and Conversion of Voice for Betterment of Deaf and Mute People,” en International Conference on Advances in Computing and Data Sciences, Singapure, 2019, pp. 46–57. https://doi.org/10.1007/978-981-13-9942-8_5

P. M. Ferreira, J. S. Cardoso, y A. Rebelo, “On the role of multimodal learning in the recognition of sign language,” Multimed. Tools Appl., vol. 78, no. 8, pp. 10035–10056, Sep. 2018. https://doi.org/10.1007/s11042-018-6565-5

Md. Sanzidul Islam, S. S. Sharmin Mousumi, AKM. S. Azad Rabby, y S. Akhter Hossain. “A Simple and Mighty Arrowhead Detection Technique of Bangla Sign Language Characters with CNN”. En Recent Trends in Image Processing and Pattern Recognition, Singapore, 2019. https://doi.org/10.1007/978-981-13-9181-1_38

Kaggle Inc “Sign Language MNIST Drop-In Replacement for MNIST for Hand Gesture Recognition Tasks version 1”, 2019. Accedido: 15-abr-2019.Disponible en: https://www.kaggle.com/datamunge/sign-language-mnist

Instituto Nacional para sordos, Insor educativo “Léxico de uso cotidiano” Accedido: 20-oct-2019. Disponible en: http://educativo.insor.gov.co/diccionario/diccionario-cotidiano/

J. Brownlee “A Gentle Introduction to k-fold Cross-Validation” Machine Learning Mastery Pty, 2018. Accedido: 19-sep-2019. Disponible en: https://machinelearningmastery.com/k-fold-cross-validation/

A. Schelstraete, “4 Principios para validar cualquier prototipo,” Medium, Accedido: 11-Abr-2019. Disponible en: https://medium.com/@ashera/4-principios-para-validar-cualquier-prototipo-b3329ef7ab32

M. Timney, “Building Better Products through Prototype Validation”, InVisionApp Inc. 2015. Disponible en: https://www.invisionapp.com/inside-design/building-better-products-through-prototype-validation/

How to Cite
Ortiz-Farfán, N., & Camargo-Mendoza, J. E. (2020). Computational Model for Sign Language Recognition in a Colombian Context. TecnoLógicas, 23(48), 197-232. https://doi.org/10.22430/22565337.1585

Downloads

Download data is not yet available.
Published
2020-05-15
Section
Research Papers