Towards the construction of a device to support blind people in the “cuarenta” game

  • Holger Ortega Universidad Politécnica Salesiana
  • Rodrigo Tufiño Universidad Politécnica Salesiana
  • Juan Estévez Universidad Politécnica Salesiana
Keywords: automatic recognition, artificial vision, k-nearest neighbors, playing cards, inclusion

Abstract

The present work has the objective of developing a system for the automatic recognition of a playing card on a table, as part of a more general project to create a device to assist the blind in the chance game called “cuarenta”. The aim of this device will be to inform the user about the cards being played, via audio. For this phase of the project the algorithm used was k-NN, trained with a set of alphanumeric synthetic characters. The test set contained photographs taken in controlled lighting conditions, with the card positioned in arbitrary orientations. The parameterization of the algorithm gave a value of 1 as the optimal k, with which a classification error of 5% was obtained in the test set. Only two characters were confused by the classifier, the “A” and the “J”, with 20% and 40% errors each one. The algorithm was implemented in an embedded Raspberry Pi 3 system, obtaining a response time of 5 seconds, including the conversion to audio, and a memory occupation no greater than 60% of the total capacity of the system. These results suggest its applicability in portable devices.

Downloads

Download data is not yet available.

References

Bradski, G., & Kaehler, A. (2008). Learning OpenCV. O'Reilly Media.
Galindo Durán, C. K., Juganaru-Mathieu, M., Áviles Cruz, C., & Vázquez, H. (2010). Desarrollo de una aplicación destinada a la clasificación de información textual y su evaluación por simulación. Administración y Organizaciones, 119-131.
Gutiérrez, P. D., Lastra, M., Bacardit, J., Benítez, J. M., & Herrera, F. (2016). GPU-SME-kNN: Scalable and memory efficient kNN and lazy learning using GPUs. Information Sciences, 165-182.
Hayward, D. (14 de marzo de 2014). CNET. Obtenido de 25 fun things to do with a Raspberry Pi: https://www.cnet.com/how-to/25-fun-things-to-do-with-a-raspberry-pi/
Larcher, L. I., Biasoni , E. M., & Cattaneo, C. A. (2011). ALGORITMO PARA DETECCIÓN DE BORDES Y ULTERIOR. Mecánica Computacional, Asociación Argentina de Mecánica Computacional, 2841-2852.
LeCun, Y., Cortes, C., & Burges, C. (s.f.). THE MNIST DATABASE. Recuperado el 06 de enero de 2017, de MNIST handwritten digit database: http://yann.lecun.com/exdb/mnist/
Lojo, D., Losada, D. E., & Barreiro, Á. (2009). CIE-9-MC Code Classification with knn and SVM. En Bioinspired Applications in Artificial and Natural Computation (págs. 499-508). Santiago de Compostela, España: Springer Berlin Heidelberg. doi:10.1007/978-3-642-02267-8_53
López, G. (2010). CENSO DE POBLACIÓN Y VIVIENDA (CPV-2010). Instituto Nacional de Estadísticas y Censos (INEC), Unidad de procesamiento - Dirección de estudios analíticos estadísticos.
Monk, S. (2016). Raspberry Pi Cookbook. O'Reilly Media.
OpenCV Organization. (2014). Geometric Image Transformations. Recuperado el 06 de enero de 2017, de OpenCV 2.4.13.2 documentation: http://docs.opencv.org/2.4/modules/imgproc/doc/geometric_transformations.html
Raikwal, J., & Saxena, K. (2012). Performance Evaluation of SVM and K-Nearest Neighbor Algorithm over Medical Data set. International Journal of Computer Applications (0975 – 8887), 50(14).
Raspberry Pi Foundation. (2016). Raspberry Pi. Recuperado el 06 de enero de 2017, de Raspberry Pi - Teach, Learn, and Make with Raspberry Pi: https://www.raspberrypi.org/
Secretaría del Buen Vivir. (2017). El Sumak Kawsay. (Secretaría del Buen Vivir - Gobierno Nacional de la Republica del Ecuador) Recuperado el 06 de enero de 2017, de Secretaría Buen Vivir | Ecuador: http://www.secretariabuenvivir.gob.ec/el-sumak-kawsay/
Sudha, L., & Bhavani, R. (2012). Performance Comparison of SVM and kNN in Automatic Classification of Human Gait Patterns. INTERNATIONAL JOURNAL OF COMPUTERS, 6.
Suzuki, S., & Abe, k. (1985). Topological Structural Analysis of Digitized Binary Images by Border Following. CVGIP, 30(1), 32-46.
Szeliski, R. (211). Computer Vision Algorithms and Applications. London: Springer-Verlag. doi:10.1007/978-1-84882-935-0
Taylor, A. (2015). Getting Started. Recuperado el 06 de enero de 2017, de python-for-android 0.1 documentation: https://python-for-android.readthedocs.io/en/latest/quickstart/
Tello, S. (2 de julio de 2014). Los no videntes cuentan con más dispositivos para desenvolverse. (Grupo El Comercio) Recuperado el 06 de enero de 2017, de El Comercio: http://www.elcomercio.com/tendencias/no-videntes-cuentan-mas-dispositivos-desenvolverse.html
Wikipedia. (28 de diciembre de 2016). Wikipedia La enciclopedia libre. Recuperado el 06 de enero de 2017, de Cuarenta (juego): https://es.wikipedia.org/wiki/Cuarenta_(juego)
Zapata, A., Pérez, S., & Mora, J. (2014). Método basado en clasificadores k-NN parametrizados con algoritmos genéticos y la estimación de la reactancia para localización de fallas en sistemas de distribución. Rev. Fac. Ing. Univ. Antioquia, 220-232.
Published
2017-09-29
How to Cite
Ortega, H., Tufiño, R., & Estévez, J. (2017). Towards the construction of a device to support blind people in the “cuarenta” game. Enfoque UTE, 8(4), pp. 27 - 40. https://doi.org/https://doi.org/10.29019/enfoqueute.v8n4.170
Section
General Engineering