System to assist visually impaired people in recognizing Real banknotes using the Artificial Neural Network technique

  • Fabrício Samuel Sausen UNISC
  • Rejane Frozza UNISC

Abstract


Visual impairment affects a large number of people in Brazil. According to the Demographic Census in 2010, by the Brazilian Institite of Geography and Statistics (IBGE), about 3,4% of the Brazilian population has visual impairment, that is, about 443 thousand people. Among all problems faced by them, we stand out the use of money, in which they are dependant on the help from known people to identify the banknotes. In this sense, this work seeks to develop a system to assist them in the recognition of the Real banknotes, through and application for smartphones, using Artificial Neural Networks techniques.

Keywords: Banknote Recognition, Artificial neural networks, Applied Computing

References

ARAÚJO, C. A. Bibliometria: evolução histórica e questões atuais. Em Questão, Porto Alegre, v. 12, n. 1, p. 11-32, 2006.

DOUSH, I. A.; AL-BTOUSH, S. Currency recognition using a smartphone: Comparison between color SIFT and gray scale SIFT algorithms. Journal of King Saud University – Computer and Information Sciences, Vol. 29, p. 494-492. 2017.

GOOGLE. Machine Learning Glossary, 2019. Disponível em: < https://developers.google.com/machine-learning/glossary >. Acesso em: outubro 2019.

HAYKIN, Simon. Neural networks: a comprehensive foundation. Upper Saddle River: Prentice Hall, v. 2, 1999. 842 p.

IBGE - Instituto Brasileiro de Geografia e Estatística. Nota técnica 01/2018. Releitura dos dados de pessoas com deficiência no Censo Demográfico 2010 à luz das recomendações do Grupo de Washington. 2018. Disponível em: < ftp://ftp.ibge.gov.br/Censos/Censo_Demografico_2010/metodologia/ notas_tecnicas/nota_tecnica_2018_01_censo2010.pdf >. Acessado em: outubro de 2019.

KORBUT, Daniil. Machine Learning Algorithms: Which One to Choose for Your Problem. 2017. Disponível em: < https://statsbot.co/blog/machine-learning-algorithms/ >. Acessado em: outubro de 2019.

MOMBACH, J. G.; WELFER, D. Proposta de um aplicativo móvel para percepção de imagens estáticas por alunos com deficiência visual. Brazilian Symposium on Computers in Education (Simpósio Brasileiro de Informática na Educação-SBIE). Vol. 24. No. 1. 2013.

PILA, Adriano Donizete. Seleção de atributos relevantes para aprendizado de máquina utilizando a abordagem de Rough Sets. 2001. Tese de Doutorado. Universidade de São Paulo.

REZENDE, Solange Oliveira. Sistemas Inteligentes – Fundamentos e Aplicações. São Paulo: Manole, 2003.

SARFRAZ, Muhammad. An intelligent paper currency recognition system. Procedia Computer Science. Vol. 65. 2015. p. 538-545.

SINHA, Rajat Kumar; PANDEY, Ruchi; PATTNAIK, Rohan. Deep learning for computer vision tasks: A review, 2018.
Published
2020-11-04
SAUSEN, Fabrício Samuel; FROZZA, Rejane. System to assist visually impaired people in recognizing Real banknotes using the Artificial Neural Network technique. In: REGIONAL SCHOOL ON COMPUTING OF RIO GRANDE DO SUL (ERCOMP-RS), 1. , 2020, Evento Online. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2020 . p. 62-67. DOI: https://doi.org/10.5753/ercomprs.2020.14297.