Improving Independence in Money Recognition for Blind Brazilians
Abstract
This paper aims to propose of an assistive technology taking advantage of using the traditional technique Template Matching combined with color recognition in the domain of HSV color space through of the development of a mobile application to recognition Brazilian banknotes provided by the segmentation of security items named Puzzles that belong to the Second Series of Real. The predominant hue, as the Puzzles, is another one of a several security items of the Second Series of Real and it is possible to classify both verses of the seven types of Brazilian banknotes using this feature. Template Matching is used to turn viable the predictions by the predominant hue extracted from homogeneous, standardized and unique location and at the same time the predominant hue is used to confirm predictions of the Template Matching. Both techniques are available in the OpenCV library which allows the viability of a prospectus to build a smartphone application which can promote the improving independence of visual impaired people in their monetary exchanges dealing with the Second Series of Real banknotes.
Keywords:
Accessibility, Assistive Technology, Brazilian Banknotes, Second Series of Real, Puzzle, Template Matching, HSV Space Color
References
E. Azevedo, A. Conci, and C. Vasconcelos. 2022. Computação gráfica: teoria e prática-geração de imagens. Alta Books.
BRASIL BACEN. 2020. Segunda Família do Real. Retrieved 04/05/2024 from [link]
BRASIL. 1941. Decreto-Lei 3688 de 3 de outubro de 1941. Retrieved 04/05/2024 from [link]
BRASIL. 1964. Lei 4595 de 31 de dezembro de 1964. Retrieved 04/05/2024 from [link]
L. E. R. Duarte. 2019. Reconhecimento de cédulas real usando algoritmo surf (speeded-up robust features). Master’s thesis. Universidade Federal de Uberlândia.
L. Dunai Dunai, M. C. Perez, G Peris-Fajarnés, and I. Lengua Lengua. 2017. Euro banknote recognition system for blind people. Sensors 17, 1 (2017), 184.
Q. Faisal. 2023. Template Matching - Lesson 06. Retrieved 05/06/2023 from [link]
R. Ferrero and B. Montrucchio. 2024. Banknote Identification Through Unique Fluorescent Properties. IEEE Transactions on Dependable and Secure Computing 21, 2 (2024), 975–986. DOI: 10.1109/TDSC.2023.3267166
J. A. M. Freitas. 2021. ANÁLISE VISUAL DO REAL. B.S. thesis. Instituto Federal de Educação, Ciência e Tecnologia - Campus Cabedelo.
R. C. Gonzalez and R. E. Woods. 2018. Digital image processing. Pearson.
L. Lang, N. F. Gazcón, and M. L. Larrea. 2018. An open source solution for money bill recognition for the visually impaired user using smartphones. In XXIV Congreso Argentino de Ciencias de la Computación (La Plata, 2018).
J. W. Lee, H. G. Hong, K. W. Kim, and K. R. Park. 2017. A survey on banknote recognition methods by various sensors. Sensors 17, 2 (2017), 313.
OpenCV. 2015. Open Source Computer Vision Library.
D. G. Pérez and E. B. Corrochano. 2018. Recognition system for Euro and Mexican banknotes based on deep learning with real scene images. Computación y Sistemas 22, 4 (2018), 1065–1076.
R. J. Radke. 2015. Intro to Digital Image Processing, class videos from Rensselaer Polytechnic Institute. DIP Lecture 14: Object and feature detection. Retrieved 05/06/2024 from [link]
M. Sarfraz. 2015. An Intelligent Paper Currency Recognition System. Procedia Computer Science 65 (2015), 538–545. DOI: 10.1016/j.procs.2015.09.128 International Conference on Communications, management, and Information technology (ICCMIT’2015).
P. Swaroop and N. Sharma. 2016. An overview of various template matching methodologies in image processing. International Journal of Computer Applications 153, 10 (2016), 8–14.
C. T. S. Tatum. 2015. Contrafação monetária de cédulas brasileiras. Master’s thesis. Universidade Federal do Sergipe.
R. S. Tavares. 2024. Viabilidade do Uso de Técnicas Tradicionais de Análise de Imagens na Caracterização do Valor de Cédulas de Real. Master’s thesis. Universidade Federal Fluminense.
R. S. Tavares, A. Conci, and A. Gonçalves. 2024. On the Possibilities of Using Traditional Pattern Recognition Techniques in Brazilian Banknote Characterization. In 2024 31st International Conference on Systems, Signals and Image Processing (IWSSIP). 1–8. DOI: 10.1109/IWSSIP62407.2024.10634019
Wikipedia. 2017. Lista de cores pelo nome. Retrieved 05/06/2024 from [link]
BRASIL BACEN. 2020. Segunda Família do Real. Retrieved 04/05/2024 from [link]
BRASIL. 1941. Decreto-Lei 3688 de 3 de outubro de 1941. Retrieved 04/05/2024 from [link]
BRASIL. 1964. Lei 4595 de 31 de dezembro de 1964. Retrieved 04/05/2024 from [link]
L. E. R. Duarte. 2019. Reconhecimento de cédulas real usando algoritmo surf (speeded-up robust features). Master’s thesis. Universidade Federal de Uberlândia.
L. Dunai Dunai, M. C. Perez, G Peris-Fajarnés, and I. Lengua Lengua. 2017. Euro banknote recognition system for blind people. Sensors 17, 1 (2017), 184.
Q. Faisal. 2023. Template Matching - Lesson 06. Retrieved 05/06/2023 from [link]
R. Ferrero and B. Montrucchio. 2024. Banknote Identification Through Unique Fluorescent Properties. IEEE Transactions on Dependable and Secure Computing 21, 2 (2024), 975–986. DOI: 10.1109/TDSC.2023.3267166
J. A. M. Freitas. 2021. ANÁLISE VISUAL DO REAL. B.S. thesis. Instituto Federal de Educação, Ciência e Tecnologia - Campus Cabedelo.
R. C. Gonzalez and R. E. Woods. 2018. Digital image processing. Pearson.
L. Lang, N. F. Gazcón, and M. L. Larrea. 2018. An open source solution for money bill recognition for the visually impaired user using smartphones. In XXIV Congreso Argentino de Ciencias de la Computación (La Plata, 2018).
J. W. Lee, H. G. Hong, K. W. Kim, and K. R. Park. 2017. A survey on banknote recognition methods by various sensors. Sensors 17, 2 (2017), 313.
OpenCV. 2015. Open Source Computer Vision Library.
D. G. Pérez and E. B. Corrochano. 2018. Recognition system for Euro and Mexican banknotes based on deep learning with real scene images. Computación y Sistemas 22, 4 (2018), 1065–1076.
R. J. Radke. 2015. Intro to Digital Image Processing, class videos from Rensselaer Polytechnic Institute. DIP Lecture 14: Object and feature detection. Retrieved 05/06/2024 from [link]
M. Sarfraz. 2015. An Intelligent Paper Currency Recognition System. Procedia Computer Science 65 (2015), 538–545. DOI: 10.1016/j.procs.2015.09.128 International Conference on Communications, management, and Information technology (ICCMIT’2015).
P. Swaroop and N. Sharma. 2016. An overview of various template matching methodologies in image processing. International Journal of Computer Applications 153, 10 (2016), 8–14.
C. T. S. Tatum. 2015. Contrafação monetária de cédulas brasileiras. Master’s thesis. Universidade Federal do Sergipe.
R. S. Tavares. 2024. Viabilidade do Uso de Técnicas Tradicionais de Análise de Imagens na Caracterização do Valor de Cédulas de Real. Master’s thesis. Universidade Federal Fluminense.
R. S. Tavares, A. Conci, and A. Gonçalves. 2024. On the Possibilities of Using Traditional Pattern Recognition Techniques in Brazilian Banknote Characterization. In 2024 31st International Conference on Systems, Signals and Image Processing (IWSSIP). 1–8. DOI: 10.1109/IWSSIP62407.2024.10634019
Wikipedia. 2017. Lista de cores pelo nome. Retrieved 05/06/2024 from [link]
Published
2025-06-03
How to Cite
TAVARES, Ronaldo da Silva; CONCI, Aura.
Improving Independence in Money Recognition for Blind Brazilians. In: ACM INTERNATIONAL CONFERENCE ON INTERACTIVE MEDIA EXPERIENCES WORKSHOPS (IMXW), 25. , 2025, Niterói/RJ.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 81-86.
DOI: https://doi.org/10.5753/imxw.2025.7114.
