Banknote Identification Methodology for Visually Impaired People
Resumo
Around the world, there are many people with disabilities; it is estimated that 39 million people are blind and 246 million have limited vision, giving a total of 285 million visually impaired people. The use of information and communication technologies can help disabled people to achieve greater independence, quality of life and inclusion in social activities by increasing, maintaining or improving their functional capacities. In this context, this paper presents an automatic methodology for identifying banknotes that can be widely used by people with visual impairment. For this, we evaluated a set of four point-of-interest detectors, two descriptors, seven ways of generating the image signature, and six classification methodologies, which can be used as a basis for the development of applications for the identification of banknotes. Experiments performed on US Dollar (USD), Euro (EUR) and Brazilian Real Banknotes (BRL) obtained rates of accuracy of 99.78%, 99.12%, and 96.92%, respectively.Referências
D. Pascolini and S. P. Mariotti, "Global estimares of visual impairment: 2010;· B./0, pp. 614-618, 2011.
F. Grij al va, J. Rodriguez, J. Larco, and L. Orozco, "Smartphone reco g nition of the us banknotes' denomination, for vis ually impaired people," in IEEE ANDESCON, 2010, pp. 1-6.
F. M. Hasanuzzaman, X. Yang, and Y. Tian, "Robus t and effective component-based banknote recognition for the blind ," lt:liH TSMC*, vol. 42, no. 6, pp. 1021-1030, 2012.
H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, "Speeded-up robust features (surf)," CV IU , vol. 110, no. 3, pp. 346- 359, Jun. 2008.
D. Mulmule-Shirkhedkar and A. Dani, "Comparative study of surf and freak descriptor on indian rupee currency notes," in IEEE /CIP, 2015, pp. 784-789.
A. Alahi, R. Ortiz, and P. Vandergheynst, "Freak: Fast retina keypoint," in JF,P,P, CVPR, June 2012, pp. 510-517.
C. M. Costa, G. Veiga, and A. Sousa, "Recognition of banknotes in multiple perspectives using selec tive feature rnatching and shape analysis," in IEEE IC A RSC , May 2016, pp. 235-240.
M. Muja and D. G. Lowe, "Fast approximate nearest neighbors with automatic algorithrn configuration," in VISAPP, 2009, pp. 331-340.
E. N. Mortensen , H . Deng , and L. Shapiro, "A sift descriptor with global context," in JEEE CVPR, vol. 1 , June 2005, pp. 184-190 vol. 1.
V. ABBURU, S. GUPTA, S. R. RIMITHA, M. MULIMANI, and S. G. KOOLAGUDI, "Currency recogni tion system using image processing," in 2017 Tenth fn lernalional Co11ference on Contemporary Compltling (/C3), Aug 2017, pp. 1- 6.
S. Mittal and S. Mitral, "Indian banknote recognition using convolutional neural network," in 2018 3rd l111erna1i onal C01(ference On Internet qf Things: Smar/ lnnovalion and Usages (foT-SIU). IEEE, 2018, pp. 1-6.
S. Lawrence, C. L. Giles, A. C. Tsoi, and A. D. Back, "Face recogni tion: A convolutional ne ural-network approach," ! EEE transactions on neural networks , vol. 8, no. 1, pp. 98-113, 1997.
J. Sivic and A. Zisserman, "Video google: A text retrieval approach to object matching in vídeos," in IEEE ICC V , 2003, p. 1470.
J. Matas, O. Churn, M. Urb an, and T. Pajdla, "Robust wide-baseline stereo from ma ximally stable extremai regions ," fmage Vision Compul., vol. 22, no. 10, pp. 761-767, 2004.
E. Rosten and T. Drummond, "Mac hin e learning for high speed comer detection," in ECCV. Springer, 2006, pp. 430-443.
S. Leutenegger, M. Chli, and R. Y. Siegwart, "Bris k: Binary robust invariant scalable keyp oin ts," in IEEE IC C V, 201 l , pp. 2548-2555.
M. Musavi, W. Ahmed, K. Chan, K. Faris, and D. Hummels , "On the training of radial basis function classifiers," Neural Netw., vol. 5, no. 4, pp. 595 - 603, 1992.
F. T. Liu , K. M. Tin g, Y. Yu, and Z.-H. Zhou, "Spectrum of variable randorn trees," JAIR, vol. 32, pp. 355-384, 2008.
H. Yan, Y. J iang, J. Zheng, C. Peng, and Q. Li, "A multilayer perceptron based medical decision support system for heart disease diagnosis," Expert Sysl. Appl., vol. 30, no. 2, pp. 272 - 281, 2006.
J. Suykens and J. Vandewalle, "Least squares support vec tor machine classifiers," Neural Process. Leu., vol. 9, no. 3, pp. 293-300, Jun 1999.
J. C. Platt, "12 fast trainiog of support vector rnachines usiog sequential minimal optimization," Advances in kernel methods, pp. 185- 208, 1999.
L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5- 32, Oct 2001.
M. Story and R. G. Cong alton, "Accuracy assessment: a user's perspec tive," PE&RS, vol. 52, no. 3, pp. 397-399, 1986.
H. Honest and K. S. Khan, "Reportin g of measures of accuracy in systematic reviews of diagnostic lite rature ," RMC Health Serv. Res., vol. 2, no. 1, p. 4, Mar 2002.
B. Chimieski and R. Fagundes, "Associatio n and classification data mining algorithms comparicion over medical datasets," .IH!, pp. 44- 51, 2013.
J. R. Landis aod G. G. Koch, "The measurement of observer agreement for categorical data," Biometri cs , vol. 33, no. 1, pp. 159- 174, 1977.
R. G. Congalton and K. Green, Assessing the Accuracy of Remotely Sensed V ata : Principi es and Praclices, 2nd ed. Boca Raton: CRC Press, 12 2008.
F. Grij al va, J. Rodriguez, J. Larco, and L. Orozco, "Smartphone reco g nition of the us banknotes' denomination, for vis ually impaired people," in IEEE ANDESCON, 2010, pp. 1-6.
F. M. Hasanuzzaman, X. Yang, and Y. Tian, "Robus t and effective component-based banknote recognition for the blind ," lt:liH TSMC*, vol. 42, no. 6, pp. 1021-1030, 2012.
H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool, "Speeded-up robust features (surf)," CV IU , vol. 110, no. 3, pp. 346- 359, Jun. 2008.
D. Mulmule-Shirkhedkar and A. Dani, "Comparative study of surf and freak descriptor on indian rupee currency notes," in IEEE /CIP, 2015, pp. 784-789.
A. Alahi, R. Ortiz, and P. Vandergheynst, "Freak: Fast retina keypoint," in JF,P,P, CVPR, June 2012, pp. 510-517.
C. M. Costa, G. Veiga, and A. Sousa, "Recognition of banknotes in multiple perspectives using selec tive feature rnatching and shape analysis," in IEEE IC A RSC , May 2016, pp. 235-240.
M. Muja and D. G. Lowe, "Fast approximate nearest neighbors with automatic algorithrn configuration," in VISAPP, 2009, pp. 331-340.
E. N. Mortensen , H . Deng , and L. Shapiro, "A sift descriptor with global context," in JEEE CVPR, vol. 1 , June 2005, pp. 184-190 vol. 1.
V. ABBURU, S. GUPTA, S. R. RIMITHA, M. MULIMANI, and S. G. KOOLAGUDI, "Currency recogni tion system using image processing," in 2017 Tenth fn lernalional Co11ference on Contemporary Compltling (/C3), Aug 2017, pp. 1- 6.
S. Mittal and S. Mitral, "Indian banknote recognition using convolutional neural network," in 2018 3rd l111erna1i onal C01(ference On Internet qf Things: Smar/ lnnovalion and Usages (foT-SIU). IEEE, 2018, pp. 1-6.
S. Lawrence, C. L. Giles, A. C. Tsoi, and A. D. Back, "Face recogni tion: A convolutional ne ural-network approach," ! EEE transactions on neural networks , vol. 8, no. 1, pp. 98-113, 1997.
J. Sivic and A. Zisserman, "Video google: A text retrieval approach to object matching in vídeos," in IEEE ICC V , 2003, p. 1470.
J. Matas, O. Churn, M. Urb an, and T. Pajdla, "Robust wide-baseline stereo from ma ximally stable extremai regions ," fmage Vision Compul., vol. 22, no. 10, pp. 761-767, 2004.
E. Rosten and T. Drummond, "Mac hin e learning for high speed comer detection," in ECCV. Springer, 2006, pp. 430-443.
S. Leutenegger, M. Chli, and R. Y. Siegwart, "Bris k: Binary robust invariant scalable keyp oin ts," in IEEE IC C V, 201 l , pp. 2548-2555.
M. Musavi, W. Ahmed, K. Chan, K. Faris, and D. Hummels , "On the training of radial basis function classifiers," Neural Netw., vol. 5, no. 4, pp. 595 - 603, 1992.
F. T. Liu , K. M. Tin g, Y. Yu, and Z.-H. Zhou, "Spectrum of variable randorn trees," JAIR, vol. 32, pp. 355-384, 2008.
H. Yan, Y. J iang, J. Zheng, C. Peng, and Q. Li, "A multilayer perceptron based medical decision support system for heart disease diagnosis," Expert Sysl. Appl., vol. 30, no. 2, pp. 272 - 281, 2006.
J. Suykens and J. Vandewalle, "Least squares support vec tor machine classifiers," Neural Process. Leu., vol. 9, no. 3, pp. 293-300, Jun 1999.
J. C. Platt, "12 fast trainiog of support vector rnachines usiog sequential minimal optimization," Advances in kernel methods, pp. 185- 208, 1999.
L. Breiman, "Random forests," Machine Learning, vol. 45, no. 1, pp. 5- 32, Oct 2001.
M. Story and R. G. Cong alton, "Accuracy assessment: a user's perspec tive," PE&RS, vol. 52, no. 3, pp. 397-399, 1986.
H. Honest and K. S. Khan, "Reportin g of measures of accuracy in systematic reviews of diagnostic lite rature ," RMC Health Serv. Res., vol. 2, no. 1, p. 4, Mar 2002.
B. Chimieski and R. Fagundes, "Associatio n and classification data mining algorithms comparicion over medical datasets," .IH!, pp. 44- 51, 2013.
J. R. Landis aod G. G. Koch, "The measurement of observer agreement for categorical data," Biometri cs , vol. 33, no. 1, pp. 159- 174, 1977.
R. G. Congalton and K. Green, Assessing the Accuracy of Remotely Sensed V ata : Principi es and Praclices, 2nd ed. Boca Raton: CRC Press, 12 2008.
Publicado
07/11/2020
Como Citar
SOUSA, Leonardo P.; BRITTO NETO, Laurindo S. ; VERAS, Rodrigo M. S..
Banknote Identification Methodology for Visually Impaired People. In: WORKSHOP DE TESES E DISSERTAÇÕES - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 33. , 2020, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 36-42.
DOI: https://doi.org/10.5753/sibgrapi.est.2020.12981.
