Character Recognition Using Fractal Dimension Values Obtained With Different Methods
Keywords:
Visão Computacional, Dimensão Fractal, Reconhecimento de CaracteresAbstract
Character recognition is an area of great interest because of the difficulty of obtaining infallible classifier systems. Among the descriptors used in this task is the fractal dimension. However, there are several methods for calculating the fractal dimension. Thus, this work presents an analysis of the classification using four fractal dimension values individually, calculated using four different methods and, finally, presents the results of a classification that makes combined use of the four fractal dimension values. The results obtained indicate an extraordinary gain with the combined use of the four fractal dimension values, as the success rates using the four individual fractal dimension measurements were 17.58%, 9.34%, 7.69% and 7.14%. While the combined use of the four values achieved a success rate of 72.53%, that is, a gain greater than four times the best individual rate.
Downloads
References
AGGARWAL, C. C. Neural Networks and Deep Learning: A Textbook. 2nd ed. [S. l.]: Springer, 2023. DOI: https://doi.org/10.1007/978-3-031-29642-0
AL SAYED, I., MAWLOD, A., ALNAJJAR, A., GHENI, H. Survey on Handwritten Recognition. In: INTERNATIONAL SYMPOSIUM ON MULTIDISCIPLINARY STUDIES AND INNOVATIVE TECHNOLOGIES (ISMSIT), 2022.Anais […]. [S. l.], 2022, p. 273-281. DOI: https://doi.org/10.1109/ISMSIT56059.2022.9932793
AL-TAEE, M.M.; NEJI, S.B.H.; FRIKHA, M., Handwritten Recognition: A survey, IEEE 4th International Conference on Image Processing, Applications and Systems (IPAS), Genova, Italy, 2020. DOI: https://doi.org/10.1109/IPAS50080.2020.9334936
ARTERO, A. O. Inteligência artificial: teoria e prática. São Paulo: Livraria da Física, 2009.
ARTERO, A. O.; OLIVEIRA, M. C. F. Viz3D: Effective Exploratory Visualization of Large Multidimensional Data Sets. In: BRAZILIAN SYMPOSIUM ON COMPUTER GRAPHICS AND IMAGE, 17., 2004. Processing […]. Curitiba: SIBGRAPI, 2004. p. 340–347. DOI: 10.1109/SIBGRA.2004.1352979
ASSIS, T.A.; MIRANDA, J.A.V.; MOTA F.M.; ANDRADE, R. F. S.; CASTILHO, C. M. C.; Geometria fractal: propriedades e características de fractais ideais. Revista Brasileira de Ensino de Física, v. 30, n. 2, 2008. DOI: https://doi.org/10.1590/S1806-11172008000200005.
BACKES, A. R. Implementação e comparação de métodos de estimativa da dimensão fractal e sua aplicação à análise e processamento de imagens. 2006. Dissertação (Mestrado) - ICMC-USP, São Carlos, 2006.
BACKES, A. R.; BRUNO, O. M., Técnicas de estimativa da dimensão fractal: um estudo comparativo, INFOCOMP Journal of Computer Science, v. 4, n. 3, p. 50–58, 2005.
BELAN, P. A.; NERY, E. P.; ARAÚJO, S. A. Software para auxílio à pré-alfabetização infantil baseado em reconhecimento inteligente de caracteres manuscritos. Exacta, v. 4, n. 1, p. 87–93, 2008. DOI: https://doi.org/10.5585/exactaep.v4i1.656
CHEN, X.; JIN, L.; ZHU, Y.; LUO, C.; WANG T., Text Recognition in the wild: a survey. ACM Computing Surveys (CSUR), v. 54, n. 2, 2021. DOI: https://doi.org/10.1145/3440756
CHIRIMILLA, R.; VARDHAN, V. A survey of optical character recognition techniques on indic script. ECS Transactions, v. 107, n. 1, 2022. DOI: https://doi.org/10.1149/10701.6507ecst
COELHO, R. C.; COSTA, L. F. The Box-Counting Fractal Dimension: Does it Provide an Accurate Subsidy for Experimental Shape Characterization? If So, How to Use It? In: SIBGRAPI, 1995. Anais […]. [S. l.: s.n.], 1995. p. 183-191,
DUGAR, S., Handbook on Standard Costing and Variance Analysis: Distinct Perspectives with Practical Examples, Independently published, 89p., 2022.
EIKVIL, L., Optical Character Recognition, Norsk Regnesentral, P.B. 114 Blindern, N-0314, December 1993.
IACOBUCCI, D., Analysis of Variance, Experimental Design, and Multivariate ANOVA, 3o ed., Independently published, 301p., 2023.
ISLAM, N., ISLAM,Z., NOOR, N., A Survey on Optical Character Recognition System, Journal of Information & Communication Technology-JICT, vol. 10 n. 2, 2016.
LAKSHMANAN, V.; GÖRNER, M.; GILLARD., Practical Machine Learning for Computer Vision: End-to-End Machine Learning for Images, O'Reilly Media, 480p., 2021.
LATHROP, J.I.; LUTZ, J.H.; SUMMERS, S.M., Strict self-assembly of discrete Sierpinski triangles. In: Proceedings of the third conference on computability in Europe, Siena, 18–23 June 2007. DOI: https://doi.org/10.1007/978-3-540-73001-9_47
LATHROP, J.I.; LUTZ, J.H.; SUMMERS, S.M., Strict self-assembly of discrete Sierpinski triangles. Theor Comput Sci 410:384–405, 2009. DOI: https://doi.org/10.1016/j.tcs.2008.09.062
MANDELBROT, B.B., The Fractal Geometry of Nature, Echo Point Books & Media, 500p, 2021.
MAYNARD, M., Neural Networks: Introduction to Artificial Neurons, Backpropagation and Multilayer Feedforward Neural Networks with Real-World Applications, Independently Published, 54p., 2020
MILANO, D; HONORATO, L.; Visão Computacional, Universidade Estadual de Campinas, 2010, pp. 1.
MIRANDA R.A.R.; SILVA, F.A.; PAZOTI M.A.; ARTERO A.O.; PITERI M.A.; Handwritten Character Recognition based on Frequency, Character-edge Distances and Densities, Colloquium Exactarum, v. 5, n.2, Jul-Dez. 2013, p.109 –127, 2013. DOI: https://doi.org/10.5747/ce.2013.v05.n2.e062
MONISHA, G.S., MALATHI, S., Effective Survey on Handwriting Character Recognition, In: Singh, V., Asari, V.K., Kumar, S., Patel, R.B. (Eds) Computational Methods and Data Engineering, Advances in Intelligent Systems and Computing, v. 1257, Springer, 2021. DOI: https://doi.org/10.1007/978-981-15-7907-3_9
OLIVEIRA, M. A. Backpropagation e redes neurais. São Paulo: Ciência Moderna, 2024. v. 1.
RAMYAA, C.H.; VARDHANA, B.V. A survey of optical character recognition techniques on indic script. ECS Transactions, v. 107, n. 1, p. 6507-6514, 2022. DOI: https://doi.org/10.1149/10701.6507ecst
SCHIERWAGEN, A. Scale-invariant diffusive growth: a dissipative principle relating neuronal form to function. In: MAYNARD-SMITH, J.; VIDA, G. (ed.). Organizational constraints on the dynamics of evolution. Manchester: Manchester University Press, 1990.
SCHWABISH, J. Better data visualizations: a guide for scholars, researchers, and wonks. [S.l.]: Columbia University Press, 2021. DOI: https://doi.org/10.7312/schw19310.
SHARMA, P. A survey on optical character recognition techniques. International Journal of Management, Technology and Engineering, v. 8, n. 10, 2018. Disponível em: https://ijamtes.org/gallery/370%20oct%20ijamte%20-%201126.pdf. Acesso em: 24 nov. 2025.
SHOLL, D. Dendritic organization in the neurons of the visual cortices of the cat. Journal of Anatomy, v. 87, p. 387-406, 1953. DOI: https://doi.org/10.1038/171387a0.
SILVA, E.; RODRIGUES, R. J.; THOMÉ, A. C. G. Extração de Características para o Reconhecimento de Letras Manuscritas. In: SIMPÓSIO BRASILEIRO DE AUTOMAÇÃO INTELIGENTE, 5., 2001 Canela, RS. Anais [...]. Canela: [s.n.], 2001.
SILVA, E. Reconhecimento inteligente de caracteres manuscritos. 2003.Dissertação (Mestrado em Engenharia) - Instituto Militar de Engenharia, 2003.
SILVA, J. L. S.; SALES, L.E.; SILVA Jr., W.S.; MELO, W. Análise de métodos de correção de iluminação. In: CONGRESSO NACIONAL DE INICIAÇÃO CIENTÍFICA, 16., 2016. Anais [...]. [S.l.: s.n.], 2016.
SILVA, F. A.; ARTERO, A. O.; PAIVA, M. S. V.; BARBOSA, R. L. Um algoritmo rápido para o reconhecimento de caracteres. Workshop de Visão Computacional – WVC, 7., 2011. Anais […]. [S.l.: s.n.], 2011.
SNEDECOR, G.W.; COCHRAN, W.G., Statistical Methods. 7th ed. [S. l.]: Iowa State, 1967.
STOYAN, D.; STOYAN, H. Methods for the empirical determination of fractal dimension. In: STOYAN, D., STOYAN, H. (Eds.). Fractals, Random Shapes and Point Fields. New York: Wiley, 1994. p. 39-45
SZELISKI, R. Computer vision: algorithms and applications (Texts in Computer Science). [S. l.]: Springer, 2022. DOI: https://doi.org/10.1007/978-3-030-34372-9.
TAKAYASU, H. Fractals in the physical sciences. Manchester: Manchester University Press, 1990.
TORRALBA, A.; ISOLA, P.; FREEMAN, W.T. Foundations of Computer Vision (Adaptive Computation and Machine Learning series). [S. l.]: The MIT Press, 2024.
WANG, X-F.; HE, Z-H.; WANG, K.; WANG, Y-F.; ZOU, L.; WU, Z-Z. A survey of text detection and recognition algorithms based on deep learning technology. Neurocomputing, v. 556, n. 1, 2023.
