Image processing for positioning mechanical device with Backpropagation algorithm and separate handling of RGB components




Artificial Neural Networks; Automation; Digital images; Backpropagation Algorithm.


Different approaches for the use of Artificial Neural Networks - ANNs, in the recognition of image patterns, have been used with variations ranging from the processing of the image data to the ANN architecture itself. This paper describes the development of a system that aims to recognize patterns of images with ANNs of three inputs that receive images decomposed into their RGB components. The ANNs have an architecture with two hidden layers of six neurons each, and use the algorithm Backpropagation. The built model normalizes RGB components with values ​​between zero and one. The Backpropagation algorithm is used for the purpose of functional approximation of these components, and after training, the numerical arrangements obtained in the three outputs corresponding to the inputs are denormalized to form the resulting training image. Six image pattern had training in different ANNs, forming a system to recognized each pattern. The feasibility of using the model was verified with the tests for its generalization capacity. Images used to position a mechanical device, which did not participate in the training, were inserted into the system and from them the positioning of the device was performed, with a high degree of accuracy.

Author Biographies

Alzira Marques de Oliveira, Santa Cecilia University


João Inácio da Silva Filho, Santa Cecilia University


Dorotéa Vilanova Garcia, Santa Cecilia University


Heraldo Silveira Barbuy, Santa Cecilia University



Baranauskas, J. A. & Monard, M. C. (2000). “Reviewing some Machine Learning Concepts and Methods”. Relatório Técnico 102, Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo, São Carlos.

Braga, A. P., de Carvalho, A. P. de Leon, Ludermir & T. B. (2012). “Redes Neurais Artificiais – Teoria e Aplicações”. 2ª edição. ISBN 978-85-216-1564-4, 181 – 182, 198. Rio de Janeiro – Brasil. Editora gen LTC.

Capelli, A. (2008). “Automação Industrial – Controle do movimento e processos contínuos”. 2ª edição. ISBN 978-85-365-0117-8, 210. São Paulo – Brasil. Editora Érica.

Faceli, K., Lorena, A. C., Gama, J. & De Carvalho, A. C. P. L. F. (2019). “Inteligência Artificial – Uma Abordagem de Aprendizado de Máquina”. 2ª edição. ISBN 978-85-216-1880-5, 117. Rio de Janeiro, Brasil, Editora gen LTC.

Gonzalez, R. C. & Woods, R. E. (2010). “Processamento Digital de Imagens”. 3ª edição, ISBN 978-85-7605-401-6, 265. São Paulo – Brasil. Editora Pearson.

Haykin, S. (2001). “Redes Neurais – Princípios e Prática”, 2ª edição, ISBN 0-13-273350-1, 183 - 259. Porto Alegre – Brasil. Editora Bookman.

Newby, J. M., Schaefer, A. M., Lee, P. T., Forest, M. G. & Lai, S. K. (2018). “Convolutional neural networks automate detection for tracking of submicron-scale particles in 2D and 3D”. National Academy of Sciences. ISSN: 0027-8424. 115 no. 36 9026-9031.

Lakhili, Z., El Alami, A., Mesbah, A., Berrabou, A. & Qjidaa, H. (2018). “Deformable 3D Shape Classification Using 3D Racah Moments and Deep Neural Networks”. Second International Conference on Intelligent Computing in Data Sciences. Procedia Computer Science. 148, 12 – 20.

Luger, G. F. (2013). “Inteligência Artificial”. 6ª edição. ISBN 978-85-8143-550-3, 386. São Paulo - Brasil, Editora Pearson.

Mario, M. C., Da Silva Filho, J. I., Garcia, D. V., Fernandes, L.A. & Fernandes, C.L.M. (2018). “Artificial Neural Network with Backpropagation algorithm applied to pattern recognition of digital images“. 50, year 13. ISSN 1809-0648. Santos – Brasil. Editora Paralogike.

Pedrini, H. & Schartz, W. R. (2008). “Digital image analysis: principles, algorithms and applications “. Publisher Thomson Learning. ISBN 978-85-221-0595-3. São Paulo – Brasil. 22, 471.

Regmi, K. & Ali Borji, A. (2019). “Cross-view image synthesis using geometry-guided conditional GANs”. Computer Vision and Image Understanding, 187,

ISSN 1077-3142.

Russel, S., Norvig, P. (2004). “Inteligência Artificial”, 2ª edição, ISBN 85-352-1177-2, 872. Rio de Janeiro – Brasil. Editora Campus - Elsevier.

Sharma, N., Jain, V. & Mishra A. (2018). “An Analysis Of Convolutional Neural Networks For Image Classification “. Proceeded by Computer Science 132. International Conference on Computational Intelligence and Data Science. 377 – 384.

Solomon, C. & Breckon, T. (2013). “Fundamentals of digital image processing – a practical approach with examples in MATLAB”. Translated by José Rodolfo Souza, 1st edition, publisher LTC. Rio de Janeiro – RJ. 5, 8 - 10.

Soloman, S. (2012). “Sensores e sistemas de controle na indústria”. 2ª edição. ISBN 978-85-216-1096-0, 248 - 251. Rio de Janeiro – Brasil. Editora gen LTC.

Wang, S., Hu, L., Li, L., Zhang, W., Huang, Q. (2020). “Two-stream deep sparse network for accurate and efficient image restoration”. Computer Vision and Image Understanding. 200, 103029. ISSN 1077-3142.

Wei, L., Jin, C., Ping, W., Cheng, J., Yongheng, M. & Keshiting. C. (2021). “Dynamic Characteristics and Anti-slip Grasping of Two-Finger Translational Manipulator”. Frontiers in Neurorobotics. 15, 10.3389/fnbot.2021.684317. ISSN=1662-5218.

Talon, T. & Pellegrino, S. (2022). “Inextensible Surface Reconstruction Under Small Relative Deformations from Distributed Angle Measurements”. Int J Comput Vis.

Tuncer, T., Dogan, S. & Ertam F. (2019). “A novel neural network based image descriptor for texture classification”. Physica A: Statistical Mechanics and its Applications.Vol. 526, 120955.




How to Cite

MARIO, M. C. .; OLIVEIRA, A. M. de .; SILVA FILHO, J. I. da .; GARCIA, D. V. .; BARBUY, H. S. . Image processing for positioning mechanical device with Backpropagation algorithm and separate handling of RGB components. Research, Society and Development, [S. l.], v. 11, n. 2, p. e21311225768, 2022. DOI: 10.33448/rsd-v11i2.25768. Disponível em: Acesso em: 21 jun. 2024.