Supervised Methods Applied to the Construction of a Vision System for the Classification of Cocoa Beans in the Cut-Test

• Felipe Santos UFRN
• Anne Canuto UFRN
• Benjamin Bedregal UFRN
• Eduardo Palmeira UESC
• Iaslan Silva UFRN

DOI: https://doi.org/10.5753/eniac.2019.9273

Resumo

Supervised machine learning methods, also known as classification algorithms, have been widely used in the literature for many classification tasks. In this context, some aspects of these algorithms, as the used attributes used and the form they were built, have a direct impact in the system performance. Therefore, in this paper, we evaluate the application of classification algorithms, along with attribute selection, to propose an improved version of a vision system that performs the classification of cocoa beans. The main aim of this investigation is to improve the performance of a cocoa classification system that aims at helping farmers to classify the different cocoa beans based on images of these beans.

Palavras-chave: Machine Learning, Artificial Neural Networks, Computer Vision

Referências

Al-Marakeby, A., Aly, A. A., and Salem, F. A. (2013). Fast quality inspection of food products using computer vision. International Journal of Advanced Research in Computer and Communication Engineering [1], 2.

Brasil, Ministério da Agricultura, P. e. A. (2008). Regulamento técnico da amêndoa de cacau. Diário Ocial da União, Brasília, 38. Instrução Normativa.

Catsberg, C. and Dommelen, K.-V. G. (1990). Cocoa and chocolate. In Food Handbook, pages 330–334. Springer.

Fayyad, U. M. and Irani, K. B. (1992). The attribute selection problem in decision tree generation. In AAAI, pages 104–110.

Hall, M. A. (2000). Correlation-based feature selection of discrete and numeric class machine learning.

Hall, M. A. and Holmes, G. (2003). Benchmarking attribute selection techniques for discrete class data mining. IEEE Transactions on Knowledge and Data engineering, 15(6):1437–1447.

Haralick, R. M., Shanmugam, K., Dinstein, I., et al. (1973). Textural features for image classication. IEEE Transactions on systems, man, and cybernetics, 3(6):610–621.

Im, J. and Jensen, J. R. (2005). A change detection model based on neighborhood correlation image analysis and decision tree classication. Remote Sensing of Environment, 99(3):326–340.

Majumdar, S., Jayas, D., Hehn, J., and Bulley, N. (1996). Classication of various grains using optical properties. Canadian Agricultural Engineering, 38(2):139–144.

Patil, N. K., Malemath, V. S., and Yadahalli, R. M. (2011). Color and texture based identication and classication of food grains using different color models and haralick features. International Journal on Computer Science and Engineering, 3(12):3669.

Quinlan, J. R. (1986). Induction of decision trees. Machine learning, 1(1):81–106.

Samaniego, L., Bárdossy, A., and Schulz, K. (2008). Supervised classication of remotely sensed imagery using a modied k-nn technique. IEEE Transactions on Geoscience and Remote Sensing, 46(7):2112–2125.

Santos, F., Palmeira, E., and Jesus, G. (2019). An image dataset of cut-test-classied cocoa beans. Data in brief, 24:103916.

Santos, F. A. (2019). Modelagem de um sistema de visão computacional para a classicação de amêndoas de cacau na prova de corte. Master’s thesis, Universidade Estadual de Santa Cruz, Ilhéus.

Santos, F. A., Palmeira, E. S., and Jesus, G. Q. (2018). Color, structural and textural features for the classication of a cocoa beans image dataset using articial neural network.

Savakar, D. (2012). Identication and classication of bulk fruits images using articial neural networks. International Journal of Engineering and Innovative Technology (IJEIT), 1(3):35–40.

Wareld, S. (1996). Fast k-nn classication for multichannel image data. Pattern Recognition Letters, 17(7):713–721.

Yang, C.-C., Prasher, S. O., Enright, P., Madramootoo, C., Burgess, M., Goel, P. K., and Callum, I. (2003). Application of decision tree technology for image classication using remote sensing data. Agricultural Systems, 76(3):1101–1117.