Agrupamento de Imagens Baseado em uma Abordagem Híbrida entre a Otimização por Busca em Grupo e K-Means para a Segmentação Automática de Doenças em Plantas

• Luciano Pacífico Universidade Federal Rural de Pernambuco

DOI: https://doi.org/10.5753/eniac.2020.12125

Resumo

Neste trabalho, um algoritmo de agrupamento particional híbrido entre o K-Means e a Otimização por Busca em Grupo é usado para a tarefa de segmentação automática de doenças em imagens de folhas, como parte de um sistema automático de classificação de doenças em plantas: o GSO-KM. Uma abordagem não supervisionada de agrupamento de imagens é adotada no intuito de lidar com o problema. O GSO-KM é comparado a cinco algoritmos da literatura de agrupamento de dados através do uso de doze imagens, que apresentam diferentes graus de doença, e pelo uso de quatro métricas de avaliação. A análise experimental revelou que o GSO-KM é capaz de realizar, de forma satisfatória, a tarefa de segmentação das doenças nas imagens avaliadas.

Palavras-chave: Agrupamento de Imagens, Segmentação de Imagens, Otimização por Busca em Grupo, Visão Computacional, Análise de Agrupamentos

Referências

Abdel-Kader, R. F. (2010). Genetically improved pso algorithm for efficient data clustering. In Machine Learning and Computing (ICMLC), 2010 Second International Conference on, pages 71–75. IEEE.

Asuncion, A. and Newman, D. (2007). Uci machine learning repository.

Barbedo, J. G. A., Koenigkan, L. V., Halfeld-Vieira, B. A., Costa, R. V., Nechet, K. L., Godoy, C. V., Junior, M. L., Patricio, F. R. A., Talamini, V., Chitarra, L. G., et al. (2018). Annotated plant pathology databases for image-based detection and recognition of diseases. IEEE Latin America Transactions, 16(6):1749–1757.

Barnard, C. and Sibly, R. (1981). Producers and scroungers: a general model and its application to captive flocks of house sparrows. Animal Behaviour, 29(2):543–550.

Bezdek, J. C., Ehrlich, R., and Full, W. (1984). Fcm: The fuzzy c-means clustering algorithm. Computers & Geosciences, 10(2-3):191–203.

Civicioglu, P. (2013). Backtracking search optimization algorithm for numerical optimization problems. Applied Mathematics and computation, 219(15):8121–8144.

Couzin, I. D., Krause, J., Franks, N. R., and Levin, S. A. (2005). Effective leadership and decision-making in animal groups on the move. Nature, 433(7025):513–516.

Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. The Journal of Machine Learning Research, 7:1–30.

Dixon, A. (1959). An experimental study of the searching behaviour of the predatory coccinellid beetle adalia decempunctata (l.). The Journal of Animal Ecology, pages 259–281.

Eiben, A. E. and Smith, J. E. (2010). Introduction to evolutionary computing, volume 2. Springer Berlin.

Friedman, M. (1937). The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Journal of the american statistical association, 32(200):675– 701.

He, S., Wu, Q. H., and Saunders, J. (2009). Group search optimizer: an optimization algorithm inspired by animal searching behavior. IEEE Transactions on Evolutionary Computation, 13(5):973–990.

Higgins, C. L. and Strauss, R. E. (2004). Discrimination and classification of foraging paths produced by search-tactic models. Behavioral Ecology, 15(2):248–254.

Holland, J. H. (1992). Genetic algorithms. Scientific american, 267(1):66–72.

Kennedy, J. and Eberhart, R. (1995). Particle swarm optimization. In Neural Networks, 1995. Proceedings., IEEE International Conference on, volume 4, pages 1942–1948. IEEE.

Lee, S. H., Chan, C. S., Wilkin, P., and Remagnino, P. (2015). Deep-plant: Plant identification with convolutional neural networks. In 2015 IEEE international conference on image processing (ICIP), pages 452–456. IEEE.

MacQueen, J. et al. (1967). Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume 1, pages 281–297. California, USA.

Nemenyi, P. (1962). Distribution-free multiple comparisons. In Biometrics, volume 18, page 263. International Biometric Soc. 1441 I ST, NW, Suite 700, Washington, DC 20005-2210.

Pacifico, L. D. S., Britto, L. F. S., Oliveira, E. G., and Ludermir, T. B. (2019). Automatic classification of medicinal plant species based on color and texture features. In 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), pages 741–746. IEEE.

Pacifico, L. D. S. and Ludermir, T. B. (2018). Hybrid k-means and improved group search optimization methods for data clustering. In 2018 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE.

Pacifico, L. D. S. and Ludermir, T. B. (2019). Hybrid k-means and improved self-adaptive particle swarm optimization for data clustering. In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–7. IEEE.

Prajapati, H. B., Shah, J. P., and Dabhi, V. K. (2017). Detection and classification of rice plant diseases. Intelligent Decision Technologies, 11(3):357–373.

Sawarkar, V. and Kawathekar, S. (2018). A review: Rose plant disease detection using image processing. IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN, pages 2278–0661.

Solanke, S., Mehare, P., Shinde, S., Ingle, V., and Zope, S. (2018). Iot based crop disease detection and pesting for greenhouse-a review. In 2018 3rd International Conference for Convergence in Technology (I2CT), pages 1–4. IEEE.

Storn, R. and Price, K. (1995). Differential evolution—a simple and efficient adaptive scheme for global optimization over continuous spaces. international computer science institute, berkeley. Technical report, CA, 1995, Tech. Rep. TR-95–012.

Tanmayee, P. (2017). Rice crop monitoring system—a lot based machine vision approach. In 2017 International Conference on Nextgen Electronic Technologies: Silicon to Software (ICNETS2), pages 26–29. IEEE.