Deep Features para sistemas de identificação de plantas
Resumo
A seleção de uma arquitetura de Rede Neural Convolucional Profunda (RNCP) é uma tarefa decisiva. Neste trabalho avaliamos o poder de generalização de Deep Features extraídas à partir de um amplo conjunto de RNCPs sem fine-tuning para classificação de espécies de plantas em imagens, utilizando um conjunto de dados de imagens multi-órgão. São comparadas as abordagens de classificação convencial com Softmax e uma alternativa baseada em SVM e seleção de features. A validação experimental permitiu indentificar os métodos mais promissores, com o métodos baseados em Softmax e SVM alcançando 0.76 e 0.82 de Micro-F1, respectivamente.
Palavras-chave:
Classificação de plantas, aprendizado profundo, SVM
Referências
Brahimi, M., Arsenovic, M., Laraba, S., Sladojevic, S., Boukhalfa, K., e Moussaoui, A. (2018). Deep Learning for Plant Diseases: Detection and Saliency Map Visualisation, pages 93–117. Springer International Publishing, Cham.
Feitoza, M. C., da Silva, W. B., e Calumby, R. T. (2019). Exploring deep features and transfer learning for plant species recognition. In Proceedings of the XV Brazilian Symposium on Information Systems, pages 1–8.
Khan, M. A., Akram, T., Sharif, M., Awais, M., Javed, K., Ali, H., e Saba, T. (2018). Ccdf: Automatic system for segmentation and recognition of fruit crops diseases based on correlation coefficient and deep CNN features. Computers and Electronics in Agriculture, 155:220–236.
Khan, M. A., Akram, T., Sharif, M., Javed, K., Raza, M., e Saba, T. (2020). An automated system for cucumber leaf diseased spot detection and classification using improved saliency method and deep features selection. Multimedia Tools and Applications, pages 1–30.
Li, Y., Nie, J., e Chao, X. (2020). Do we really need deep cnn for plant diseases identification? Computers and Electronics in Agriculture, 178:105803.
Maeda-Gutiérrez, V., Galván Tejada, C., Zanella Calzada, L., Celaya Padilla, J., Galván Tejada, J., Gamboa-Rosales, H., Luna-Garcia, H., Magallanes-Quintanar, R., Carlos, G.-M., e Olvera-Olvera, C. (2020). Comparison of convolutional neural network architectures for classification of tomato plant diseases. Applied Sciences, 10:1245.
Meng, Q., Qiu, R., He, J., Zhang, M., Ma, X., e Liu, G. (2015). Development of agricultural implement system based on machine vision and fuzzy control. Computers and Electronics in Agriculture, 112:128–138.
Shi, Y., Wang, N., Taylor, R., e Raun, W. (2015). Improvement of a ground-lidar-based corn plant population and spacing measurement system. Computers and Electronics in Agriculture, 112:92–101.
V. Sivakumar, A. N., Li, J., Scott, S., Psota, E., Jhala, A. J., Luck, J. D., e Shi, Y. (2020). Comparison of object detection and patch-based classification deep learning models on mid- to late-season weed detection in UAV imagery. Remote Sensing, 12(13).
Feitoza, M. C., da Silva, W. B., e Calumby, R. T. (2019). Exploring deep features and transfer learning for plant species recognition. In Proceedings of the XV Brazilian Symposium on Information Systems, pages 1–8.
Khan, M. A., Akram, T., Sharif, M., Awais, M., Javed, K., Ali, H., e Saba, T. (2018). Ccdf: Automatic system for segmentation and recognition of fruit crops diseases based on correlation coefficient and deep CNN features. Computers and Electronics in Agriculture, 155:220–236.
Khan, M. A., Akram, T., Sharif, M., Javed, K., Raza, M., e Saba, T. (2020). An automated system for cucumber leaf diseased spot detection and classification using improved saliency method and deep features selection. Multimedia Tools and Applications, pages 1–30.
Li, Y., Nie, J., e Chao, X. (2020). Do we really need deep cnn for plant diseases identification? Computers and Electronics in Agriculture, 178:105803.
Maeda-Gutiérrez, V., Galván Tejada, C., Zanella Calzada, L., Celaya Padilla, J., Galván Tejada, J., Gamboa-Rosales, H., Luna-Garcia, H., Magallanes-Quintanar, R., Carlos, G.-M., e Olvera-Olvera, C. (2020). Comparison of convolutional neural network architectures for classification of tomato plant diseases. Applied Sciences, 10:1245.
Meng, Q., Qiu, R., He, J., Zhang, M., Ma, X., e Liu, G. (2015). Development of agricultural implement system based on machine vision and fuzzy control. Computers and Electronics in Agriculture, 112:128–138.
Shi, Y., Wang, N., Taylor, R., e Raun, W. (2015). Improvement of a ground-lidar-based corn plant population and spacing measurement system. Computers and Electronics in Agriculture, 112:92–101.
V. Sivakumar, A. N., Li, J., Scott, S., Psota, E., Jhala, A. J., Luck, J. D., e Shi, Y. (2020). Comparison of object detection and patch-based classification deep learning models on mid- to late-season weed detection in UAV imagery. Remote Sensing, 12(13).
Publicado
10/11/2021
Como Citar
D. FILHO, Luciano A.; CALUMBY, Rodrigo T..
Deep Features para sistemas de identificação de plantas. In: CONGRESSO BRASILEIRO DE AGROINFORMÁTICA (SBIAGRO), 13. , 2021, Evento Online.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2021
.
p. 366-369.
ISSN 2177-9724.
DOI: https://doi.org/10.5753/sbiagro.2021.18410.
