Stem-base Rot Disease Detection in Oil Palm using RGB  (Red, Green, Blue) and OCN (Orange, Cyan, NIR) Image Fusion Method Based on ResNet50

Prima Ria Rumata Panggabean; Rista Rista; Adhi Harmoko Saputro; Windri Handayani

doi:10.21009/SPEKTRA.101.02

Authors

Prima Ria Rumata Panggabean Department of Physics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Depok, 16424, Indonesia
Rista Rista Department of Physics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Depok, 16424, Indonesia
Adhi Harmoko Saputro Department of Physics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Depok, 16424, Indonesia
Windri Handayani Department of Biology, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Depok, 16424, Indonesia

DOI:

https://doi.org/10.21009/SPEKTRA.101.02

Keywords:

basal stem rot, image fusion, CNN

Abstract

Current image acquisition and processing methods still need to be improved to effectively detect oil palm diseases. A precise and fast method to detect stem base rot disease in oil palm trees can be developed using drone technology and image processing approaches. An OCN (Orange, Cyan, NIR) camera is added to a standard drone and equipped with an RGB (Red, Green, Blue) camera. Combining the two cameras is proposed to generate multispectral imagery using an image fusion method called early fusion. A Multispectral Convolution Neural Network (MCNN) is also introduced to detect stem base rot disease by analysing the leaf patterns of oil palms. Healthy and unhealthy leaf samples were collected from oil palm plantations in Bogor. The images that have passed the image processing stage with the fusion method become inputs for modelling to identify stem base rot disease in oil palm. The results of the research using the multispectral image fusion method (RGB and OCN) based on the ResNet50 architecture can be used to identify stem base rot disease in oil palm effectively, as evidenced by the training and validation accuracy of 97.75% and 96.48%.

References

Y. H. Haw, et al., "Detection of Ganoderma Boninense diseases of palm oil trees using machine learning," 13th IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2023, pp. 228–232, 2023, doi: 10.1109/ISCAIE57739.2023.10165368.

H. Santoso, "Peningkatan akurasi identifikasi penyakit busuk pangkal batang di perkebunan kelapa sawit menggunakan Unmanned Aerial Vehicle (UAV) dan Machine Learning," J. Penelit. Kelapa Sawit, vol. 31, no. 2, pp. 82–95, 2023, doi: 10.22302/iopri.jur.jpks.v31i2.218.

M. Wahyuni, T. Sabrina, Mukhlis, and H. Santoso, "Analysis of vegetation index of oil palm plants infected with Ganoderma disease," IOP Conf. Ser.: Earth Environ. Sci., vol. 1188, no. 1, 2023, doi: 10.1088/1755-1315/1188/1/012006.

M. A. R. Siregar, "Penggunaan teknologi drone dalam monitoring dan pengelolaan lahan pertanian," 2023. [Online]. Available: https://osf.io/dmu5g/download.

W. Wicaksono, et al., "Metode deteksi cepat serangan Ganoderma pada perkebunan kelapa sawit dengan penginderaan jauh," J. Embedded Syst. Secur. Intell. Syst., vol. 3, no. 2, pp. 135–142, 2022. [Online]. Available: http://journal.unm.ac.id/index.php/JESSI/article/view/467.

O. Win Kent, et al., "Early symptom detection of basal stem rot disease in oil palm trees using a deep learning approach on UAV images," Comput. Electron. Agric., vol. 213, p. 108192, 2023, doi: 10.1016/j.compag.2023.108192.

T. Chungcharoen, et al., "Machine learning-based prediction of nutritional status in oil palm leaves using proximal multispectral images," Comput. Electron. Agric., vol. 198, 2022, doi: 10.1016/j.compag.2022.107019.

M. A. Izzuddin, et al., "Analysis of multispectral imagery from unmanned aerial vehicle (UAV) using object-based image analysis for detection of Ganoderma disease in oil palm," J. Oil Palm Res., vol. 32, no. 3, pp. 497–508, 2020, doi: 10.21894/jopr.2020.0035.

M. H. Tan, et al., "Ganoderma boninense classification based on near-infrared spectral data using machine learning techniques," Chemometr. Intell. Lab. Syst., vol. 232, 2023, doi: 10.1016/j.chemolab.2022.104718.

H. Santoso, "Pengamatan dan pemetaan penyakit busuk pangkal batang di perkebunan kelapa sawit menggunakan Unmanned Aerial Vehicle (UAV) dan kamera multispektral," J. Fitopatol. Indones., vol. 16, no. 2, pp. 69–80, 2020, doi: 10.14692/jfi.16.2.69-80.

G. A. W. Satia, E. Firmansyah, and A. Umami, "Perancangan sistem identifikasi penyakit pada daun kelapa sawit (Elaeis guineensis Jacq.) dengan algoritma deep learning convolutional neural networks," J. Ilm. Pertan., vol. 19, no. 1, pp. 1–10, 2022, doi: 10.31849/jip.v19i1.9556.

S. Y. Boulahia, et al., "Early, intermediate and late fusion strategies for robust deep learning-based multimodal action recognition," Mach. Vis. Appl., vol. 32, no. 121, 2021, doi: 10.1007/s00138-021-01249-8.

J. Jiang, et al., "Multi-spectral RGB-NIR image classification using double-channel CNN," IEEE Access, vol. 7, pp. 20607–20613, 2019, doi: 10.1109/ACCESS.2019.2896128.

H. Lv, B. Deng, and X. Li, "Research on image fusion technology of infrared and visible image based on MST and CNN," 2022 IEEE 4th Int. Conf. Civil Aviat. Safety Inf. Technol., ICCASIT 2022, pp. 1395–1399, 2022, doi: 10.1109/ICCASIT55263.2022.9986707.

S. S. Priyanka and T. K. Kumar, "Multi-channel speech enhancement using early and late fusion convolutional neural networks," Signal Image Video Process., vol. 17, no. 4, pp. 973–979, 2023, doi: 10.1007/s11760-022-02301-4.

H. Su, C. Jung, and L. Yu, "Multi-spectral fusion and denoising of color and near-infrared images using multi-scale wavelet analysis," Sensors, vol. 21, no. 11, 2021, doi: 10.3390/s21113610.

E. Rasywir, et al., "Analisis dan implementasi diagnosis penyakit sawit dengan metode convolutional neural network (CNN)," Paradigma – J. Inform. Komput., vol. 22, no. 2, 2020, doi: 10.31294/p.v21i2.

W. Styorini, et al., "Penerapan deep learning pada jenis penyakit tanaman kelapa sawit menggunakan algoritma convolutional neural network," J. Politeknik Caltex Riau: J. Komput. Terapan, vol. 8, no. 2, 2022, doi: 10.35143/jkt.v8i2.5522.

K. Yarak, et al., "Oil palm tree detection and health classification on high‐resolution imagery using deep learning," Agriculture (Switzerland), vol. 11, no. 2, pp. 1–17, 2021, doi: 10.3390/agriculture11020183.

L. Z. Yong, et al., "Automatic detection of an early stage of basal stem rot disease infection using VGG16 and mask R-CNN," IOP Conf. Ser.: Earth Environ. Sci., vol. 1133, no. 1, 2023, doi: 10.1088/1755-1315/1133/1/012076.

D. Theckedath and R. R. Sedamkar, "Detecting affect states using VGG16, ResNet50 and SE-ResNet50 networks," SN Comput. Sci., vol. 1, no. 2, 2020, doi: 10.1007/s42979-020-0114-9.

H. K. Kumar and S. A. Kumar, "Comparison of ResNet50 algorithm with AlexNet algorithm in precise biometric palm print recognition," IEEE 9th Int. Conf. Smart Struct. Syst., ICSSS, 2023, doi: 10.1109/ICSSS58085.2023.10407082.

X. Liu, et al., "Sustainable oil palm resource assessment based on an enhanced deep learning method," Energies, vol. 15, no. 12, 2022, doi: 10.3390/en15124479.

E. Oktafanda, "Klasifikasi citra kualitas bibit dalam meningkatkan produksi kelapa sawit menggunakan metode convolutional neural network (CNN)," J. Inform. Ekon. Bisnis, pp. 72–77, 2022, doi: 10.37034/infeb.v4i3.143.

J. H. Ong, P. Ong, and W. K. Lee, "Image-based oil palm leaf disease detection using convolutional neural network," J. Inf. Commun. Technol., vol. 21, no. 3, pp. 383–410, 2022, doi: 10.32890/jict2022.21.3.4.