The Automated Detection of Fusarium Wilt on Phalaenopsis Using VIS-NIR and SWIR Hyperspectral Imaging

• Published in: Remote sensing (Basel, Switzerland) Vol. 15; no. 17; p. 4174
• Main Authors: Shih, Min-Shao, Chang, Kai-Chun, Chou, Shao-An, Liu, Tsang-Sen, Ouyang, Yen-Chieh
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2023
• Subjects: Accuracy; Artificial neural networks; Automatic Target Generation Process (ATGP); Automation; Background noise; Cameras; Comparative analysis; Constrained Energy Minimization (CEM); Crop diseases; Data analysis; Deep Neural Network (DNN); Diagnosis; Diseases and pests; Fungal diseases of plants; Fusarium; Hyperspectral imaging; Identification and classification; Image processing; Infections; Machine learning; Methods; Multispectral photography; Near infrared spectroscopy; Neural networks; Orchids; Phalaenopsis; Popularity; Product quality; Remote sensing; Spectral Angle Mapper (SAM); Support Vector Machine (SVM); Support vector machines; Three-dimensional receiver operating characteristics (3D ROC); Unmanned aerial vehicles; Wilt; Taiwan
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs15174174

Phalaenopsis, an essential flower for export, is significantly affected by fusarium wilt, which impacts its export quality. Hyperspectral imaging technology offers the potential to detect fusarium wilt on Phalaenopsis. The goal of this study was to establish an automated platform for the rapid detection of fusarium wilt on Phalaenopsis. In this research, the automatic target generation process (ATGP) method was employed to identify outliers in the hyperspectral spectrum. Subsequently, the Spectral Angle Mapper (SAM) method was utilized to detect signals similar to the outliers. To suppress background noise and extract the region of interest (ROI), the Constrained Energy Minimization (CEM) method was implemented. For ROI classification and detection, a deep neural network (DNN), a support vector machine (SVM), and a Random Forest Classifier (RFC) were employed. Model performance was evaluated using three-dimensional receiver operating characteristics (3D ROC), and the automated identification system was integrated into hyperspectrometers. The proposed system achieved an accuracy of 95.77% with a total detection time of 3380 ms ± 86.36 ms, proving to be a practical and effective tool for detecting fusarium wilt on Phalaenopsis in the industry.