Classification of citrus leaf diseases using hyperspectral reflectance and fluorescence imaging and machine learning techniques

Authors: MIN, HYUN JUNG - Oak Ridge Institute For Science And Education (ORISE); Qin, Jianwei; YADAV, PAPPU - South Dakota State University; FREDERICK, QUENTIN - University Of Florida; BURKS, THOMAS - University Of Florida; DEWDNEY, MEGAN - University Of Florida; Baek, Insuck; Kim, Moon

Submitted to: Biosystems Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/11/2024
Publication Date: N/A
Citation: N/A

Interpretive Summary: Citrus diseases pose serious risks to Florida's citrus farms, leading to economic losses due to smaller fruit, surface imperfections, early fruit loss, and even tree mortality. This study examines how using advanced hyperspectral imaging (HSI) that combines reflectance and fluorescence can enhance the detection and classification of citrus diseases, such as canker, Huanglongbing (HLB), greasy spot, melanose, scab, and zinc deficiency, thereby improving management and mitigation efforts in citrus groves. The combination of the full spectrum and spectral bands from the HSI with pixel-based and leaf-based spectrum were trained using nine machine learning classifiers. The highest overall classification accuracy of 90.7% was achieved by using a support vector machine (SVM) classifier and pixel-based, whereas the best accuracy of 94.5% was acquired by a discriminant analysis classifier and leaf-based analysis. Therefore, the reflectance and fluorescence HSI with the machine learning techniques would assist the citrus industry and regulatory agencies (e.g., FDA and USDA APHIS) in enforcing standards for the quality and safety of citrus-related food and beverage products.

Technical Abstract: Citrus diseases are significant threats to citrus groves, causing financial losses through reduced fruit size, blemishes, premature fruit drop, and tree death. Detection of the citrus diseases via leaf inspection can improve grove management and mitigation efforts. This study explores the potential of combined reflectance and fluorescence hyperspectral imaging (HSI) for detecting and classifying a control group and citrus leaf diseases, including canker, Huanglongbing (HLB), greasy spot, melanose, scab, and zinc deficiency. The front and back sides of the leaves displaying visible symptoms were imaged using an HSI system. Nine machine learning classifiers were trained using full spectrum and spectral bands selected through principal component analysis (PCA) from the HSI with pixel-based and leaf-based spectrum. A support vector machine (SVM) classifier achieved the highest overall classification accuracy of 90.7% when employing the full spectrum of combined reflectance and fluorescence data and pixel-based analysis from the back side of the leaves, whereas a discriminant analysis classifier yielded the best accuracy of 94.5% with the full spectrum of combined reflectance and fluorescence data and leaf-based analysis. Among the diseases, control, scab, and melanose were classified most accurately, each with over 90% accuracy. The integration of the reflectance and fluorescence HSI with advanced machine learning techniques demonstrated the capability to accurately detect and classify these citrus leaf diseases with high precision.