Multiclass classifier based on deep learning for detection of citrus disease using fluorescence imaging spectroscopy

Neves, Ruan F O; Wetterich, Caio Bruno; Sousa, Elaine P M; Marcassa, Luís Gustavo

doi:10.1088/1555-6611/acc6bd

Cited by 5 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neves et al tested several classifiers on features extracted from fluorescence imagery with a convolutional neural network (CNN) to distinguish canker, HLB, scab, and zinc deficiency. The system developed was a low-cost, early detection system [17]. Kukreja et al diagnosed canker severity on leaves using a CNN for feature extraction and support vector machines (SVM) for classification.…”

Section: Multiclass Citrus Leaf Inspectionmentioning

confidence: 99%

Classifying adaxial and abaxial sides of diseased citrus leaves with selected hyperspectral bands and YOLOv8

Frederick,

Burks,

Yadav

et al. 2024

Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping IX

View full text Add to dashboard Cite

Citrus greening disease (HLB) and citrus canker are diseases afflicting Florida citrus groves, causing financial losses through smaller fruits, blemishes, premature fruit drop and/or eventual tree death. Often, symptoms of these resemble those of other defects/infections. Early detection of HLB and canker via in-grove leaf inspection can permit more effective mitigation tactics and more intelligent management of groves. Autonomous, vision-based disease scouting in a grove offers a financial benefit to the Florida citrus industry. This study investigates the potential of hyperspectral reflectance imagery (HSI) for detecting and classifying these conditions in the presence of other, less consequential leaf defects. Both sides of leaves with visible symptoms of HLB, canker, zinc deficiency, scab, melanose, greasy spot, and a control set were collected and imaged with a line-scan hyperspectral camera. Spectral bands from this imagery were selected using two methods: an unsupervised method based on principal component analysis (PCA), and a supervised method based on linear discriminant analysis (LDA). Using the selected bands, the YOLOv8 network architecture was trained to classify each side of these leaves. LDA-selected bands from the back of the leaves yielded an overall classification accuracy of 84.23%. Leaves with HLB and zinc deficiency were classified most accurately, with F1 scores of 0.977 and 0.953, respectively. On the back side of the leaf, recall of melanose was significantly improved by using the LDA bands. These findings favor the use of supervised band selection for HSI-based in-grove disease detection.

show abstract

Section: Multiclass Citrus Leaf Inspectionmentioning

confidence: 99%

Classifying adaxial and abaxial sides of diseased citrus leaves with selected hyperspectral bands and YOLOv8

Frederick,

Burks,

Yadav

et al. 2024

Autonomous Air and Ground Sensing Systems for Agricultural Optimization and Phenotyping IX

View full text Add to dashboard Cite

show abstract

“…Previous research on deep learning based methods have achieved promising results in the early detection of plant diseases ( Upadhyay and Kumar, 2021 ), lesion segmentation ( Li et al., 2022 ), disease type classification ( Xing et al., 2019 ), and disease occurrence prediction ( Delnevo et al., 2022 ). Historically, citrus disease identification and classification methods have primarily used single-source data based on image modalities, including images ( Barman et al., 2020 ; Luaibi et al., 2021 ; Syed-Ab-Rahman et al., 2022 ), fluorescence spectra ( Neves et al., 2023 ), and Internet of Things (IoT) data ( Delnevo et al., 2022 ). The performance of such methods is highly dependent on large datasets and manual annotation.…”

Section: Introductionmentioning

confidence: 99%

Detection of citrus diseases in complex backgrounds based on image–text multimodal fusion and knowledge assistance

Qiu,

Chen,

Huang

et al. 2023

Front. Plant Sci.

View full text Add to dashboard Cite

Diseases pose a significant threat to the citrus industry, and the accurate detection of these diseases represent key factors for their early diagnosis and precise control. Existing diagnostic methods primarily rely on image models trained on vast datasets and limited their applicability due to singular backgrounds. To devise a more accurate, robust, and versatile model for citrus disease classification, this study focused on data diversity, knowledge assistance, and modal fusion. Leaves from healthy plants and plants infected with 10 prevalent diseases (citrus greening, citrus canker, anthracnose, scab, greasy spot, melanose, sooty mold, nitrogen deficiency, magnesium deficiency, and iron deficiency) were used as materials. Initially, three datasets with white, natural, and mixed backgrounds were constructed to analyze their effects on the training accuracy, test generalization ability, and classification balance. This diversification of data significantly improved the model’s adaptability to natural settings. Subsequently, by leveraging agricultural domain knowledge, a structured citrus disease features glossary was developed to enhance the efficiency of data preparation and the credibility of identification results. To address the underutilization of multimodal data in existing models, this study explored semantic embedding methods for disease images and structured descriptive texts. Convolutional networks with different depths (VGG16, ResNet50, MobileNetV2, and ShuffleNetV2) were used to extract the visual features of leaves. Concurrently, TextCNN and fastText were used to extract textual features and semantic relationships. By integrating the complementary nature of the image and text information, a joint learning model for citrus disease features was achieved. ShuffleNetV2 + TextCNN, the optimal multimodal model, achieved a classification accuracy of 98.33% on the mixed dataset, which represented improvements of 9.78% and 21.11% over the single-image and single-text models, respectively. This model also exhibited faster convergence, superior classification balance, and enhanced generalization capability, compared with the other methods. The image-text multimodal feature fusion network proposed in this study, which integrates text and image features with domain knowledge, can identify and classify citrus diseases in scenarios with limited samples and multiple background noise. The proposed model provides a more reliable decision-making basis for the precise application of biological and chemical control strategies for citrus production.

show abstract

Sensor fusion techniques in deep learning for multimodal fruit and vegetable quality assessment: A comprehensive review

Singh,

Nisha,

Naik

et al. 2024

Food Measure

View full text Add to dashboard Cite

Multiclass classifier based on deep learning for detection of citrus disease using fluorescence imaging spectroscopy

Cited by 5 publications

References 50 publications

Classifying adaxial and abaxial sides of diseased citrus leaves with selected hyperspectral bands and YOLOv8

Classifying adaxial and abaxial sides of diseased citrus leaves with selected hyperspectral bands and YOLOv8

Detection of citrus diseases in complex backgrounds based on image–text multimodal fusion and knowledge assistance

Sensor fusion techniques in deep learning for multimodal fruit and vegetable quality assessment: A comprehensive review

Contact Info

Product

Resources

About