Innovative Leaf Disease Mapping: Unsupervised Anomaly Detection for Precise Area Estimation
Preprint
- 21 August 2024
- preprint
- Published by Springer Nature in Research Square
Abstract
Detecting and quantifying the diseased regions in a leaf is an important task in plant breeding in order to select plants based on disease resistance. Ratings done by eye and hand are not accurate, can be highly subjective and take a lot of work hours. Using machine learning, it is possible to generate faster more accurate data. By combining modern anomaly detection algorithms with masking algorithms a robust method capable of estimating the infected leaf area was developed, resulting in a novel method with superior results. Using unsupervised models both for the masking and for the detection, the method can easily be used for different kinds of detection tasks.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies2024
- Deep learning-based segmentation for disease identificationEcological Informatics, 2023
- Modified U-Net for plant diseased leaf image segmentationComputers and Electronics in Agriculture, 2022
- Self-Supervised Leaf Segmentation under Complex Lighting ConditionsPattern Recognition, 2022
- Towards Total Recall in Industrial Anomaly Detection2022
- FreeSOLO: Learning to Segment Objects without Annotations2022
- Depthwise separable convolution architectures for plant disease classificationComputers and Electronics in Agriculture, 2019
- Visual Rating and the Use of Image Analysis for Assessing Different Symptoms of Citrus Canker on Grapefruit LeavesPlant Disease, 2008
- Improving the accuracy and precision of disease assessments: selection of methods and use of computer-aided training programsCanadian Journal of Plant Pathology, 1995
- A Threshold Selection Method from Gray-Level HistogramsIEEE Transactions on Systems, Man, and Cybernetics, 1979