Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning

Abstract

Deep learning and computer vision have become emerging tools for diseased plant phenotyping. Most previous studies focused on image-level disease classification. In this paper, pixel-level phenotypic feature (the distribution of spot) was analyzed by deep learning. Primarily, a diseased leaf dataset was collected and the corresponding pixel-level annotation was contributed. A dataset of apple leaves samples was used for training and optimization. Another set of grape and strawberry leaf samples was used as an extra testing dataset. Then, supervised convolutional neural networks were adopted for semantic segmentation. Moreover, the possibility of weakly supervised models for disease spot segmentation was also explored. Grad-CAM combined with ResNet-50 (ResNet-CAM), and that combined with a few-shot pretrained U-Net classifier for weakly supervised leaf spot segmentation (WSLSS), was designed. They were trained using image-level annotations (healthy versus diseased) to reduce the cost of annotation work. Results showed that the supervised DeepLab achieved the best performance (IoU = 0.829) on the apple leaf dataset. The weakly supervised WSLSS achieved an IoU of 0.434. When processing the extra testing dataset, WSLSS realized the best IoU of 0.511, which was even higher than fully supervised DeepLab (IoU = 0.458). Although there was a certain gap in IoU between the supervised models and weakly supervised ones, WSLSS showed stronger generalization ability than supervised models when processing the disease types not involved in the training procedure. Furthermore, the contributed dataset in this paper could help researchers get a quick start on designing their new segmentation methods in future studies.

Image-based classification of wheat spikes by glume pubescence using convolutional neural networks

“…Semi-supervised learning involves training samples with labeled and unlabeled images, where unlabeled images can receive pseudolabels or be assigned negative labels based on trained networks. This approach has been utilized in plant disease analysis (Zhou et al, 2023), counting cotton balls (Adke et al, 2022), and plant shoot counting (Karami et al, 2020).…”

Reviewing the essential roles of remote phenotyping, GWAS and explainable AI in practical marker-assisted selection for drought-tolerant winter wheat breeding

“…Moreover, deep learning models have expanded the range of possible predictions to include disease detection, stress severity quantification, and yield ( Mohanty et al., 2016 ; Giménez-Gallego et al., 2019 ; Zhou et al., 2021a ). An intriguing direction that research has taken is semi-supervised approaches to the learning problem ( Tang et al., 2023 ; Zhou et al., 2023 ). Semi-supervised deep learning is an ML paradigm where a model is trained using a combination of labelled and unlabelled data.…”

High-Throughput Analysis of Leaf Chlorophyll Content in Aquaponically Grown Lettuce Using Hyperspectral Reflectance and RGB Images

“…Previously, several approaches and strategies focused on specific aspects of the AutoML process. However, a range of fully automated approaches have been developed in recent years [54][55][56][57]. The AutoML automated approach encompasses sequential procedures to prepare the selected model for prediction:…”

“…Model Selection: The primary aim of model selection is to determine the ML models that exhibit the highest level of accuracy when trained on a particular dataset [54].…”