Image-based Plant Disease Diagnosis with Unsupervised Anomaly Detection Based on Reconstructability of Colors
This work addresses the problem of plant disease diagnosis for farmers and agriculturalists by reducing the reliance on large labeled datasets, which is a common bottleneck in supervised learning approaches.
This paper introduces an unsupervised anomaly detection technique for image-based plant disease diagnosis, which leverages a deep encoder-decoder network to reconstruct colors of healthy plant images. The method, which includes a pix2pix conditional adversarial network and a CIEDE2000 color difference-based anomaly score, demonstrated superior accuracy, interpretability, and computational efficiency compared to an existing anomaly detector on the PlantVillage dataset.
This paper proposes an unsupervised anomaly detection technique for image-based plant disease diagnosis. The construction of large and publicly available datasets containing labeled images of healthy and diseased crop plants led to growing interest in computer vision techniques for automatic plant disease diagnosis. Although supervised image classifiers based on deep learning can be a powerful tool for plant disease diagnosis, they require a huge amount of labeled data. The data mining technique of anomaly detection includes unsupervised approaches that do not require rare samples for training classifiers. We propose an unsupervised anomaly detection technique for image-based plant disease diagnosis that is based on the reconstructability of colors; a deep encoder-decoder network trained to reconstruct the colors of \textit{healthy} plant images should fail to reconstruct colors of symptomatic regions. Our proposed method includes a new image-based framework for plant disease detection that utilizes a conditional adversarial network called pix2pix and a new anomaly score based on CIEDE2000 color difference. Experiments with PlantVillage dataset demonstrated the superiority of our proposed method compared to an existing anomaly detector at identifying diseased crop images in terms of accuracy, interpretability and computational efficiency.