ScabyNet, a user-friendly application for detecting common scab in potato tubers using deep learning and morphological traits

Abstract

Common scab (CS) is a major bacterial disease causing lesions on potato tubers, degrading their appearance and reducing their market value. To accurately grade scab-infected potato tubers, this study introduces “ScabyNet”, an image processing approach combining color-morphology analysis with deep learning techniques. ScabyNet estimates tuber quality traits and accurately detects and quantifies CS severity levels from color images. It is presented as a standalone application with a graphical user interface comprising two main modules. One module identifies and separates tubers on images and estimates quality-related morphological features. In addition, it enables the extraction of tubers as standard tiles for the deep-learning module. The deep-learning module detects and quantifies the scab infection into five severity classes related to the relative infected area. The analysis was performed on a dataset of 7154 images of individual tiles collected from field and glasshouse experiments. Combining the two modules yields essential parameters for quality and disease inspection. The first module simplifies imaging by replacing the region proposal step of instance segmentation networks. Furthermore, the approach is an operational tool for an affordable phenotyping system that selects scab-resistant genotypes while maintaining their market standards.

The Combination of Low-Cost, Red–Green–Blue (RGB) Image Analysis and Machine Learning to Screen for Barley Plant Resistance to Net Blotch

“…This simple and low-cost solution mostly uses red-green-blue (RGB) imagery to extract information about the shape, texture, and color of plants, and has shown promise for the evaluation of different abiotic and biotic stresses even before the typical symptoms manifest [31,32]. Image acquisition can be performed through various methods, either manually [33] or via an automatic platform [34], and encompass various devices such as mobile phones [35], imaging chambers [36], high-throughput phenotyping facilities [37], or drones [38]. An example is the Phenocave, an automatic, low-cost, custom-built, and user-friendly system for image acquisition under indoor growth conditions [34].…”