Botanic Spectrum Analyser: A Deep Learning GUI for Plant Image Segmentation in Hyperspectral and RGB Phenotyping

Abstract

Plant phenotyping systematically quantifies plant traits such as growth, morphology, physiology, or yield, assessing genetic and environmental influences on plant performance. The integration of advanced phenotyping technologies, including imaging sensors and data analytics, facilitates the non-destructive and longitudinal acquisition of high-throughput data. Nevertheless, the sheer volume of such phenotyping data introduces significant challenges for researchers, particularly related to data processing. To overcome these challenges, researchers are turning to artificial intelligence (AI), a tool that can autonomously process and learn from large amounts of data. Despite this advantage, accurate image segmentation remains a key hurdle due to the complexity of plant morphology and environmental noise. In this study, we present the Botanical Spectrum Analyser (BSA), a user-friendly graphical user interface (GUI) that integrates a modified U-Net deep neural network for plant image segmentation. Designed for accessibility, BSA enables non-technical users to apply advanced AI segmentation to RGB and hyperspectral (VNIR and SWIR) imagery. We evaluated BSAs performance across three case studies involving wheat, barley, and Arabidopsis, demonstrating its robustness across species and imaging modalities. Our results show that BSA achieves an average accuracy of 99.7%, with F1-scores consistently exceeding 98% and strong Jaccard and recall performance across datasets. For challenging root segmentation tasks, BSA outperformed commercial algorithms, achieving a 76% F1-score compared to 24%, representing a 50% improvement. These results highlight the adaptability of the BSA framework for diverse phenotyping scenarios, bridging the gap between advanced deep learning methods and accessible plant science applications.