Hu, TaoPoire, RichardWay, Danielle2026-05-312026-05-31WOS:001677276400001ORCID:/0000-0003-4801-5319/work/216099373ORCID:/0000-0002-5687-7421/work/216101550https://hdl.handle.net/1885/733809752Accurate and efficient leaf trait measurement is essential for plant phenotyping, agronomy, and ecological studies. In this work, we introduce Leaf Analyzer, a novel open-source, fully automated computer vision-based tool for high-throughput leaf morphological trait measurement such as leaf area, dimensions, perimeter, count, and percent damage. Unlike existing methods that rely on strong foreground-background contrast or controlled imaging conditions, Leaf Analyzer employs an unsupervised clustering approach based on the K-means++ clustering algorithm and a novel Leaf Background Separation (LBS) feature, which combines the L∗ and b∗ channels from CIEL∗a∗b∗ color space and the saturation channel from HSV color space. The proposed method and the LBS feature can effectively distinguish leaves from the background across varying lighting conditions, leaf colors, and camera orientations. To evaluate the performance of the new software, we conducted comprehensive quantitative and qualitative comparison experiments with two widely used software tools — Petiole Pro and LeafByte, demonstrating that Leaf Analyzer achieves superior accuracy and consistency, particularly under challenging imaging conditions. Additionally, we explore methods to further enhance measurement precision, including leaf flattening and the integration of supplementary leaf features such as texture features and color specific features. Beyond leaf trait measurement, we showcase the versatility of Leaf Analyzer in a range of applications, including nondestructive plant phenotyping, seed counting, root trait analysis, leaf area measurement for petri dish-grown plants, plant projected silhouette area or crown projection area estimation, leaf damage assessment, and broader plant science applications, making it a valuable tool for researchers working in laboratory and field environments.We acknowledge the use of the facilities, and scientific and technical assistance of the Australian Plant Phenomics Network (APPN), which is supported by the Australian Government’ s National Collaborative Research Infrastructure Strategy (NCRIS). We also knowledge the Australian National University (ANU) PhD students Sadia Ayyub, Sadia Majeed, Syamlal Sasi, Gervais Lee, honours student Liv Handfield, as well as former APPN tech lead Dr. Tim Brown and CSIRO Senior Research Scientist Dr. Gonzalo Estavillo for testing the Leaf Analyzer software and providing valuable feedback. We are also grateful to ANU Master's student Yikun Li, APPN Project Lead Dr. Frederike Stock, APPN Technical Officer Ming-Dao Chia, and CSIRO Senior Research Scientist Dr. Estavillo for supplying some of the image data used in this study.16enPublisher Copyright: © 2026 The Authors. Published by Elsevier B.V. on behalf of Nanjing Agricultural University. This is an open access article under the CC BY license. http://creativecommons.org/licenses/by/4.0/Leaf areaLeaf damage assessmentLeaf dimensionsLeaf segmentationLeaf traitsPercent herbivoryPlant phenotypingUnsupervised learning2025-12-2610.1016/j.plaphe.2025.100145105034473043