AUTHOR=Artemenko Nikita V. , Genaev Mikhail A. , Epifanov Rostislav UI. , Komyshev Evgeny G. , Kruchinina Yulia V. , Koval Vasiliy S. , Goncharov Nikolay P. , Afonnikov Dmitry A. TITLE=Image-based classification of wheat spikes by glume pubescence using convolutional neural networks JOURNAL=Frontiers in Plant Science VOLUME=Volume 14 - 2023 YEAR=2024 URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2023.1336192 DOI=10.3389/fpls.2023.1336192 ISSN=1664-462X ABSTRACT=Pubescence is an important phenotypic trait observed in both vegetative and generative plant organs. Pubescent plants demonstrate increased resistance to various environmental stresses such as drought, low temperatures, and pests. It serves as a significant morphological marker and aids in selecting stress-resistant cultivars, particularly in wheat. In wheat, pubescence is visible on leaves, leaf sheath, glumes and nodes. Regarding glumes, the presence of pubescence plays a pivotal role in classification. It supplements other spike characteristics, aiding in distinguishing between different varieties within wheat species. The determination of pubescence typically involves visual analysis by an expert. However, methods without the use of binocular loupe tend to be subjective, while employing additional equipment is labor-intensive. This paper proposes an integrated approach to determine glume pubescence presence in spike images captured under laboratory conditions using a digital camera and convolutional neural networks. Initially, image segmentation is conducted to extract the contour of the spike body, followed by cropping of the spike images to an equal size. These images are then classified based on the glume pubescence (pubescent/glabrous) using various convolutional neural networks architectures (Resnet-18, EfficientNet-B0 and EfficientNet-B1). The networks were trained and tested on a dataset comprising 9664 spike images. For segmentation, the U-Net model with EfficientNet-B1 encoder was chosen, achieving the segmentation accuracy IoU=0.947 for the spike body and 0.777 for awns. The classification model for glume pubescence with the highest performance utilized the EfficientNet-B1 architecture. On the test sample, the model exhibited prediction accuracy parameters of F1=0.85 and AUC=0.96, while on the holdout sample it showed F1=0.84 and AUC=0.89. Additionally, the study investigated the relationship between image scale, artificial distortions and 2 This is a provisional file, not the final typeset article model prediction performance, revealing that higher magnification and smaller distortions yielded more accurate prediction of glume pubescence.