Wheat spikelet detection on RGB images using deep machine learning
Open Access
- 5 March 2026
- journal article
- Published by Institute of Cytology and Genetics, SB RAS in Vavilov Journal of Genetics and Breeding
- Vol. 30 (1) , 27-35
Abstract
This study addresses the challenge of automated high-throughput phenotyping of wheat spike characteristics using modern computer vision and deep learning methods. Accurate estimation of spikelet number is a key indicator of plant productivity, yet traditional manual counting approaches are labor-intensive, slow, and difficult to scale to large breeding datasets. To overcome these limitations, we propose a spikelet detection strategy based on simplified point annotations, where an expert marks only the centers of spikelets rather than drawing detailed segmentation masks or bounding boxes. This significantly reduces annotation time and lowers the overall cost of preparing training datasets for machine learning models. To determine the most effective way of utilizing such simplified annotations, three computational methods were explored: segmentation of binary masks using a U-Net architecture, density regression based on two-dimensional Gaussian distributions optimized via Kullback–Leibler divergence, and detection of fixed-size bounding regions using the YOLOv8 object detection framework. The models were evaluated on dedicated test datasets using both quantitative metrics (MAE, MAPE) and spatial localization metrics (Precision, Recall, F1 score). The results demonstrate that U-Net-based approaches provide consistently high accuracy in spikelet localization and counting while maintaining robustness to annotation imperfections. In contrast, the YOLOv8-based method showed reduced performance, likely due to the geometric mismatch between fixed-size boxes and the natural elongated shape of spikelets. Overall, the proposed methodology highlights the effectiveness of combining minimalistic point-level annotation with advanced segmentation models for automating phenotyping workflows. This approach has the potential to accelerate breeding programs, enhance the efficiency of largescale phenotypic data collection, and support further development of robust computer-vision tools for plant science applications.Keywords
This publication has 28 references indexed in Scilit:
- Learning to Localise and Count with Incomplete Dot-annotations2021
- Designing Network Design Spaces2020
- Res2Net: A New Multi-Scale Backbone ArchitectureIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- SpikeletFCN: Counting Spikelets from Infield Wheat Crop Images Using Fully Convolutional Networks2019
- Rice and wheat grain counting method and software development based on Android systemComputers and Electronics in Agriculture, 2017
- You Only Look Once: Unified, Real-Time Object Detection2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Novel function of a putative MOC1 ortholog associated with spikelet number per spike in common wheatScientific Reports, 2015
- NIH Image to ImageJ: 25 years of image analysisNature Methods, 2012
- ImageNet: A large-scale hierarchical image database2009