Comparative Analysis of Automatic Mask Generation Methods for Agricultural Seed Instance Segmentation
论文比较了多种自动掩膜生成方法在农业种子实例分割中的性能，数据详实，结论具有实用价值，但时效性稍差。
本文针对农业图像分析中像素级标注耗时费力的问题,比较了5种无需领域定制的自动掩码生成方法用于豌豆种子实例分割:Cellpose、EfficientSAM、SAM2、StarDist、FastSAM。研究使用164张图像数据集(100张手工标注含33462个实例,64张空白用于下游训练),固定测试集20张含6849个实例。结果显示,Cellpose在重叠豌豆尺寸颗粒上整体表现最佳(F1:0.957,Recall:0.973);EfficientSAM精度最高(mean IoU:0.970);SAM2召回高(0.965)但精度低(0.815);StarDist因形状约束在重叠颗粒上表现较差;FastSAM漏检密集簇中的颗粒。基于Cellpose自动标注的144张图像训练YOLO11m-seg模型与80张手工标注训练的模型性能接近(mAP50:0.848 vs 0.860),证明自动标注是密集农业影像中人工标注的实用替代品。
-
Article
-
Published: 08 August 2026
Scientific Reports (2026) Cite this article
We are providing an unedited version of this manuscript to give early access to its findings. Before final publication, the manuscript will undergo further editing. Please note there may be errors present which affect the content, and all legal disclaimers apply.
Abstract
In agricultural image analysis, training deep learning models relies on large amounts of pixel-level labeled data. However, individually labeling densely stacked and overlapping objects, such as pea seeds, is both time-consuming and laborious. This study compares five automated mask-generation methods for instance segmentation of pea seeds (Pisum sativum) that do not require domain-specific customization: Cellpose, EfficientSAM, SAM2, StarDist, and FastSAM. A dataset of 164 images was used in the study. 100 of these images were manually annotated by a trained annotator using the LabelMe tool, containing a total of 33,462 instance labels. The remaining 64 images were left unlabeled and evaluated for automated labeling in downstream model training. All methods were evaluated on a fixed testset of 20 images containing 6,849 instances using precision, recall, F1 score, and mean IoU metrics. The results show that Cellpose, developed for biomedical cell segmentation, achieved the highest overall performance on overlapping pea-sized particles (F1: 0.957, Recall: 0.973). EfficientSAM produced the most precise pixel-level masks (mean IoU: 0.970), while SAM2 exhibited high recall (0.965) but low precision (0.815). StarDist struggled with overlapping particles due to shape constraints (mean IoU: 0.866), while FastSAM missed many particles in dense clusters, achieving high precision (0.976) but low recall (0.725). Furthermore, the YOLO11m-seg model, trained on 144 images automatically labeled with Cellpose tags, performed nearly as well as the model trained on only 80 manually labeled images (mAP50: 0.848 vs. 0.860). These findings suggest that automated labeling could be a practical alternative to manual labeling, even in challenging agricultural imagery containing overlapping objects.
Funding
This work was supported by the Deanship of Scientific Research, the Vice Presidency for Graduate Studies and Scientific Research, King Faisal University, Saudi Arabia, under the project number KFU263615.
Author information
Authors and Affiliations
- Faculty of Engineering and Architecture, Sinop University, Sinop, Turkey
Yavuz Unal
- Department of Management Information Systems, College of Business Administration, King Faisal University, Al-Ahsa, 31982, Saudi Arabia
Yonis Gulzar
Authors
- Yavuz Unal
- Yonis Gulzar
Corresponding authors
Correspondence to Yavuz Unal or Yonis Gulzar.
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethics statement
This study does not involve human participants or human subjects. The annotation process was performed by a trained annotator on image data of agricultural seeds. Therefore, informed consent was not required.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Unal, Y., Gulzar, Y. Comparative analysis of automatic mask generation methods for agricultural seed instance segmentation. Sci Rep (2026). https://doi.org/10.1038/s41598-026-66297-4
-
Received: 20 May 2026
-
Accepted: 06 August 2026
-
Published: 08 August 2026