Aghamohammadesmaeilketabforoosh Kimia, Parfitt Joshua, Nikan Soodeh, Pearce Joshua M
Department of Electrical & Computer Engineering, Western University, London, Ontario, Canada.
College of Engineering, Pennsylvania State University, University Park, Pennsylvania, United States of America.
PLoS One. 2025 Apr 24;20(4):e0322189. doi: 10.1371/journal.pone.0322189. eCollection 2025.
The aim of this study was to train a Vision Transformer (ViT) model for semantic segmentation to differentiate between ripe and unripe strawberries using synthetic data to avoid challenges with conventional data collection methods. The solution used Blender to generate synthetic strawberry images along with their corresponding masks for precise segmentation. Subsequently, the synthetic images were used to train and evaluate the SwinUNet as a segmentation method, and Deep Domain Confusion was utilized for domain adaptation. The trained model was then tested on real images from the Strawberry Digital Images dataset. The performance on the real data achieved a Dice Similarity Coefficient of 94.8% for ripe strawberries and 94% for unripe strawberries, highlighting its effectiveness for applications such as fruit ripeness detection. Additionally, the results show that increasing the volume and diversity of the training data can significantly enhance the segmentation accuracy of each class. This approach demonstrates how synthetic datasets can be employed as a cost-effective and efficient solution for overcoming data scarcity in agricultural applications.
本研究的目的是训练一个用于语义分割的视觉Transformer（ViT）模型，以使用合成数据区分成熟和未成熟的草莓，从而避免传统数据收集方法带来的挑战。该解决方案使用Blender生成合成草莓图像及其相应的掩码，以进行精确分割。随后，使用合成图像训练和评估SwinUNet作为分割方法，并利用深度域混淆进行域适应。然后在来自草莓数字图像数据集的真实图像上测试训练好的模型。在真实数据上的性能，成熟草莓的骰子相似系数达到94.8%，未成熟草莓的骰子相似系数达到94%，突出了其在果实成熟度检测等应用中的有效性。此外，结果表明，增加训练数据的数量和多样性可以显著提高每个类别的分割精度。这种方法展示了合成数据集如何作为一种经济高效的解决方案，用于克服农业应用中的数据稀缺问题。
