自定义光学透镜数据集
收藏资源简介:
该数据集是由哈德斯菲尔德大学计算与工程学院创建,用于训练YOLOv8模型的图像数据集。数据集包含在受控照明条件下使用高分辨率数字相机拍摄的光学透镜图像,并通过注释标出缺陷和透镜区域。创建过程中,对图像进行了筛选以确保质量,并采用了多种数据增强技术以提高模型的泛化能力。该数据集旨在用于光学透镜制造中的质量控制和缺陷检测研究。
This image dataset was developed by the School of Computing and Engineering, University of Huddersfield specifically for training YOLOv8 models. It comprises optical lens images captured using high-resolution digital cameras under strictly controlled lighting conditions, with annotations marking both the lens regions and their associated defects. During the dataset construction process, image screening was conducted to ensure data quality, and multiple data augmentation techniques were adopted to improve the generalization capability of downstream models. This dataset is designed to support research on quality control and defect detection in optical lens manufacturing.

- 1YOLO Network For Defect Detection In Optical lenses哈德斯菲尔德大学计算与工程学院 · 2025年



