ORVS (Online Retinal image for Vessel Segmentation (ORVS))

ORVS 数据集是卡尔加里大学计算机科学和视觉科学系之间的合作新建立的。
该数据集包含从加拿大卡尔加里的一家诊所收集的 49 幅图像（42 幅训练图像和 7 幅测试图像）。所有图像均使用具有 30 度视野 (FOV) 的 Zeiss Visucam 200 获取。图像大小为 1444×1444，每像素 24 位。图像以 JPEG 格式存储，压缩率低，这在眼科实践中很常见。所有图像均由一位一直在视网膜图像分析领域工作并经过培训的专家手动追踪。要求专家标记属于视网膜血管的所有像素。 Windows Paint 3D 工具用于手动标记图像。

The ORVS dataset is a newly established collaborative project between the Department of Computer Science and the Department of Vision Science at the University of Calgary.
This dataset contains 49 images collected from a clinic in Calgary, Canada, including 42 training images and 7 test images. All images were acquired using a Zeiss Visucam 200 with a 30-degree field of view (FOV). The images have a resolution of 1444×1444, with 24 bits per pixel, and are stored in JPEG format with low compression, which is a common practice in ophthalmic practice.
All images were manually annotated by an expert who has worked and received professional training in the field of retinal image analysis. The expert was required to label all pixels belonging to retinal blood vessels. The Windows Paint 3D tool was used to perform the manual annotation of these images.