SIXray
收藏资源简介:
SIXray数据集是由中国科学院大学等机构创建的,包含超过100万张X射线图像,其中8929张图像标注了6类禁止物品。该数据集模拟了真实世界中安全检查的场景,其中禁止物品的出现频率非常低。数据集的创建旨在为研究提供一个基准,以解决X射线图像中物品重叠和复杂背景带来的挑战。SIXray数据集的应用领域主要集中在提高自动识别X射线图像中禁止物品的准确性和效率,以增强公共安全。
The SIXray dataset was developed by institutions including the University of Chinese Academy of Sciences. It contains more than 1 million X-ray images, among which 8929 images are annotated with 6 categories of prohibited items. This dataset simulates real-world security inspection scenarios, where the prevalence of prohibited items is extremely low. The dataset is designed to provide a benchmark for research aiming to tackle the challenges arising from overlapping objects and complex backgrounds in X-ray images. The primary application of the SIXray dataset focuses on improving the accuracy and efficiency of automatic recognition of prohibited items in X-ray images, thereby enhancing public safety.

- 1SIXray : A Large-scale Security Inspection X-ray Benchmark for Prohibited Item Discovery in Overlapping Images中国科学院大学 · 2019年



