{"url":"/dataset/compass-xp","name":"COMPASS-XP","full_name":null,"description_markdown":"COMPASS-XP is a dataset of matched photographic and X-ray images of single objects, made available\r\nfor use in Machine Learning & Computer Vision research, in particular in the context of transport\r\nsecurity. Objects are imaged in multiple poses, and accompanied by metadata including labels for\r\nwhether we consider the object to be dangerous in the context of aviation. Object classes overlap with\r\nthose in the popular ImageNet Large Scale Visual Recognition Challenge class set and theWordNet\r\nlexical database, and identifiers for shared classes in both schemes are also provided.\r\n\r\nHardware Configuration\r\nPhotographs were captured with a Sony DSC-W800 compact digital camera. X-ray scans were obtained\r\nusing a Gilardoni FEP ME 536 mailroom X-ray machine, distributed in the UK by Todd Research\r\nunder the name TR50. The scanner is dual energy and generates several image outputs:\r\n• Low: Raw 8-bit greyscale data from the scanner’s low energy X-ray channel.    \r\n• High: Raw 8-bit greyscale data from the scanner’s high energy X-ray channel.    \r\n• Density: 8-bit greyscale data representing inferred material density computed from the two channels.    \r\n• Grey: RGB PNG image representing a combination of both low and high energy channels with some appearance improvements. Although nominally greyscale, the image does include subtle duotone-style colouration.    \r\n• Colour RGB PNG image with false colour palette representing material density.    \r\n\r\nIn practice the grey and colour versions are probably most useful, but for\r\ncompleteness the dataset includes all variants for each scan.\r\n\r\nData Files\r\nImage files are supplied in six subdirectories, corresponding to the five X-ray image variants above\r\nplus photos. X-rays are provided in PNG format, while photos are JPEG. Each scan is identified by a\r\nnumeric index, which is also used to name the file, padded with leading zeros to always be 4 digits\r\nlong.\r\n\r\nScan metadata is provided in the accompanying tab-delimited text file, meta.txt. This includes the\r\nfollowing columns:\r\n• basename: The zero-padded identifier for the scan. All six image type variants for the same class-instance-pose have the same basename. X-ray files are named basename.png while photos are basename.jpg.    \r\n• class: The object class in the scan.    \r\n• instance: An integer identifying the object instance. Instances start at 1 for each class.     \r\n• pose: An integer identifying the object pose. Poses start at 1 for each instance.    \r\n• scan tray: Either A, indicating that the pose was imaged in a weighted tray, or N indicating it was not.    \r\n• dangerous: Whether the object was considered dangerous (True/False).    \r\n• IN id: Numeric index of the object class in the ILSVRC list of 1000 classes, or empty if the class isn’t present there.    \r\n• WN id: WordNet identifier for the object class, or empty if the class isn’t present inWordNet.    \r\n\r\nLicense\r\nThe COMPASS-XP dataset was acquired as part of a research project funded by the UK Government\r\nFuture Aviation Security Solutions programme. Both the images and their metadata are licensed under\r\nthe Creative Commons Attribution 4.0 International License and may be freely used for research and\r\ncommercial purpose, including derivative works, providing the source is acknowledged.\r\n\r\nCOMPASS-XP Dataset Authors\r\nLewis D. Griffin*, Matthew Caldwell, Jerone T. A. Andrews\r\nComputational Security Science Group, UCL\r\n* l.griffin@cs.ucl.ac.uk","description_withheld":null,"homepage":"https://zenodo.org/records/2654887","introduced_date":"2018-11-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/unexpected-item-in-the-bagging-area-anomaly","title":"‘Unexpected item in the bagging area’: Anomaly Detection in X-ray Security Images","first_author":"Lewis D. Griffin","url":null},"license":{"name":"Creative Commons Attribution 4.0 International License","url":"https://creativecommons.org/licenses/by/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Anomaly Detection","url":"/task/anomaly-detection","datasets_with_task":"/datasets/task/anomaly-detection"}],"languages":[],"variants":["COMPASS-XP"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}