CT-OCR-2022 (scroll002)

CT-OCR-2022 dataset

Dataset is in the process of uploading, we plan to release packages scroll01-scroll04 by October 15, 2022, and packages folded01-folded-02 by October 29, 2022.

CT-OCR-2022 dataset contains optically scanned images for source paper document, 400 X-ray projections, 2687 CT-reconstructed cross-sections and  segmentation markups for 6 model objects.

Description of the data for each model object is presented in the table.

Files
Data description

[package].proj_src/proj_s_.log
X-ray measurement log file

[package].proj_src/*.tif
preprocessed projections before rotation axe correction

[package].proj_norm/proj_s_.log
X-ray measurement and geometry correction log file

[package].proj_norm/*.tif
preprocessed projections after rotation axe correction

[package].rec_XXXX/metadata.json
reconstruction metadata

[package].rec_XXXX/*.tif
CT-reconstructed volume, slices with size XXXX×XXXX

[package].seg_XXXX/*.tif.seg.png
segmentation markup

[package].blank.png
sample croped from pdf

[package].scan.png
sample croped from scanned image

Due to the large amount of data, folders were packed into multi-volume zip-archives. Dataset published in Zenodo service in several linked repositories.

scroll01 - https://doi.org/10.5281/zenodo.7123495
scroll02 -

Any questions, complaints, etc. can be directed to: [e-mail] (Dmitry Polevoy)

The article about this dataset is currently under review. When the article is published, the full reference will be added.