Data · dataset · 2025
SteelBlastQC Dataset
Listed in IISH Dataverse
The SteelBlastQC dataset consists of 1654 RGB images (512×512 pixels) of steel surfaces that are either shot-blasted or still need shot-blasting to achieve the required texture, forming a binary classification task.
Description
The dataset includes 888 “good” (ready for paint) images and 766 “not-good” (needs shot-blasting) images. As declared by the collaborating manufacturer, the ideally treated surface is clean and uniformly coarse with an average roughness level of SA 2.5.
The “not-good” class presents several types of defects to the surface, located by industrial shot-blasting experts. These include: fresh welding lines and cuts, abrasion, corrosion, and discoloration. The presented dataset can be used for training computer vision models for automated metal surface quality control, addressing the lack of publicly available datasets containing images of shot-blasted steel.
Read the rest (1 more)
For convenience and reproducibility, the data were split into train and test (80/20 ratio).
Links
Where it is published
- Dataverse dataset page dataverse.nl/dataset.xhtml?persistentId=doi%3A10.34894%2FEKZNN0 ↗
landing page · from datasets iisg amsterdam
- DOI doi.org/10.34894/ekznn0 ↗
DOI / persistent id · from datasets iisg amsterdam
Catalogue records · 1
- Dataverse API dataverse.nl/api/datasets/:persistentId/?persistentId=doi%3A10.34894%2FEKZN… ↗
metadata API · from datasets iisg amsterdam
Topics
- Stated by source
- Computer and Information Science · Engineering
- From keywords
- Computer Science & AI · Computer vision · Engineering
- Inferred from text
- Image 65%
Provenance · 1 source records, 12 field assertions
| Source | Key | Last seen | Raw |
|---|---|---|---|
| IISH Dataverse | doi:10.34894/EKZNN0 | 12 d ago | JSON v1 |
| Field | Assertion | Extractor | Evidence |
|---|---|---|---|
| concepts[field].anzsrc:field:460304 | mapping · datasets iisg amsterdam | vocabulary-mapper@1.0.0 | keywords['Computer Vision'] |
| concepts[field].dataverse_subject:computer-and-information-science | source · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | /subjects |
| concepts[field].dataverse_subject:engineering | source · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | /subjects |
| concepts[field].local:field:computer-science-ai | mapping · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | /subjects |
| concepts[field].local:field:engineering | mapping · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | /subjects |
| concepts[modality].local:modality:image | enrichment · datasets iisg amsterdam | keyword-concept-rules@1.0.0 | title+description (65%) |
| created_date | source · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | |
| description | source · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | /description |
| publication_date | source · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | |
| title | source · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | /name |
| updated_date | source · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 | |
| version_label | source · datasets iisg amsterdam | connector:datasets_iisg_amsterdam@1.0.0 |