Fashion Product Defects Dataset
An image dataset of fashion product defects, that can be used for testing or training for AI models.
Asset Description
A set of fashion product defects images that include, but are no limited to the following common defects: uneven shrinkage, uneven betel, overlapping crucibles, reserve from the uneven trouser hem, hook and eye not conforming (crooked), broken crucible, wider seam allowance than zipper and lace overlay, surfilate deviated (fallen), deformed pockets at final ironing, uneven collar, printed pockets at the final iron, deformed slits at final ironing, Pocket corner is misaligned (crooked) ,the second crucible is missing, the hem (the bottom part) must not be visible on the face of the product, pin marks (holes), the collar has no left-right symmetry, stepped crucible (discontinued), crooked pocket reinforcement crucible.
Dataset Details
Dataset Overview
Images of fashion products that contain defects that were found during a regular work day taken with a phone camera. Most of the defective products have examples of good products.
Usage
This is an image dataset and can be used for testing or training for AI models.
Maturity
Ongoing development: currently there are around 310 images where annotation has started based on findings from production. New images are added at a weekly basis.
Licence
Proprietary
Resources
- For further information, please contact eduard.modreanu@katty-fashion.ro with CC to project.management@katty-fashion.ro
Acknowledgement
The dataset was created in the framework of the AI REDGIO 5.0 project. It will be used in the Industrial Pilot VII: Quality Assurance of clothing production at Katty Fashion