Public Datasets

CERTH Color Image Dataset of Folded Garments, Ioannis Mariolis and Sotiris Malassiotis

This dataset consists of colour images of folded garments. The dataset is designed for testing and benchmarking of various computer vision algorithms. That might include cloth segmentation, garment recognition, model fitting and fold detection. Manually annotated ground truth is also provided.

ftp://clopema.iti.gr/CERTH_folded_clothes_database

If used, please cite the following paper:

Ioannis Mariolis and Sotiris Malassiotis. Matching folded garments to unfolded templates using robust shape analysis techniques. Computer Analysis of Images and Patterns, volume 8048 of Lecture Notes in Computer Science, pages 193–200. Springer Berlin Heidelberg, 2013.

CERTH RGB-D Database of Clothes Hanging from Lowest Points.

This database consists of clothes hanging from their lowest point, as captured from an xtion sensor. The images contain RGB and Depth information.

ftp://clopema.iti.gr/CERTH_RF_unfolding_training_database

If used, please cite the following paper:

Autonomous Active Recognition and Unfolding of Clothes using Random Decision Forests and Probabilistic Planning. Andreas Doumanoglou, Andreas Kargakos, Tae-Kyun Kim, Sotiris Malassiotis. ICRA 2014.