Detekcija površinskih napak na oblačilih za reciklažo z uporabo nadzorovanih metod globokega učenja

Efficient sorting of used garments is essential for textile recycling in the circular economy. Surface defect detection, such as identifying stains or tears, enables automated classification of items for reuse or recycling. In this paper, we focus on the problem of detecting surface defects on second-hand clothing using supervised deep learning methods. We present an analysis of our two previously proposed general-purpose surface defect detection models (SegDecNet and SuperSimpleNet) along with four modern backbone image classification architectures (ConvNeXt, ViT, Swin, and DINO). For evaluation, we curate a tailored binary classification dataset derived from the real-world garment dataset, including over 12000 annotated clothing images. Our results show that SuperSimpleNet significantly outperforms other methods, achieving an average precision of 72%, while highlight ing the inherent challenges of this task due to garment variability and subtle or occluded defects.