Development of an image recognition system for material tags using machine learning

Abstract

In this study, we focus on sustainable fashion initiatives, particularly secondhand clothes. We interviewed Nakano Corporation, a company involved in these initiatives. They manually sort 10 to 20 tons of used clothes daily, facing a manpower shortage. To address this, they are exploring mechanizing the sorting process. We develop and evaluate an image recognition system to automate and improve efficiency in sorting by identifying material tags on used clothes using machine learning.