Recognition of marks in many texture noises on washing clothes

Abstract

Flexible objects such as clothes are hard to be handled by robots. But the working conditions for laundry factories are severe because of dusts, heats and steams, and full automation systems which can handle clothes are highly required. To automate these factories, a cloth handling robot system has been developed. The system consists with two robots, 3-D vision systems, flexible hands to handle clothes and mechanisms to help robots. It can handle face towels and hand towels. But to handle the bath towels, it is required to recognize the marks on bath towels. The marks on bath towels are written as a texture. The image of the towel marks contains many noises, and it is hard to recognize the mark in many textures. Here, to recognize the marks, the recognition method using HOG features has been introduced. The HOG feature space distances make robust recognition of marks on cloth textures.