Instance recognition of clumped clothing using image features focusing on clothing fabrics and wrinkles

This paper describes about a method of instance recognition for clumped clothes. The method assumes to be used for building autonomous systems, with the purpose of recognizing day-to-day clothing thrown casually. A set of Gabor filters is applied to an input image, and then several image features that are invariant to translation and rotation are generated. To cope with a situation in clumped clothes, the feature description is applied after image over-segmentation and boundary edge detection. Experiments of state description and instance recognition using real clothes show the effectiveness of the proposed method.