With the growing number of digital music, the automatic genre recognition problem has been receiving the spotlight in music retrieval information field. A large number of musical acoustic features are reported to degrade the genre classification performance and lead to heavy computational cost. In this paper, we propose a new method for selecting genre-discriminative feature subset from a large number of musical features. We show that the proposed method is able to improve the genre recognition accuracy compared to the traditional selection method.

Quilting, a technique to join two or more layers of fabrics, has long been used in the textile and fashion sectors. To evaluate dimensional effect of quilting that changes according to the characteristics of fabrics, 3D scanning method is employed in this study. Goal of this study is to interpret how fabric's composition, stiffness, thickness, and weight affect the appearance when quilted fabrics are used in a garment. Surface reconstruction method based on 3D scanning is used as a research method to evaluate the changing appearance depending on the material properties quantitatively with the quilting method. Besides, exemplary virtual clothing is realized through a virtual quilting method in 3D digital clothing system based on the properties of fabrics.