D.: An efficient garment visual search based on shape context

Abstract:- In recent years, the theoretical models of mass consumer behavior have change to buy from websites rather than in stores. Because the high-growing of e-commerce, a new demand emerges: the special-purpose search engine for searching goods from network shop. How to meet the customer’s requirement in product search is an import problem. Although it is easy for human eyes to determine the existence of clothes styles, recognizing it automatically from a computer program is not a trivial problem. Our work focuses on the garment retrieval from the e-shopping database, which supports feature-based retrieval by shape categories and styles. Traditionally the rigid shape-based algorithms unable to apply well on garment images. Because the clothing is essentially a non-rigid soft object: it is apt to self-occlusion, folding, and has deformation among every part (such as sleeve and tube). While producing deformation, it also influenced by light which lead to various kinds of shade at clothes, and the surface might include various kinds of pattern, texture, little piece, and decorate, these will all cause the great interference on image analysis