In this paper, we propose an effective classification method for the silhouettes of various kinds of clothes. There are two approaches to analyzing clothes. The first method focuses on the basic elements of a garment's design, from the viewpoint of its creator. The second method features detailed categories with respect to the garment made. The silhouette of a garment is one of the most important pieces of information in fashion design trends. Here, we focused on classifying silhouettes that lead to the creation of trends, rather than classifying items made of clothing. This classification makes it possible to create a data set of silhouettes that can be used to multi-class classifications in a deep neural network.
The silhouette is an important element of fashion design. The designer's sensibility is expressed by the design changes in silhouette lines. The purpose of this research is to construct a silhouette classification criterion and renew the silhouette category, The analyzed images that capture the silhouette transformations were selected from recent designer's collections of luxury brands: Dior, a traditional luxury brand; Sacai, a new Japanese brand; and Doris Van Noten, one of the Antwerp Six. 11 measurement points used for the catwalk analysis were based on the reference points measured during the production of the clothes. The analysis utilized a combination of cluster analysis and multidimensional scaling. As the results, nine silhouette categories were obtained and the trend change was grasped visually by systematizing and classifying silhouettes that are important in predicting the future of fashion design. Moreover, this method could be applicable to automatic silhouette classification for unknown silhouettes.
The objective of our studies is the inquiry into data set of the silhouette styling by machine learning for the luxury brands. The computer vision meets the visual fashion for the long years. Recently, computer vision techniques has been employed in algorithm of fashion recognition. But the aim of the computer vision is that the computer vision meets fashion but not that fashion meets computer visions. The luxury fashion consumer expects the favorite own beautiful silhouette styling, not simply the computer pictures. Therefore, silhouette learning of clothing by Neural Network Console needs to meet the personal professional styling knowledge.
:The main subject of our paper is to evaluate qualitatively the ambiguous fashion value. As this approach, we have adapted the repertory grid. The merit of this repertory grid approach is to use the laddering methods which analyze the human cognitive structure. Already the fashion marketing has described qualitatively the cognitive and affective value of the fashion consumers. The fashion marketing has called this fashion value "wearable needs". As the research method, the first step choice the small sample group in order to elucidate the "Love Metaphor". Then we interviewed the students about the picture they loved. According to the interview analysis we constructed the repertory grid of "Love Metaphor".
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.