12 March 2021 in Fashion Practice
Women’s upper body changes with age are categorized and analyzed. The researchers validated shape-related measurement variables, extracted principal components, and classified the shapes of 423 women ages 40–69 using 3 D body scans from the CAESAR database. Shape and posture differences were quantified according to four age groups based on 47 measurements processed into 27 shape-related variables; six principal components (i.e. acromion inclination, upper body slope, neck inclination, shoulder angle, upper back curvature, and back protrusion height) were identified. Acromial inclination, shoulder angle, and back protrusion height did not change with age, but upper back curvature increased after age 45, and the slope of the upper body inclined further forward after age 50. The neck demonstrated a more pronounced incline after age 55. The 50–69 group exhibited the greatest upper body slope and the largest back curvature. The 40–44 group showed the most backward shoulder point and the highest shoulders.
9 April 2007 in ETRI Journal
Query-by-example (QBE) is a well-known method for image retrieval. In reality, however, an example image to be used for the query is rarely available. Therefore, it is often necessary to find a good example image to be used for the query before applying the QBE method. Query-by-layout (QBL) is our proposal for that purpose. In particular, we make use of the visual descriptors such as the edge histogram descriptor (EHD) and the color layout descriptor (CLD) in MPEG-7. Since image features of the CLD and the EHD can be localized in terms of a 4×4 sub-image, we can specify image features such as color and edge distribution on each sub-image separately for image retrieval without a query image. Experimental results show that the proposed query method can be used to retrieve a good image as a starting point for further QBE-based image retrieval.
7 September 2018 in International Journal of Clothing Science and Technology
Purpose: The purpose of this paper is to develop a versatile and extensible three-dimensional (3D) body measurement system. Design/methodology/approach: An integrated development environment and a script language compiler were designed for easy definition of measurement process. Findings: Researchers can do every kind of anthropometric research with respect to gender, age or race simply by writing appropriate scripts. Research limitations/implications: System does not support the management of 3D data itself. The possible flaws of data should be removed by other hardware specific software. Practical implications: Researchers without comprehensive knowledge of computer programming can conduct complex anthropometric research by simply learning the concise script language. Social implications: This system will facilitate many anthropometric research works and will help to provide valuable information to many industries. Originality/value: This is the first script language based body data analysis system. The script language consists of about 60 simple commands. Researchers will be able to concentrate more on the research topic itself than on the painstaking computer programming.
27 April 2022 in International Journal of Clothing Science and Technology
Purpose: The purpose of this study is to solve the cold start problem caused by the lack of evaluation information about the products.Design/methodology/approach: A recommendation system has been developed by using the image data of the clothing products, assuming that the user considers the visual characteristics importantly when purchasing fashion products. In order to evaluate the performance of the model developed in this study, it was compared with Random, Itempop, Matrix Factorization and Generalized Matrix Factorization models.Findings: The newly developed model was able to cope with the cold start problem better than other models.Social implications: A hybrid recommendation system has been developed that combines the existing recommendation system with deep learning to effectively recommend fashion products considering the user's taste.Originality/value: This is the first research to improve the performance of fashion recommendation system using the deep learning model trained by the images of fashion products.