A novel optimization approach to minimize aggregate-fit-loss for improved breast sizing

Abstract

Ready-to-wear clothing is typically based on the body-shape of human fit models that an apparel company hires. The body-shape difference between a consumer and the fit model of their size results in fit-loss of a certain degree. Aggregate-fit-loss is a concept attempting to quantify and estimate the accumulative fit-loss that a population may encounter. This paper reports on a novel method that minimizes the aggregate-fit-loss of a sizing system for bras, through shape categorization and optimized selection of prototypes (which can be regarded as the most appropriate fit models, or standard dress forms) for the categorized groups. A fit-loss function was introduced that calculates the dissimilarity between any two three-dimensional body scans, via pointwise comparisons of the point-to-origin distances of 9000 points on the scan surface. The within-group aggregate-fit-loss is minimized by an algorithm that returns the optimal prototype for the group. The overall aggregate-fit-loss is reduced by breast shape categorization based on the dissimilarities between the scans. Finally, the constraint of band sizes was brought into the categorization to provide a more feasible solution for improved bra sizing. The findings of this study can also contribute to the optimization of sizing systems for other apparel products.

Devising a method to parametrize the jacket style varieties through the modification of tіpological series structures

“…Statistical analysis of the anthropomorphic structure of design is used for the optimized choice of a prototype in shape categories according to aesthetic and functional attributes of the constructive solution of products [6]. The concept of design argumentation is aimed at the targeted management of hypothetical models of the style image of the product from the point of view of typifying the design and manufacturing processes at an enterprise [7].…”

Devising a method for the interactive arrangement of structural elements of men’s jacket models

“…The classification system of optimized selection of prototype categories [19] creates prerequisites for simplifying the parallel encoding method. The use of the method of visual expert evaluation of the design idea of novelty levels of articles in the loop of the fashion life cycle «high -modern -massoutdated» makes it possible to evaluate the production feasibility of the transaction of typical representatives of the shape.…”

Prediction of garment fit level in 3D virtual environment based on artificial neural networks

“…Step 2: In the pattern layer, the relationship between the input vector, x i , and each pattern of the fit level, fl j ð Þ l , is calculated by Euclidean distance following equation (3). The neuron output of the pattern layer is then activated by a radial Gauss function like that of equation (4):…”

“…In the clothing industry, fit is defined as how the garment conforms to the body and how it appears on the body. 3 Compared with other design attributes, such as fashion styles, silhouettes, fabrics, and colors, fit is one of the most significant purchasing criteria for consumers. Unfortunately, the return rate (close to 30%) due to poor garment fit remains high in garment eshopping.…”