Content uploaded by Alfredo Ballester
Author content
All content in this area was uploaded by Alfredo Ballester on Feb 10, 2015
Content may be subject to copyright.
A preview of the PDF is not available
Exploitation of 3D Body Databases for the Apparel Industry
Abstract and Figures
Nowadays each clothing company defines its own sizing chart to label the garment. The lack of regulations and the different labelling methods used on each country contribute to have a confusing buying process for the end users in terms of garment size selection. Depending on the brand, the customer selection can vary several sizes. This makes that customers need to try on many sizes to select the suitable one during the buying process. This is one of the main barriers to the growth of the online sales in the fashion market. The high number of returns and their associated costs (e.g. management, logistics and operations) represent an important economic burden for fashion companies.
The aim of the this paper is to present a proposal of new methods for the development size selection systems based on a 3D body acquisition process using 3D body reconstruction and a multi-fitting approach to predict garment size.
Figures - uploaded by Alfredo Ballester
Author content
All figure content in this area was uploaded by Alfredo Ballester
Content may be subject to copyright.
... Getting the right size without trying the clothes on is a challenge [1] that every parent faces whenever they intend to buy clothing for their children, either online or at brick-and-mortar stores. Children's sizing has the particularity of being designed based on statures but being labelled according to age (i.e. ...
... Kidsize provides size advice (expert's and parents') and fit predictions from a set of body measurements of the child and the properties of the garment (figure 3). In order to model and explain the child-garment interaction we used Ordinal Logistic Regression (OLR) with stepwise variable selection and a set of expert rules using an adaptation of the methods proposed by Alemany et al. [1]. ...
... The reliability of the size advices provided by Kidsize showed a similar performance than previous studies conducted with adult female garments (86-93%) using also OLR for modelling the user-garment try-on interaction [1]. The performance results obtained by unidimensional size guides (stature-or age-based) in this study (48-59%) are also similar to those obtained by tri-dimensional size guides (bust-waist-hip) used in the female study (41-64%). ...
... To select the best features and to estimate the best coefficients for each shoe model, stepwise method was used. IBV has already used logistic regression models to tackle this problem successfully in clothing [19], [20]. In this project, we also used data projection to bring all the observations to a single size by upscaling and downscaling the foot features characterizing each foot, making it work in all available sizes. ...
... The two models that showed a fit tolerance below 70% were models with fit issues that probably affected the size choices of the subjects. These results are in line with similar systems using logistic regressions to recommend sizes [19], [20] and provides better results than just picking the usual size (55-60%) or using the brand's size chat using foot length (45-55%). ...
... Despite the potential benefits that individual 3D information may bring to the e-commerce (off-the-shelf and made-to-measure orders) of wearable products, 3D body scanners have not yet been widely used as consumer goods or as typical in-store appliances in small brick-andmortar retail outlets because of their cost, which is beyond the price of the most common home appliances, the dedicated space they need, which is typically more than 2x2x2m, and, in the case of off-the-shelf products, due to the lack of reliable product size guides and prediction software (Alemany et al., 2013). ...
The advances and availability of technologies for the acquisition, registration and analysis of the three-dimensional (3D) shape of human bodies (or body parts) are resulting in the formation of large databases of parameterised meshes from which digital human body models can be derived. Such models can be used for the data-driven reconstruction of parameterised human body shapes from partial information such as one-dimensional (1D) measurements or 2D images. In this paper, we propose a new method for the reconstruction of 3D bodies from images gathered with a smartphone or tablet. Moreover, the method is implemented into a prototype app and tested at different levels through three experimental studies including synthetic models, 1:10 scale figurines and real children. The results demonstrate the feasibility of acquiring reliable anthropometric information easily at home by non-experts. This method and implementation have great potential for their application to the personalisation, size recommendation and virtual try-on simulation of wearable products.
... (1) Pre-selection of measures to be included in the statistical models based on previous research (Alemany et al. 2013) and the opinion of the experts. ...
Mass-customization of wearable products are offered as a higher added value to the broad public and have to compete with ready-to-wear offer. However, people with specific requirements are not covered by the current mass-customised products. This is the case of the elderly, disabled, diabetic and obese population groups when wearing textiles, clothing, footwear and textile-based orthotic goods. Further, at present, available knowledge and flexibility of production equipment and machinery of small and medium-sized enterprises operating in these traditional industries (even those that already offer made-to-measure products to the mass public) is unable to respond to the individual needs among such heterogeneous groups. The FASHION-ABLE project has solved this problem with a comprehensive set of solutions.
... The template structure used by IBV was developed under the EUROFIT project [1,2,3]. It is constituted by a single closed mesh surface made up of 49.530 vertices, 99.056 triangle faces and a 17-bone and 14-joint skeleton as depicted in Figure 2 [4]. ...
Today, there is an increasing availability of human body 3D data and an increasing number of anthropometric owners. This is due to the fact of the progressive conduction of large national surveys using high resolution 3D scanners and due to the increasing number of low-cost technologies for acquiring body shape with electronic consumer devices like webcams, smartphones or Kinect. However, the commercial use and exploitation in industry of digital anthropometric data is still limited to the use of 1D measurements extracted from this vast 3D information. There is a lack of universal resources enabling: to conjointly use and analyse datasets regardless from the source or type of scanning technology used, the flexible measurement extraction beyond pre-defined sets, and the analysis of the information contained in human shapes. This paper presents four software tool solutions aimed at addressing different user profiles and needs regarding the use and exploitation of the increasing number of 3D anthropometric data
This paper attempts to estimate a 3D shape of human torso from 2 pictures which are front and side silhouette of a subject. Our method assumes that input pictures have accurate contours of a subject's body. And regions of torsos are extracted manually from input pictures. We use a deformable body model for estimation. This model is generated by principal component analysis to a homologous model database which is made of whole body scanned data. A result shape is computed by optimizing some deformation parameters of the model with comparing model's silhouettes and input silhouettes.
Recently, researches and developments for measuring and modeling of the human body have been receiving much attention. Our aim is to reconstruct an accurate shape of a human foot from multiple camera images, which can capture dynamic behavior of the object. In this paper, a foot-shape database is used for accurate reconstruction of human foot. By using Principal Component Analysis, the foot shape can be represented with new meaningful variables. The dimensionality of the data is also reduced. Thus, the shape of object can be recovered efficiently, even though the object is partially occluded in some input views. To demonstrate the proposed method, two kinds of experiments are presented: reconstruction of human foot in a virtual reality environment with CG multi-camera images, and in real world with eight CCD cameras. In the experiments, the reconstructed shape error with our method is around 2 mm in average, while the error is more than 4 mm with conventional volume intersection method.
This paper describes how size-specific analyses of body scan data of an apparel company's target market can provide information that can be used to adjust ready-to -wear sizing to improve apparel fit. We describe a variety of size-based statistical and visual analysis methods that can be applied to target market body scan data. These analyses begin to describe and address the variety of body shapes and measurements that exist within a sizing system and identify potential design adjustments that could be made in order to increase the percent of acceptable fit within each size category for a target market.
In this paper, we demonstrate a system for synthesizing high-resolution, realistic 3D human body shapes according to user-specified anthropometric parameters. We begin with a corpus of whole-body 3D laser range scans of 250 different people. For each scan, we warp a common template mesh to fit each scanned shape, thereby creating a one-to-one vertex correspondence between each of the example body shapes. Once we have a common surface representation for each example, we then use principal component analysis to reduce the data storage requirements. The final step is to relate the variation of body shape with concrete parameters, such as body circumferences, point-to-point measurements, etc. These parameters can then be used as "sliders" to synthesize new individuals with the required attributes, or to edit the attributes of scanned individuals.
PLS-regression (PLSR) is the PLS approach in its simplest, and in chemistry and technology, most used form (two-block predictive PLS). PLSR is a method for relating two data matrices, X and Y, by a linear multivariate model, but goes beyond traditional regression in that it models also the structure of X and Y. PLSR derives its usefulness from its ability to analyze data with many, noisy, collinear, and even incomplete variables in both X and Y. PLSR has the desirable property that the precision of the model parameters improves with the increasing number of relevant variables and observations.This article reviews PLSR as it has developed to become a standard tool in chemometrics and used in chemistry and engineering. The underlying model and its assumptions are discussed, and commonly used diagnostics are reviewed together with the interpretation of resulting parameters.Two examples are used as illustrations: First, a Quantitative Structure–Activity Relationship (QSAR)/Quantitative Structure–Property Relationship (QSPR) data set of peptides is used to outline how to develop, interpret and refine a PLSR model. Second, a data set from the manufacturing of recycled paper is analyzed to illustrate time series modelling of process data by means of PLSR and time-lagged X-variables.
We show that surface reconstruction from oriented points can be cast as a spatial Poisson problem. This Poisson formulation considers all the points at once, without resorting to heuristic spatial partitioning or blending, and is therefore highly resilient to data noise. Unlike radial basis function schemes, our Poisson approach allows a hierarchy of locally supported basis functions, and therefore the solution reduces to a well conditioned sparse linear system. We describe a spatially adaptive multiscale algorithm whose time and space complexities are pro- portional to the size of the reconstructed model. Experimenting with publicly available scan data, we demonstrate reconstruction of surfaces with greater detail than previously achievable.
We describe a method for filling holes in unstructured triangular meshes. The resulting patching meshes interpolate the shape and density of the surrounding mesh. Our methods work with arbitrary holes in oriented connected manifold meshes. The steps in filling a hole include boundary identification, hole triangulation, refinement, and fairing.
We develop a novel method for fitting high-resolution template meshes to detailed human body range scans with sparse 3D markers. We formulate an optimization problem in which the degrees of freedom are an affine transformation at each template vertex. The objective function is a weighted combination of three measures: proximity of transformed vertices to the range data, similarity between neighboring transformations, and proximity of sparse markers at corresponding locations on the template and target surface. We solve for the transformations with a non-linear optimizer, run at two resolutions to speed convergence. We demonstrate reconstruction and consistent parameterization of 250 human body models. With this parameterized set, we explore a variety of applications for human body modeling, including: morphing, texture transfer, statistical analysis of shape, model fitting from sparse markers, feature analysis to modify multiple correlated parameters (such as the weight and height of an individual), and transfer of surface detail and animation controls from a template to fitted models.
Medical applications
- N D'apuzzo
- H Luv
D'Apuzzo, N. and Luv, H., (2009): "Medical applications", Proceedings of 3D-Meas 2009, Rome,
Milan, pp. 44-50.
Filling holes in meshes Eurographics Association
- P Liepa
Liepa, P. (2003, June). Filling holes in meshes. In Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on Geometry processing (pp. 200-205). Eurographics Association