Search results

Clothing patterns play a dominant role in costume design and have become an important link in the perception of costume art. Conventional clothing patterns design relies on experienced designers. Although the quality of clothing patterns is very high on conventional design, the input time and output amount ratio is relative low for conventional design. In order to break through the bottleneck of conventional clothing patterns design, this paper proposes a novel way based on generative adversarial network (GAN) model for automatic clothing patterns generation, which not only reduces the dependence of experienced designer, but also improve the input-output ratio.

In view of the fact that clothing patterns have high requirements for global artistic perception and local texture details, this paper improves the conventional GAN model from two aspects: a multi-scales discriminators strategy is introduced to deal with the local texture details; and the self-attention mechanism is introduced to improve the global artistic perception. Therefore, the improved GAN called multi-scales self-attention improved generative adversarial network (MS-SA-GAN) model, which is used for high resolution clothing patterns generation.

To verify the feasibility and effectiveness of the proposed MS-SA-GAN model, a crawler is designed to acquire standard clothing patterns dataset from Baidu pictures, and a comparative experiment is conducted on our designed clothing patterns dataset. In experiments, we have adjusted different parameters of the proposed MS-SA-GAN model, and compared the global artistic perception and local texture details of the generated clothing patterns.

Experimental results have shown that the clothing patterns generated by the proposed MS-SA-GAN model are superior to the conventional algorithms in some local texture detail indexes. In addition, a group of clothing design professionals is invited to evaluate the global artistic perception through a valence-arousal scale. The scale results have shown that the proposed MS-SA-GAN model achieves a better global art perception.

The introduction of clothing pattern cutting systems represented a significant technological and economic breakthrough for the garment designer, as they noticeably reduced the amount of time and skill required to cut a fashionable garment offering an acceptable fit. Many different types of pattern system are currently in use across the world, each being appropriate for specific measurement systems, tailoring methods and for particular types of figure. These pattern-cutting systems have developed to accommodate cultural predilections and diverse preferences in respect of fashion silhouettes. Modern clothing pattern design work is increasingly performed using computer-based pattern-drafting systems. This commonly results in conformance with international designs, with its attendant loss of traditional design cues. An examination has been made of the distinctions between the shapes of clothes created using the English block pattern system and those that result from using the Chinese Proportion Assigned Cutting Method. The analysis shows that English patterns are more closely tailored to the body whilst Chinese patterns offer more freedom of movement. This knowledge should inform the clothing pattern designer, so that appropriate features may be incorporated into drafted patterns in order to facilitate the tailoring of clothing with apposite design characteristics.

The main issue in the mass customization of apparel products is how to efficiently produce products of various sizes. A parametric pattern-making system is one of the notable ways to rectify this issue, but there is a lack of information on the parametric design itself and its application to the apparel industry. This study compares and analyzes three types of parametric clothing pattern CAD (P-CAD) software currently in use to identify the characteristics of each, and suggest a basic guideline for efficient and adaptable P-CAD software in the apparel industry.

This study compared three different types of P-CAD software with different characteristics: SuperALPHA: PLUS(as known as YUKA), GRAFIS and Seamly2D. The authors analyzed the types and management methodologies of each software, according to the three essential components that refer to previous studies about parametric design systems: entities, constraints and parameters.

The results demonstrated the advantages and disadvantages of methodology in terms of three essential components of each software. Based on the results, the authors proposed five strategies for P-CAD development that can be applied to the mass customization of clothing.

This study is meaningful in that it consolidates and organizes information about P-CAD software that has previously been scattered. The framework used in this study has an academic value suggesting guidelines to analyze P-CAD systems.

The final goal of this study is to virtualize draping. Draping which is one of the methods to design paper patterns for clothing requires much labor and time. The sub-goal of this study is to construct a system in which the fundamental functions of draping are equipped.

The system is realized in the virtual world by integrating the virtualized elements of real draping. The cloth is modeled by mechanical formulation, and the shape is determined by numerical calculation. The hand is geometrically modeled, and the captured motions of the hand and fingers are applied to the model. The model dress form is made from the data by measurement. The system in which darts can be made in the virtual space is constructed by integrating the models.

It is confirmed that the cloth model in the virtual world can be manipulated by the motions of the fingers in the real world. And it is suggested that it is possible to design practical paper patterns for clothing by adding functions to the system.

We are aiming at the system to design paper patterns by the movements of the fingers. With this system, it is expected that the efficiency in designing paper patterns is much improved, and it becomes possible to design clothing that fits individuals efficiently.

The purpose of this paper is to investigate the chest girth and height related to men’s upper body dimensions to develop men’s grading system for semi-customized clothing.

A data set of the 3,012 men between the age group of 18 and 59 years from 6th Size Korea was used in this study. The men’s upper body dimensions were tested in terms of five horizontal lengths, seven circumferences and seven vertical lengths. Experiment and data analysis were carried out with two methods: one is multiple linear regression with chest girth and height as each independent variable and the other is calculating variation among chest girth size groups and height size groups, respectively.

Regression analysis showed that some horizontal lengths are affected not only by chest girth, but also by height, and some vertical lengths are affected not only by height, but also by chest girth. In variation analysis it was found that the variation value for each part of the body is different and it was observed that with an increase in chest girth vertical length also increases. In variation analysis of height, it is found that some horizontal body dimensions and hip girth increase with an increase in height. In the comparison of upper body dimension variation among height groups with the size based on the chest girth, we found that a tall person who already has long vertical length is less affected by the increase in dimensions by increases in their horizontal girth than a short person.

The findings showed detailed numerical body shape changes according to chest girth and height, and it may be used as the basis for determining pattern grading values by chest girth or height.

The purpose of this paper is to study online clothing consumers' behaviour and their visual attention mechanism to provide objective and quantitative evidences for the display and sales of online clothing.

Firstly, this paper conducted a Focus Group Methodology and questionnaire survey to obtain concern factors of online clothing. Secondly, the online clothing's bottom-up visual stimulation and consumer's top-down expectations were analysed, and proposed the hypotheses about significant stimulus of clothing and consumer's emotional experience. Thirdly, the online clothing consumer's visual attention rules and related qualitative results were discussed, and proposed visual attention law for online clothing. Finally, took the company's 84th quarter clothing design practices as research projects, all the hypotheses were demonstrated through eye movement physiology experiments, online clothing trial release and node sales data.

Online clothing has unique visual display ways compared with other online products such as online advertising, brands and food packaging. Clothing patterns of unfamiliar (fresh) font shapes are more attractive than the patterns of familiar fonts. The cause of the bottom-up visual attention bias is the contrast between clothing features, not the absolute stimulus intensity of the features themselves. Clothing factors can change their emotional experience from no difference to significant difference under the influence of other clothing factors.

Put forward hypotheses of online clothing consumer behaviour and its visual attention mechanism, provided objective and quantitative evidences through eye tracker.

This study aims to automate the process of converting grading patterns into parametric patterns using artificial intelligence and to objectively evaluate the fitness of the converted patterns.

The developed system consists of a user interface that defines input data by importing multi-size grading patterns, an artificial neural network that learns the relationship between human body size and pattern geometry, and a module that converts training results into parametric patterns. In order to evaluate the fitness of the generated pattern, an objective fitting evaluation method using drape simulation was developed.

The body sizes of the wearer were input to the converted parametric pattern to generate a customized pattern. Resulting pattern showed a better fit than the grading pattern on the off-average body model.

In this study, a method has been developed that enables the users with minimal pattern drafting knowledge to convert grading patterns into parametric patterns using artificial intelligence and drape simulation. The human body's symmetry and the physical properties of fabric were not considered.

The system developed in this study requires less data compared to existing methods that attempt to design clothing patterns with machine learning. In addition, it was possible to evaluate pattern fitness on various body models through drape simulation based fit evaluation process for the first time.

In the trend of individuation and customization, more rapid and flexible clothing pattern production systems are required. Many studies about the system have been done into producing paper pattern automatically for sewing. The purpose of this paper is to propose a novel three‐dimensional intelligent pattern‐making algorithm.

Body features are referenced for crack designing, the concept of functional dividing is proposed on the triangled upper body surface based on Gauss Curvature. A new surface flattening algorithm based on body features (SFABF) is put forward. Robert Hooke Law and Young's modulus are referenced for energy model (EMRY) setting up to define and calculate the edge length variation of triangle. Basing on EMRY, another optimizing surface flattening algorithm (OSFA) is designed to optimize SFABF so as to minimize the accumulated energy.

Shape variation accumulation of flattened pattern can be reduced a lot when the cracks are distributed along functional dividing lines. The points with the largest Gauss Curvature as Bust Point have played a great role in shape variation reduction. Because of textiles' flexibility shape variation need not be reduced to zero. Comparing with the related methods this research is more practical.

To this study, SFABF and OSFA are novel methods to improve practicality. The proposed concept of functional dividing is value to the shape variation reduction from surface flattening.

New techniques are required to link 3D whole body scans to manufacturing techniques to allow for the mass‐customization of clothes. This study aims to compare two methods of producing skirts based on 3D whole body scans.

Three females participated in the study. They were scanned with an accurate 3D whole body scanner. A set of relevant 1D measures was automatically derived from the 3D scan. The measures were incorporated in a skirt pattern and the skirt was made from jeans material. The second method was based on triangulation of the scanned waist‐to‐hip part. The points in the 3D scan were first converted to triangles and these triangles were thereafter merged with neighboring triangles of similar orientation until about 40 triangles remained. These triangles were sewn together to form a “patchwork”‐skirt. All females performed fit tests afterwards.

The fit of the 3D‐generated patchwork skirt was much better than the fit of the skirt generated by the 1D scan‐derived measures. In the latter case, two of the three skirts were too wide because the scan‐derived hip circumference exceeded the manually derived values. For the 3D generated skirt, it was necessary to enlarge the triangles with a factor of 1.025 to achieve optimal fit.

As far as is known, this is the first study that reports a direct conversion of a 3D scan to clothing without interference of clothing patterns. The study shows that it is possible to generate a fitting patchwork skirt based on 3D scans; the intermediate step of using 1D measures derived from 3D scans is shown to be error‐prone.

An exact pattern prototype is a prerequisite for female girdle pattern-making. The purpose of this paper is to develop new ways to make girdle pattern prototypes based on 3D technology.

This paper presented two novel methods for creating girdle pattern prototypes. The first one was the girdle's parametric foundation pattern developing method based on 3D geometric modeling. In this method, considering the different characteristics of a female's lower body shape, several models were created to define the relationship between the female's lower body shape and the pattern, such as a side-waist curvature model, an interior-posterior waist-warping model, a buttocks' parametric model and an abdomen parametric model. Then, parameters of drawing the prototype were abstracted to facilitate transforming the 3D geometric model into the 2D pattern. Another method was implemented by 3D virtual modeling and unwrapping. The whole process included surface division, surface reconstruction and surface unwrapping.

The prototypes created by these two methods were tested using the 3D virtual trying-on examination. Trial tests showed that the patterns can be dressed in the right positions on the virtual model with little pressure. This means that the proportions and shapes of the pattern are correct. The prototypes obtained through the methods proposed in this paper have good effects and high precision. Both methods can be used for making the girdle's foundation pattern.

Two pragmatic approaches of girdle's prototype building have been put forward. The parametric prototype designing method has changed the unconstrained state of free modeling. The pattern structure can be controlled by parameter constraints. In the other method, with 3D scanning and surface modeling technology, personalized girdle's pattern is generated, and the segmentation lines of the girdle can be designed flexibly according to the requirements. These findings also can be used in other tight garments' prototype making.