Seo Hyo Kim, Sungmin Kim and Chang Kyu Park
The purpose of this paper is to develop a similarity evaluation method between virtual and actual clothing.
Abstract
Purpose
The purpose of this paper is to develop a similarity evaluation method between virtual and actual clothing.
Design/methodology/approach
The paper analyzes the subjective and objective evaluation results of virtual and actual clothing.
Findings
In this paper, significant factors affecting the evaluation of similarity between actual and virtual clothing have been found.
Research limitations/implications
Evaluation experiment was performed only for a skirt. However, the method can be easily applied for other types of garments.
Practical implications
The evaluation of similarity between actual and virtual garment will be facilitated.
Social implications
The garment design process can be facilitated by simulating garments in virtual space.
Originality/value
There has not been any quantitative evaluation method for the similarity of virtual and actual garment.
Details
Keywords
Gwang Han Lee, Sungmin Kim and Chang Kyu Park
The purpose of this study is to solve the cold start problem caused by the lack of evaluation information about the products.
Abstract
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.
Details
Keywords
Chang Kyu Park, Dae Hoon Lee and Tae Jin Kang
Focuses on Korean garment manufacturing and the feasibility and benefits of introducing an expert system. Reviews previous literature on knowledge‐based system and describes in…
Abstract
Focuses on Korean garment manufacturing and the feasibility and benefits of introducing an expert system. Reviews previous literature on knowledge‐based system and describes in detail the stages followed in developing, constructing, testing, evaluating, integrating, implementing and maintaining the expert system. Concludes that an expert system could be used to solve various garment manufacturing problems and would contribute to garment quality improvement through a standardized apparel production process.
Details
Keywords
Choong Hyo Kim, In Hwan Sul, Chang Kyu Park and Sungmin Kim
The purpose of this paper is to illustrate the generation of basic garment pattern using three‐dimensional body measurement data.
Abstract
Purpose
The purpose of this paper is to illustrate the generation of basic garment pattern using three‐dimensional body measurement data.
Design/methodology/approach
A pre‐defined garment model is deformed using free‐form deformation method and the model is flattened to generate flat patterns.
Findings
The paper finds that individual basic garment patterns are automatically generated and verified to be well fit on human subjects.
Research limitations/implications
The current approach is to focus on the generation of basic bodice patterns; however, other patterns can also be generated by this method by preparing more garment models.
Practical implications
This method can reduce the time required to design basic patterns as well as enhance their fitness.
Originality/value
The automatic generation of individually fitted garment pattern is one of the most important steps in future garment production process.
Details
Keywords
Sungmin Kim and Chang Kyu Park
The generation of individually fit basic garment pattern is one of the most important steps in the garment‐manufacturing process. This paper seeks to present a new methodology to…
Abstract
Purpose
The generation of individually fit basic garment pattern is one of the most important steps in the garment‐manufacturing process. This paper seeks to present a new methodology to generate basic patterns of various sizes and styles using three‐dimensional geometric modeling method.
Design/methodology/approach
The geometry of a garment is divided into fit zone and fashion zone. The geometry of fit zone is prepared from 3D body scan data and can be resized parametrically. The fashion zone is modeled using various parameters characterizing the aesthetic appearance of garments. Finally, the 3D garment model is projected into corresponding flat panels considering the physical properties of the base material as well as the producibility of the garment.
Findings
The main findings were geometric modeling and flat pattern generation method for various garments.
Originality/value
Parametrically deformable garment models enable the design of garments with various size and silhouette so that designers can obtain flat patterns of complex garments before actually making them. Also the number and direction of darts can be determined automatically considering the physical property of fabric.
Details
Keywords
Hyun-Sook Han, Sungmin Kim and Chang Kyu Park
– The purpose of this paper is to develop an automated custom-pattern-making system using the width-height independent grading method for semi-customized clothing.
Abstract
Purpose
The purpose of this paper is to develop an automated custom-pattern-making system using the width-height independent grading method for semi-customized clothing.
Design/methodology/approach
The system reads basic patterns and graded large patterns and calculates the grading ratio of independent horizontal and vertical values on all points in a pattern. The custom pattern is automatically generated by calculating the horizontal and vertical grading amount according to individual body measurements. The system does not follow any complicated alteration rules.
Findings
The width-height independent grading method can provide custom-pattern fitted primary body circumference and length and helps to quickly produce semi-customized clothing.
Originality/value
There are few studies on automated custom-pattern-making systems without an alteration rule. This study developed an automatic custom-pattern-making system using the width-height independent grading method.
Details
Keywords
Chang Kyu Park, Dae Hoon Lee and Tae Jin Kang
The AATCC grades of seam pucker do not provide sufficient information for analysing and solving the problems. Develops a new measurement system which redefines seam pucker with…
Abstract
The AATCC grades of seam pucker do not provide sufficient information for analysing and solving the problems. Develops a new measurement system which redefines seam pucker with shape parameters and evaluates it using artificial intelligence. New standards of seam pucker with five shape parameters were developed. Shows that prediction and optimization for seam pucker are possible using these means. The system has already been employed in men’s suit manufacture.
Details
Keywords
Examines the fifthteenth published year of the ITCRR. Runs the whole gamut of textile innovation, research and testing, some of which investigates hitherto untouched aspects…
Abstract
Examines the fifthteenth published year of the ITCRR. Runs the whole gamut of textile innovation, research and testing, some of which investigates hitherto untouched aspects. Subjects discussed include cotton fabric processing, asbestos substitutes, textile adjuncts to cardiovascular surgery, wet textile processes, hand evaluation, nanotechnology, thermoplastic composites, robotic ironing, protective clothing (agricultural and industrial), ecological aspects of fibre properties – to name but a few! There would appear to be no limit to the future potential for textile applications.
Details
Keywords
Beth McGee, Xu Jin, Nam-Kyu Park, Skylar Ball and April Carr
The Biophilic Interior Design Matrix (BID-M) was created to assist designers with identifying biophilic interior design features for optimizing nature integration for…
Abstract
Purpose
The Biophilic Interior Design Matrix (BID-M) was created to assist designers with identifying biophilic interior design features for optimizing nature integration for evidence-based design. The BID-M was developed and tested with interior design practitioners in the United States. There was a need to further develop the BID-M for other cultures along with understanding the designers' perceptions of biophilia.
Design/methodology/approach
A mixed methods approach was used with 101 interior designers/architects practicing in China using a pre- and post-questionnaire surrounding a room assessment using the BID-M.
Findings
The Chinese translation of the BID-M was perceived as beneficial to design practice, evaluated as reliable and valid. The Chinese designers perceived a significant increase in knowledge and importance of biophilia after using the BID-M and it was useful in assisting all parts of the design process. The designers had some prior experience with biophilic design and clients have been requesting suitable natural and artificial light features.
Practical implications
The BID-M was seen as a human centered design tool that is useful to evaluate biophilic design features in the built environment.
Originality/value
Overall, the BID-M appears to be useful throughout the design process to ultimately support well-being. The participants' cultural background expands use of the BID-M and provides opportunities for additional cultural applications of biophilic design and future research. The BID-M offers additional language for incorporating biophilic design as well as serving to educate and guide feature selection.