Search results

To better respond to today’s volatile and changing fashion market, the purpose of this paper is to develop a web-based design support system that enables users to design realistic and interesting skirts in the form of technical sketches over the internet.

The proposed system mainly consists of a sketch representation and composing method (SRCM), a graphic user interface (GUI) and a controller. The SRCM is implemented at the server end that generates technical sketches according to user defined parameters and features via the web-based GUI at the client side. The controller manages the workflows between the server and the clients.

To evaluate the effectiveness of the proposed system, a survey was conducted by inviting 30 subjects (professional designers or undergraduate students studying fashion design) to have trial run of the system in Hong Kong and in the USA. Positive comments and feedbacks were received, and valuable suggestions were also obtained in regard to the prototype system.

Compared with traditional computer-aided design (CAD) systems, the proposed system is more effective and easier to operate as users can create technical sketches in accurate proportions with simple computer operations in a few mouse clicks. Besides, the output sketches are fully compatible with most commercial CAD software. The system is developed based on web technologies, thus fashion sketches can be easily designed using any computer connected to the internet; it can be implemented on Android or iOS platform in the future.

The purpose of this study is to develop an easy-to-use CAD software for fashion flat sketch that can create new sketches by combining the flat sketch modules.

A sample fashion flat module database was constructed by performing a sketch modularization process as well as a morphological analysis. In addition, an automatic module assembling algorithm was developed to create new sketches using the database.

The module assembling algorithm enabled the users to make new fashion flat sketches by the combination of design modules in the database. The example database constructed in this study was composed of bodice, sleeve, collar, cuffs and pocket modules chosen based on the results of a morphological analysis.

A CAD program has been developed that might improve the efficiency of design work by helping the users to make fashion flat sketches more easily.

The automatic module assembling algorithm developed in this study has not been implemented in any existing commercial systems. It is expected that users who do not have expertise in fashion design could be able to participate from the clothing design stage as a mass customization prosumer by using the software.

The purpose of this paper is to study the problem of fashion flat sketches classification and proposed an integrated approach. It aims to propose a fast, reliable method to handle multi-class fashion flat sketches classification problems and lay the foundation for the garment style query in the next step.

The proposed integrated approach adopts wavelet Fourier descriptor (WFD), linear discriminant analysis (LDA) and extreme learning machine (ELM). First, the discrete wavelet and Fourier transform are adopted to extract the shape features of fashion flat sketches. Then, LDA is employed for multi-class classification to reduce dimensionality. Finally, ELM is used as the classifier.

The experimental results show that the classification accuracy of the integrated approach is obtained at about 100 percent. Contrary to the traditional approaches, efficiency and accuracy are the advantages of the present approach.

Fashion concept is conveyed often in the form of the fashion illustration or sketch. This type of sketch is useful to imply the style and overall feel of the design. However, this sketch gives no clue about the parts or sections that make up each garment. For this reason, this paper only studies the classification of flat sketches.

A new shape descriptor named WFD is proposed. The WFD acquires high classification accuracy comparing with Fourier descriptor (FD) and multiscale Fourier descriptor (MFD) without dimensionality reduction and nearly the same classification accuracy comparing with FD while MFD easily causes small sample size problem with dimensionality reduction using LDA. In addition, ELM is first used as the classifier in the textiles field related to the classification problem.

In this study, a methodology integrating a sketch design recognition approach with an interactive genetic algorithm is proposed to help laypersons get clothes reflecting their preferences. The sketch design recognition approach consists of a composite description model, a sketch recognition method and a database. First, a composite description model based on the knowledge of fashion design is developed to describe the characteristics of a skirt. Second, a sketch recognition method is used to help laypersons get satisfactory clothes. Third, a database in constructed to record general elements of skirts. Moreover, an interactive genetic algorithm (IGA) is used to accelerate the sketch recognition process. The experimental results demonstrate that the proposed method can 'recognize' users' preferred styles efficiently. The subjective evaluation has shown that the system can help general consumers without any fashion design or sketch training to create their own designs.

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 purpose of this paper is to build a mathematical model of men’s wear prototype, so that the computer can draw men’s wear prototype automatically.

First, the bust line, front and back center line, waist line, side seam, front chest width and back width line in the coordinate system are expressed by equations. Then, a parabola is used to establish a neckline curve, a linear equation is used to establish a shoulder oblique line, and a double ellipse is superposed to construct the armhole arc. Finally, all the garment prototype curves are built mathematical models.

The result shows that every curve of garment prototype can be expressed approximately by mathematical model.

This research lays the foundation for the automation and intelligence of garment pattern-making.

The main purpose is to construct the mapping relationship between garment flat and pattern. Particle swarm optimization–least-squares support vector machine (PSO-LSSVM), the data-driven model, is proposed for predicting the pattern design dimensions based on small sample sizes by digitizing the experience of the patternmakers.

For this purpose, the sleeve components were automatically localized and segmented from the garment flat by the Mask R-CNN. The sleeve flat measurements were extracted by the Douglas–Peucker algorithm. Then, the PSO algorithm was used to optimize the LSSVM parameters. PSO-LSSVM was trained by utilizing the experience of patternmakers.

The experimental results demonstrated that the PSO-LSSVM model can effectively improve the generation ability and prediction accuracy in pattern design dimensions, even with small sample sizes. The mean square error could reach 1.057 ± 0.06. The fluctuation range of absolute error was smaller than the others such as pure LSSVM, backpropagation and radial basis function prediction models.

By constructing the mapping relationship between sleeve flat and pattern, the problems of the garment flat objective recognition and pattern design dimensions accurate prediction were solved. Meanwhile, the proposed method overcomes the problem that the parameters are determined by PSO rather than empirically. This framework could be extended to other garment components.

While much is made of the contribution of design to the achievement of competitive advantage within the British fashion retail sector, little attempt has been made to examine the processes in which design is managed, integrated and developed within such companies. With the cooperation of 11 of the UK's most successful fashion retailers, this research identifies that the responsibility for design direction and development has moved from supplier to fashion retailer, in order that the latter can fully exploit and protect the opportunities afforded to them through own‐branding. Suggesting that design control affords greater supply chain control, the research also provides a valuable insight into the varying roles and responsibilities of the designer as well as the differing ways in which the design function is managed by fashion retailers. In addition, the research identifies that for some of the most successful fashion retailers, the contribution of the designer has been extended and his or her creativity incorporated into areas of decision making not traditionally associated with that of the fashion designer.

To improve the apparel e-customized system and meet consumers’ personalized requirement in the e-customization, the purpose of this paper is to develop an e-customized co-design system on garment design (ECS-GD) that enables users to co-design garment and communicate with stakeholders.

The e-customized co-design system mainly consists of function and modular structure, communication and evaluation modular. Based on the evolutionary algorithm and fuzzy theory, the e-customized system model is proposed with a presentation of garment interface. Based on the parameters of skirts, technical sketches, fabrics, color, patterns, comments and scores, the decision is made by consumers.

For the system to be effective, the system was conducted by multi-individuals co-work (consumers, designers, manufacturers and experts). The data flow was congruent to the design knowledge. The expert evaluation and communication were involved in the proposed system.

The limitation of this study is that the system is not tested in experiments. The model, main function and data flow are proposed in this study, which is important in the e-customized co-design system development.

Compared to the e-shopping and garment recommendation, the proposed ECS-GD is a good approach to improve the existing e-customized system and a well solution to help consumers with design knowledge recommending, professional suggestions and evaluations. Besides, the sketches and knowledge recommendation are provided to consumers which is a learning process.

The purpose of this paper is, first, to examine the design requirements of Islamic fashion in the new product-development process; second, to explore the different practices of new product-development activities from successful and unsuccessful new product lines; and third, to investigate the sequence of the new product-development practice in the fashion industry, specifically the Islamic fashion industry in Indonesia.

Questionnaires were distributed and semi-structured interviews were conducted to collect information regarding the practice of the new product-development activities. The Mann–Whitney U test was performed based on the quality of the new product-development activities of 100 Islamic fashion firms, including five innovative companies that had won several awards in Indonesia. An analysis of the extent to which fashion firms were engaging in new product-development activities provided a more detailed picture of the sequence of those activities.

Islamic norms were adapted during the early design and promotional phases of new product development in Islamic fashion. Various choices of design and colour in Islamic fashion were also perceived as a way of preaching to women to dress more accordingly to the Islamic norm. The new product-development activities that were conducted differently for successful vs unsuccessful new product lines were idea conceptualisation, market analysis, technical and engineering analysis, financial analysis and commercialisation. The commercialisation phase was given the least priority of all the activities. Nevertheless, it contributed to the very first communication to the customers about new product lines.

This study makes an important contribution to the deeper and more detailed research on how Islamic fashion companies perceive Islamic values during new product developments and how they perform new product-development activities between successful and unsuccessful products.