Search Results (80)

Pose transfer methods often struggle to simultaneously preserve fine-grained clothing textures and facial details, especially under large pose variations. To address these limitations, we propose a model based on the Multi-scale attention guided pose transfer model, with modifications to its residual block by integrating the convolutional block attention module and changing the activation function from ReLU to Mish to capture more features related to clothing and skin color. Additionally, as the generated images had facial features differing from the original image, we propose two different facial feature loss functions to help the model learn more precise image features. According to the experimental results, the proposed method demonstrates superior performance compared to the Multi-scale Attention Guided Pose Transfer (MAGPT) on the DeepFashion dataset, achieving a 3.41% reduction in FID, a 0.65% improvement in SSIM, a 2% decrease in LPIPS, and a 2.7% decrease in LPIPS. Ultimately, only one reference image is required to enable users to transform into different action videos with the proposed system architecture. Full article

The significant waste generated by the fashion industry necessitates sustainable textile recycling strategies. Polyester, made from poly(ethylene terephthalate) (PET), is abundant in post-consumer textiles. Technologies have been developed to convert low-density garment waste into flakes, but the role of color sorting in achieving uniform aesthetics in injection-moldable plastics remains underexplored. This study compares materials extruded from dark color-sorted polyester garment flakes with those from light-color flakes in terms of processability in extrusion and injection molding. The properties examined include melt fluidity, injection molding shrinkage, and mechanical and thermal properties. Commercial chain extenders with anhydride, oxazoline, or epoxide reactive groups were added during extrusion. Interestingly, only dark-colored extruded pellets showed significant degradation, but all the chain extenders allowed melt fluidity to be controlled during reprocessing. The bisoxazoline-based additive was the most promising, due to the highly improved ductility of the samples, regardless of whether they were dark-colored or light-colored. The results indicate significant potential for the industrial recycling of post-consumer textiles and highlight the industrial feasibility of repurposing post-consumer polyester garments. This approach not only supports initiatives of circular economy but also offers a viable solution for managing textile waste, particularly in the fashion industry. Additionally, the suggested recycling route combats the production of microplastics. Full article

In this paper, a comparative analysis of historical and contemporary fashion designs was conducted using quantitative methods and indices. Elements such as silhouettes, color palettes, and structural characteristics were analyzed in order to identify models for reinterpretation of classic fashion costume. Clothing from four historical periods was studied: Empire, Romanticism, the Victorian era, and Art Nouveau. An image processing algorithm was proposed, through which data on the shapes and colors of historical and contemporary clothing were obtained from digital color images. The most informative of the shape and color indices of contemporary and historical clothing were selected using the RReliefF, FSRNCA, and SFCPP methods. The feature vectors were reduced using the latent variable and t-SNE methods. The obtained data were used to group the clothing according to historical periods. Using Euclidean distances, the relationship between clothing by contemporary designers and the elements of the historical costume used by them was determined. These results were used to create an educational and methodological framework for practical training of students in the field of fashion design. The results of this work can help contemporary designers in interpreting and integrating elements of historical fashion into their collections, adapting them to the needs and preferences of consumers. Full article

At present, the integration of cultural and emotional aspects in interior designs is considered to be crucial. The combined emotional and new Chinese decorative style effects of interior spaces have not been examined adequately in previous studies. Thus, this study focuses on the role of new Chinese decorative elements in influencing emotional aspects within the context of interior design in China. To fulfil this aim, a qualitative approach was utilized. For this purpose, the data is gathered in two phases. In phase I, semi-structured interviews were utilized to collect data from 5 interior designers. In phase II, data was collected from a focus group discussion with 6 experts. Nvivo 12 software was used for conducting a thematic analysis of the collected transcripts within the context of interview strategy. However, for focus group discussion, content analysis was conducted. The findings from five interior designers showed that emotional aspects in interior designs are impacted by cultural elements. Moreover, numerous challenges in interior design can be overcome by the integration of emotional strategies. The results have shown that the emotional and cultural aspects are crucial for the development of creative interior spaces. Three levels of emotional design have been identified from focus group discussion. Visual aesthetic level comprises of novelty, color conformity, order and sequence, and richness of design. Three main functional levels are usability, comfort, and privacy. Individual level consists of culture, personalization, and fashion elements. Therefore, this study can be effective in promoting the development of creative interior spaces with a comprehensive focus on the levels of emotional design in the context of the new Chinese decorative style. Full article

Written accounts of cultural festivals often deal with the various activities that comprise those types of events. There is a paucity of analyses that discuss how festivals encourage the status quo of consumption practices, while conjuring their hidden costs on society. This paper analyses how the Hamburg Cruise Days Festival attempted to perpetuate the status quo of the cruising industry. The research answers the following question: What would it take to help change the current “cobalt” color promoted by the organizers of the Hamburg’s Waterfront Cruise Days Festival to a “True Blue”, a symbol of the cleanest sky and harbor waters in Germany, and the best example of sustainable Green and Blue Infrastructure in Europe? The research methods comprised in loco fieldwork participant observation in the tradition of participatory action research. It is argued that, from a governance perspective, festival organizers ought to be required to disclaim, in the fashion of “truth in advertising”, the ecological impacts and sponsors’ progress toward reaching existing environmental standards to eradicate costly social and environmental injustices. Said practice will increase our individual and collective awareness of the invaluable richness of the world’s land- and water-based environment before it is irreplaceably exhausted. The article suggests extending events’ emphasis on sustainable tourism to also encompass three additional measures: (i) the socio-ecological performance of the cruise (and shipping) industry; (ii) in the fashion of a Solomonic approach to justice; and (iii) within a formalized Porto of Call Sister Cities Network. Full article

Organic light-emitting diode (OLED) technology has rapidly emerged in the display and lighting sectors due to its high contrast ratio, wide viewing angle, and sleek design. Beyond these attributes, OLEDs have also demonstrated crucial applications in medicine, fashion, sports, and more, leveraging their emissive properties and flexible design. As the cornerstone of full-color displays, blue OLEDs, whose performance directly impacts color rendition and saturation, have garnered significant attention from both scientific researchers and industrial practitioners. Despite the numerous advantages of OLED technology, blue OLEDs still confront formidable challenges in terms of luminous efficiency, durability, and material stability. This review examines the evolution of blue OLED materials over recent years, specifically focusing on three generations: fluorescent, phosphorescent, and thermally activated delayed fluorescence (TADF). Through molecular design, device structure optimization, and the application of innovative technologies, remarkable advancements have been achieved in enhancing the luminous efficiency, lifetime, and color purity of blue OLEDs. However, to advance commercialization, future efforts must not only ensure high efficiency and long lifetime but also improve material stability, environmental sustainability, and reduce development costs. Emerging materials such as thermally activated exciton materials and the application of hyperfluorescent (HF) OLED technology represent vital driving forces for the continuous advancement of blue OLED technology. It is anticipated that significant milestones will continue to be achieved in the development of highly efficient blue OLEDs in the future. Full article

To achieve the color matching rules for the textiles discovered during Silk Road excavations between the 4th and 8th centuries, this research proposed an image-based matching network modeling method. The Silk Road facilitated trade and cultural exchange between the East and West, and the textiles found along the way depict the development of fabrics in a color scheme with great cultural significance. A total of 165 images with brocade patterns were collected from a book with a detailed description of the Western influences on textiles along the Silk Road. Two different clustering methods, including the K-means clustering method and octree quantization approach, were used to extract the primary and secondary colors. By combining the HSV color space with the PCCS color system, the color distribution was analyzed to discover the features of representative color patterns. The co-occurrence relationship of the auxiliary colors was explored using the Apriori algorithm, and a total of eight association rules were established. The results showed that the K-means clustering algorithm can show a better effect of color classification to obtain three primary colors and nine secondary colors. The matching mechanism with a visualized network model was also proposed, which showed that reddish-yellow tones are the main colors in the brocade patterns, and the light and soft tones separately account for 27% and 20%. Beige and brown are the most common colorways, with a confidence level of 47%. One style of brocade pattern was used to demonstrate different appearances within various color networks, which could be applied to 3D virtual fitting. This image-based matching network modeling approach makes the color matching schemes visible, and can assist fashion design with fabric features influenced by historical and cultural development. Full article

Digital technology has changed every process of the fashion industry significantly. Using big data analysis methods such as text-mining, network, CONCOR, and content analyses, this study aims to understand the impact of digital technology trends from the fashion design perspective. The influence of digital technology on fashion design elements (e.g., color, print and graphic, textiles, and style and details) was evident through various keywords related to digital technology, humans, and nature, and the relationships between these keywords were confirmed. The analysis of the implicit meanings and directions of the derived keywords resulted in four clusters: (1) human- and nature-oriented design in the digital world as a new reality; (2) new textiles reflecting digital technology; (3) sustainable design technology; and (4) new utility fashion in the digital space. This study proposed a new design research methodology in which big data were incorporated and could be applied to educational curricula, allowing students to derive practical design elements through big data analysis and serving as a guide for planning and developing technology-inspired designs. Practically, it provided specific information on the direction of digital-technology-inspired fashion design trends, which could assist fashion designers and aspiring entrepreneurs in planning. Full article

With the improvement of the energy density and sensing accuracy of wearable devices, there is increasing interest in applying wearable electronics in daily life. However, traditional rigid plate-structured wearable devices cannot meet the human body’s wearing habits and make users may feel uncomfortable after wearing them for a long time. Fabric-type wearable electronics can be conformably coated on human skin without discomfort from mismatches in mechanical properties between the human body and electronics. Although state-of-the-art textile-based wearable devices have shown unique advantages in the field of e-textiles, real-world scenarios often involve stretching, bending, and wetting. Further efforts should be made to achieve “comfortable wearing” due to the great challenge of achieving both promising electrical properties and comfort in a single device. This review presents a comprehensive overview of the advances in smart fabric-based wearable electronics toward comfortable wearing, emphasizing their stretchability, hydrophobicity, air permeability, stability, and color-change abilities. Through addressing the challenges that persist in fabric-type wearable electronics, we are optimistic that these will be soon ubiquitous in our daily lives, offering exceptionally comfortable wearing experiences for health monitoring, sports performance tracking, and even fashion, paving the way for a more comfortable and technologically advanced future. Full article

In the ever-expanding online fashion market, businesses in the clothing sales sector are presented with substantial growth opportunities. To utilize this potential, it is crucial to implement effective methods for accurately identifying clothing items. This entails a deep understanding of customer preferences, niche markets, tailored sales strategies, and an improved user experience. Artificial intelligence (AI) systems that can recognize and categorize clothing items play a crucial role in achieving these objectives, empowering businesses to boost sales and gain valuable customer insights. However, the challenge lies in accurately classifying diverse attire items in a rapidly evolving fashion landscape. Variations in styles, colors, and patterns make it difficult to consistently categorize clothing. Additionally, the quality of images provided by users varies widely, and background clutter can further complicate the task of accurate classification. Existing systems may struggle to provide the level of accuracy needed to meet customer expectations. To address these challenges, a meticulous dataset preparation process is essential. This includes careful data organization, the application of background removal techniques such as the GrabCut Algorithm, and resizing images for uniformity. The proposed solution involves a hybrid approach, combining the strengths of the ResNet152 and EfficientNetB7 architectures. This fusion of techniques aims to create a classification system capable of reliably distinguishing between various clothing items. The key innovation in this study is the development of a Two-Objective Learning model that leverages the capabilities of both ResNet152 and EfficientNetB7 architectures. This fusion approach enhances the accuracy of clothing item classification. The meticulously prepared dataset serves as the foundation for this model, ensuring that it can handle diverse clothing items effectively. The proposed methodology promises a novel approach to image identification and feature extraction, leading to impressive classification accuracy of 94%, coupled with stability and robustness. Full article

The application of augmented reality (AR) in the beauty and hairdressing industry provides customers with a rich experience, especially in terms of virtual hair styling. Through virtual hair color tests, customers can quickly decide on the most suitable hair dye for them. Teenagers use multimedia communication channels to distinctively express their enjoyment of and aesthetic experiences with the interactive, emotional, and spatial aspects of AR. They can also preview diverse hair dyes and hairstyles in a virtual environment and, ultimately, select the option that suits them the most. This study applied the Stimulus–Organism–Response (S–O–R) theoretical framework and collected 337 valid samples through a SmartPLS-4-supported questionnaire survey for analysis. The results revealed that spatiality significantly influenced behavioral intention in the context of aesthetic experiences, whereas interactivity significantly influenced behavioral intention in the context of entertainment experiences. Overall, the hair dye consumption behavior of Taiwanese teenagers was positively influenced by spatiality and interactivity, and the overall model was well structured. The findings of this study can serve as a reference for businesses to develop innovative technology products that enhance consumer marketing experiences and can contribute to the future development of the hair dye segment of the fashion industry. Full article

Additive manufacturing (AM), also known as three-dimensional printing (3DP), has been widely applied to various fields and industries, including automotive, healthcare, and rapid prototyping. This study evaluates the effects of 3DP on textile properties. The usability of a textile and its durability are determined by its strength, washability, colorfastness to light, and abrasion resistance, among other traits, which may be impacted by the application of 3DP on the fabric’s surface. This study examines the application of photosensitive acrylic resin on two fabric substrates: 100% cotton and 100% polyester white woven fabrics made of yarns with staple fibers. A simple alphanumeric text was translated into braille and the braille dots were 3D printed onto both fabrics. The color of the printed photosensitive acrylic resin was black, and it was an equal mixture of VeroCyanV, VeroYellowV, and VeroMagentaV. The 3D-printed design was the same on both fabrics and was composed of braille dots with a domed top. Both of the 3DP fabrics passed the colorfastness to washing test with no transfer or color change, but 3D prints on both fabrics showed significant color change during the colorfastness to light test. The tensile strength tests indicated an overall reduction in strength and elongation when the fabrics had 3DP on their surface. An abrasion resistance test revealed that the resin had a stronger adhesion to the cotton than to the polyester, but both resins were removed from the fabric with the abrader. These findings suggest that while 3DP on textiles offers unique possibilities for customization and design, mechanical properties and color stability trade-offs need to be considered. Further evaluation of textiles and 3D prints of textiles and their performance in areas such as colorfastness and durability are warranted to harness the full potential of this technology in the fashion and textile industry. Full article

Designing virtual characters that are capable of reflecting a sense of personality is a key goal in research and applications in virtual reality and computer graphics. More and more research efforts are dedicated to investigating approaches to construct a diverse, equitable, and inclusive metaverse by infusing expressive personalities and styles into virtual avatars. While most previous work focused on exploring variations in virtual characters’ dynamic behaviors, characters’ visual appearance plays a crucial role in affecting their perceived personalities. This paper presents a series of experiments evaluating the effect of virtual characters’ outfits on their perceived personality. Based on the related psychology research conducted in the real world, we determined a set of outfit factors likely to reflect personality in virtual characters: color, design, and type. As a framework for our study, we used the “Big Five” personality model for evaluating personality traits. To test our hypothesis, we conducted three perceptual experiments to evaluate the outfit parameters’ contributions to the characters’ personality. In our first experiment, we studied the color factor by varying color hue, saturation, and value; in the second experiment, we evaluated the impact of different neckline, waistline, and sleeve designs; and in our third experiment, we examined the personality perception of five outfit types: professional, casual, fashionable, outdoor, and indoor. Significant results offer guidance to avatar designers on how to create virtual characters with specific personality profiles. We further conducted a verification test to extend the application of our findings to animated virtual characters in augmented reality (AR) and virtual reality (VR) settings. Results confirmed that our findings can be broadly applied to both static and animated virtual characters in VR and AR environments that are commonly used in games, entertainment, and social networking scenarios. Full article

Hair dyeing has become a prevalent lifestyle trend, especially within the fashion industry. However, it possesses disadvantages, such as containing carcinogenic and toxic materials. In this study, we developed a biocompatible hair-dyeing technology using a shampoo with a dark polyphenol complex (DPC), referred to as S-DPC. The DPC was formed from a mixture of gallic acid and [1,1′-biphenyl]-2,2′,4,4′,5,5′-hexol and used to enhance both the stability of the hair coating and its ability to scavenge reactive oxygen species (ROS). Colloidal DPC particles play a pivotal role in the coating process of various hair dyes, ensuring the uniform coloring of human hair through intermolecular interactions such as hydrogen bonding. Owing to the effect of a polyphenol complex on hair coating, we observed improved antistatic performance and enhanced mechanical strength, resulting in a substantial increase in elongation at the breaking point from 33.74% to 48.85%. The multicolor S-DPC exhibited antioxidant properties, as indicated by its ROS-scavenging ability, including 2,2-diphenyl-1-picrylhydrazyl inhibition (87–89%), superoxide radical scavenging (84–87%), and hydroxyl radical scavenging (95–98%). Moreover, the in vitro analysis of the DPC revealed nearly 100% cell viability in live and dead assays, highlighting the remarkable biocompatibility of the DPC. Therefore, considering its effectiveness and safety, this biomaterial has considerable potential for applications in hair dyeing. Full article