• Title/Summary/Keyword: 패션의류산업

검색결과 613건 처리시간 0.023초

딥러닝을 이용한 의류 이미지의 텍스타일 소재 분류 (Textile material classification in clothing images using deep learning)

  • 이소영;정혜선;최윤성;이충권
    • 스마트미디어저널
    • /
    • 제12권7호
    • /
    • pp.43-51
    • /
    • 2023
  • 온라인 거래가 증가하면서 의류 이미지는 소비자의 구매 결정에 큰 영향을 미치게 되었다. 의류 소재에 대한 이미지 정보의 중요성이 강조되고 있으며, 의류 이미지를 분석하여 사용된 소재를 파악하는 것은 패션 산업에 있어서 중요하다. 의류에 사용된 텍스타일의 소재는 육안으로 식별하기 어렵고, 분류 작업에도 많은 시간과 비용이 소모된다. 본 연구는 딥러닝 알고리즘을 기반으로 의류 이미지로부터 텍스타일의 소재를 분류하고자 하였다. 소재를 분류함으로써 의류 생산 비용을 절감하고, 제조공정의 효율성을 증대하는데 도움이 되며 소비자에게 특정 소재의 제품을 추천하는 AI 서비스에 기여할 수 있다. 의류 이미지를 분류하기 위해 머신비전 기반의 딥러닝 알고리즘 ResNet과 Vision Transformer를 이용하였다. 760,949장의 이미지를 수집하였고, 비정상 이미지를 검출하는 전처리 과정을 거쳤다. 최종적으로 총 167,299장의 의류 이미지와 섬유라벨 19개, 직물라벨 20개를 사용하였다. ResNet과 Vision Transformer를 사용해서 의류 텍스타일의 소재를 분류하였으며 알고리즘 성능을 Top-k Accuracy Score 지표를 통해 비교하였다. 성능을 비교한 결과, ResNet 보다 Vision Transformer 알고리즘이 더 우수하였다.

패션기업의 특허.실용신안 등록현황에 관한 연구 -IPC분류코드 A41B와 A41D를 중심으로- (A Study on the Registration of Patent and Utility Models by Fashion Firms in Korea -Focus on IPC A41B and A41D-)

  • 김용주
    • 한국의류학회지
    • /
    • 제35권2호
    • /
    • pp.192-205
    • /
    • 2011
  • This study analyzed the registration of patent and utility models by fashion firms in Korea. A total of 2,291 registration cases of IPC A41B-H from the period of 1996 to 2009 were collected by KIPRIS of the Korean Intellectual Property Organization (KIPO). All cases were analyzed by year to review the longitudinal trend and 481 cases of IPC A41B (shirts, underwear, baby linen, and handkerchiefs) and 1088 cases of IPC A41D (outerwear, protective garments, and accessories) were analyzed by content (provided benefit type and developing method), by detailed product items and the characteristics of the applicant. The results of this study were as follows: 1) Registration of IPC 41 increased steeply by the year (especially since 2006) and the patent registrations increased more than those in the utility model. 2) Analyzing the application content of A41B on the basis of benefit showed that 75% were to provide new functions and the rest were for health. In terms of the developing method, 83% of benefit provided by the application were by design development, 11.2% were by material, and the rest was by process, In the cases of IPC A41D, 23.6% were for safety and protection. In terms of the developing method, the process and material development were more frequently adopted than in the cases of A41B. 3) The major product types of A41B were socks, underwear, and infant wear, whereas gloves and parts of clothing were major items in A41D. 4) In terms of the characteristics of the applicant, registration by firms was greater for patents than for utility models and registration by foreigners increased in 2006 due to the complete opening of the retail market. 5) Fifteen universities registered for a total 57 cases and major applications were for IT related clothing or high-tech protective items.

패션기업의 조직 특성이 빅데이터 분석 시스템의 수용의도에 미치는 영향 (The Effect of the Organizational Characteristics of Fashion Companies on Acceptance Intention of Big Data Analysis System)

  • 장세윤;양수진
    • 한국의류학회지
    • /
    • 제41권2호
    • /
    • pp.378-391
    • /
    • 2017
  • The application of Big Data has been introduced to the Korean fashion industry; however, the literature has not yet investigated how well high technologies are being perceived and adopted by the practitioners of fashion companies. Recognizing the lack of research, the current research explores how big data analysis has been adopted by fashion practitioners based on the Technology Acceptance Model (TAM) that considers the effect of organizational characteristics (i.e., innovation, slack, and IS infra maturity). First, all TAM relationships were accepted as significant; however, the effect of perceived ease of use on the attitude toward big data was greater than perceived usefulness. Regarding organizational characteristics, while organization innovation had positive impacts on perceived usefulness as well as perceived ease of use, organization slack did not show significant and positive influence on perceived ease of use only. On the other hand, IS infra maturity had a negative effect on perceived usefulness while it did not have any significant impact on perceived ease of use. Finally, the level of perceived usefulness is decreasing as the IS infra of the fashion organization becomes more mature. With the results, the study suggested that fashion industry needs more education on the usage of big data analysis systems and development in related analysis tools.

더블라셀 소재의 CAD에 의한 표현과 물성연구 (Analysis of CAD Design and Physical Properties of Double-raschel Spacer Fabric)

  • 최경미;김종준
    • 패션비즈니스
    • /
    • 제23권1호
    • /
    • pp.37-48
    • /
    • 2019
  • WKSF (Warp-knitted spacer fabrics) knitted using a double Raschel machine is the three-dimensional knit that has vertically connected separate layers in loop structures. Because of its unique structure, the fabric is light, compressible and breathable. Owing to the high production speed, the use of the fabric is increasing in various areas. The purpose of this study is to establish the design process in the utilization of WKSF program and analyze the difference between WKSF and Neoprene as garment materials.. The study on the design related to WKSF has rarely been carried out because of the complexity of WKSF structure and the difficulties encountered in analyzing the structure and thread. Therefore, checking beforehand the simulation results similar to a final knit using the CAD program for WKSF can only enhance the efficiency of the design for the light knits. The conclusion drawn after designing the light knits using the CAD program and analyzing the pros and cons of WKSF through the various property evaluation techniques is as follows. The tension characteristic analysis results indicated that Neoprene specimen has the elastic transformation and resilience, thus behaving like an elastic product such as rubber. By contrast, in the event that clothing and fashion accessories are designed with WKSF, these products are kept in a boxy style fit so that the fabric can be applied flexibly to a curvy body line. In addition, WKSF is good in forming noticeably around a curvy body, because its resistance shear deformation is lower than that of Neoprene.

럭셔리 패션 브랜드의 디지털 마케팅 전략 분석 (Analysis of digital marketing strategies of luxury fashion brands)

  • 박지수;이영주
    • 한국의상디자인학회지
    • /
    • 제23권1호
    • /
    • pp.87-102
    • /
    • 2021
  • The purpose of this study is to consider effective digital marketing strategies through analysis of luxury fashion brands. This study conducted both quantitative analysis and case studies of the brands Louis Vuitton, Gucci, Burberry, and Chanel. To measure the brand image of the luxury fashion brands, the survey was distributed to Millennials, and total of 277 responses were used for the final analysis by using SPSS 25.0 statistical program. Other than survey, this paper analyzed digital marketing strategies of luxury fashion brands through brand-related papers, website and social media of each brand, Samsung Designnet's database, and news posted on search engines. The results of this study are as follows: First, according to the result of examining brand image of luxury fashion brands, there was no significant difference between brands, except Gucci. Second, this study analyzed each luxury fashion brand to understand the characteristics of digital marketing, and common characteristics were identified. Third, by analyzing the brand image and digital marketing strategies of luxury fashion brands, it was confirmed that Gucci's brand image and digital marketing strategies were consistent, while there was a difference between Burberry's brand image and digital marketing strategy. Therefore, this article proposes the following digital marketing strategies that are suitable for luxury fashion brands. First, is the connection of on/offline channels. Second, is the use of AI technology. Third, is a blockchain-based platform.

챗봇 기반의 개인화 패션 추천 서비스 향상을 위한 사용자-제품 속성 제안 (Proposal for User-Product Attributes to Enhance Chatbot-Based Personalized Fashion Recommendation Service)

  • 안효선;김성훈;최예림
    • 패션비즈니스
    • /
    • 제27권3호
    • /
    • pp.50-62
    • /
    • 2023
  • The e-commerce fashion market has experienced a remarkable growth, leading to an overwhelming availability of shared information and numerous choices for users. In light of this, chatbots have emerged as a promising technological solution to enhance personalized services in this context. This study aimed to develop user-product attributes for a chatbot-based personalized fashion recommendation service using big data text mining techniques. To accomplish this, over one million consumer reviews from Coupang, an e-commerce platform, were collected and analyzed using frequency analyses to identify the upper-level attributes of users and products. Attribute terms were then assigned to each user-product attribute, including user body shape (body proportion, BMI), user needs (functional, expressive, aesthetic), user TPO (time, place, occasion), product design elements (fit, color, material, detail), product size (label, measurement), and product care (laundry, maintenance). The classification of user-product attributes was found to be applicable to the knowledge graph of the Conversational Path Reasoning model. A testing environment was established to evaluate the usefulness of attributes based on real e-commerce users and purchased product information. This study is significant in proposing a new research methodology in the field of Fashion Informatics for constructing the knowledge base of a chatbot based on text mining analysis. The proposed research methodology is expected to enhance fashion technology and improve personalized fashion recommendation service and user experience with a chatbot in the e-commerce market.

의류 패션산업에서 순한글과 외래어 용어에 대한 감성비교 (Emotion and Sensibility Comparison between Loanword and Hangul Label in Fashion Industry)

  • 윤용주;나영주
    • 감성과학
    • /
    • 제18권1호
    • /
    • pp.79-94
    • /
    • 2015
  • 본 연구는 패션산업에서 상품라벨과 패션용어의 형태, 즉 한글과 외래어, 외국어 등 표기 종류에 따라 소비자의 감성이 어떻게 다르게 나타나는지 분석한 것이다. 20대 소비자 200명을 대상으로 패션아이템 1종에 대한 라벨 1종과 3종 패션용어에 대하여 설문조사를 실시하였는데 외래어 영어표기, 외래어 한글표기, 순한글표기 등 3가지 형태에 대해 15개 형용사로 구성된 감성 척도를 이용하여 감성을 측정하였고 또한 선호도와 상품에 대한 예상가격을 질문하였다. 결과로는 소비자들은 라벨에서 한글보다 외래어를 선호하였으며 외래어 라벨 중에서도 한글표기보다 영어표기를 선호하였다. 외래어 라벨을 볼 때 소비자들은 패션 제품이 더 '긍정적이고 세련되고 화려하며 우아하다'고 평가하고 있었으며 또 상품의 가격을 더 높은 것으로 예상하였다. 즉 외래어 영어표기 라벨이 모든 평가에서 가장 높은 점수를 받았고, 외래어 한글표기가 다음 순이었으며, 순한글 라벨은 가장 낮은 평가를 받았다. 소비자들은 자신의 유행 몰입도에 따라서 감성 평가를 부분적으로 다르게 하고 있는 것으로 나타났다. 즉 유행 몰입도가 높은 소비자들은 낮은 소비자보다 외래어를 볼때 '세련된 우아한 화려한' 등에 대해서 더 높게 평가하고 있었다. 또한 유행몰입도가 높은 소비자들은 낮은 소비자보다 순한글표기 라벨을 볼 때 '친근한, 안정된' 등에 대해서 더 높게 또는 외래어와 유사하게 평가하고 있었다.

IT 패션에 대한 국내 연구 동향 (Domestic Research Trends in IT Fashion)

  • 추호정;남윤자;이유리;이하경;이성지;이새은;장재임;박진희;최진우;김도연
    • 한국의류산업학회지
    • /
    • 제14권4호
    • /
    • pp.614-628
    • /
    • 2012
  • The purpose of this study was to analyze research trends and make suggestions regarding the future of information technology (IT) in the fashion industry. In this study, 437 papers written regarding IT fashion from five major journals published between 2000 and 2011 were examined. The research areas were then organized by subject and keyword, and divided into 16 high-context categories. Two IT fashion maps were constructed, one from a fashion consumer's perspective, and the other based on the fashion industry's supply chain. This study identified important trends in IT fashion such as: 3D scanners, 3D digital renderings of the human form, 3D digital garments, smart garments, mass customization, production automation, online shopping, home shopping, online communities, e-commerce, digital media, virtual reality, e-tail, the digital generation, E-CRM, and education. Data from body scans was collected and applied to production, and research on smart textiles was also carried out. As for IT fashion's service areas, the majority of the research focused on online shopping or online communication. Additionally, research done on avatars and cyber space, and studies on social networking services are shown. The results of this study indicated that a new field of research has opened and that current research has been developing. Also, this study showed what is needed to expand and strengthen IT fashion.

패션문화에 나타난 오리엔탈리즘에 대한 비판적 논의 (Critical Discussion on the 'Orientalism' in Fashion Culture)

  • 서봉하
    • 한국의류학회지
    • /
    • 제32권6호
    • /
    • pp.902-910
    • /
    • 2008
  • Orientalism은 동양을 서양과는 다른 이질적 인 대상, 괴상하고 후진적이며 수동적 인 특성을 지닌 열등한 타자로 서양인의 무의식 속에 내면화되어 왔다. 아시아를 일정한 지배의 틀 속에 가두는 문화적 장치와 담론의 체계인 Orientalism은 원래 남유럽과 북아프리카를 포함한 서남아시아에 해당하는 서유럽 중심의 용어였으며, 비 서구사회는 서구문명을 수용함으로써만 발전할 수 있다는 논리의 사상이다. 따라서 이러한 용어의 무분별한 사용은 부적절하다. 또한 아시아의 이미지나 복식양식을 차용한 서구의 아시안 룩에 아시아 본래의 정신은 사라졌다고 하여도 아시아를 저급한 타자로 인식한 것에서 비롯된 것이 아니다. Asian Ethnic Look은 동양적 미학에 매료되어 동양의 이미지나 양식을 차용한 서양의 복식이므로 Orientalism의 속성과는 차이가 있다. 국내의 패션계에서는 이에 대한 분별없이 혼용하여 사용하고 있고, 특히 Orientalism Fashion 또는 Oriental Look이라고 자주 사용하고 있다. 아시아의 복식이나 이미지를 기괴하게 조작한 일부 특정한 복식만을 Orientalism Fashion 또는 Oriental Look이라 해야 하며, 이를 제외하고는 'Asian Look', 'Asian Fashion', 'Asian Ethnic Look' 등으로 바꾸어 쓰거나, 'Korean Look' 등의 개별 국가나 지역 명으로 바꾸어 쓰는 것을 분명히 해야 한다 한국을 비롯한 아시아는 서구 중심의 수동적 입장이 아니라, 세계 패션산업의 중심축 중 하나로써 세계 패션을 리드하고 있다. 이제는 우리 스스로가 서구중심의 이분법적 편견을 해체해 나가야 할 것이다.

패션 라이브 커머스의 특성과 소비자 신뢰 (The characteristics of fashion live commerce channels and consumer trust)

  • 박신영;신수연
    • 복식문화연구
    • /
    • 제29권5호
    • /
    • pp.665-678
    • /
    • 2021
  • This study empirically verified the effect of the characteristics of live commerce on consumer trust and purchase intention. An online survey was conducted targeting adult women in their 20s and 30s who watched videos relating to fashion products on the NAVER shopping live channel; 281 questionnaires were analyzed using the IBM SPSS statistics 23 and AMOS 21 software packages. Consequently, the four factors of interactivity, attractiveness, price discount, and playfulness were identified from the data as characteristics of live commerce. Whereas interactivity and playfulness positively affected trust in both the seller and the product, attractiveness did nor significantly affect trust in the seller and the product. Furthermore, price discount had a significant positive effect only on trust in the seller and had no significant effect on trust in the product. In addition, trust in both the seller and the product had a significant positive effect on consumers' purchase intention; in particular, trust in the seller had a greater influence on consumers' purchase intention than trust in the product did. Research on the characteristics of live commerce can contribute to extend the theorical framework of live commerce research. Finally, fashion companies using live commerce channels will be able to develop live commerce channels that can elicit positive consumer perceptions based on the results of this study.