• Smart Media Journal
• /
• v.13 no.4
• /
• pp.57-64
• /
• 2024

Attributes such as material, color, and fit in fashion images are important factors for consumers to purchase clothing. However, the process of classifying clothing attributes requires a large amount of manpower and is inconsistent because it relies on the subjective judgment of human operators. To alleviate this problem, there is a need for research that utilizes artificial intelligence to classify clothing attributes in fashion images. Previous studies have mainly focused on classifying clothing attributes for either tops or bottoms, so there is a limitation that the attributes of both tops and bottoms cannot be identified simultaneously in the case of full-body fashion images. In this study, we propose a deep learning model that can distinguish between tops and bottoms in fashion images and classify the category of each item and the attributes of the clothing material. The deep learning models ResNet and EfficientNet were used in this study, and the dataset used for training was 1,002,718 fashion images and 125 labels including clothing categories and material properties. Based on the weighted F1-Score, ResNet is 0.800 and EfficientNet is 0.781, with ResNet showing better performance.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.467-472
• /
• 2021

본 연구는 패션앱 후기글에 나타나는 구매자의 의견에 대한 '평가분석(Evaluation Analysis: EA)'을 수행하여, 이를 기반으로 상품의 검색 및 추천을 수행하는 의류 검색추천 챗봇을 개발하는 LICO 프로젝트의 언어데이터 구축의 일환으로 수행되었다. '평가분석 트리플(EAT)'과 '평가기반요청 쿼드러플(EARQ)'의 구성요소들에 대한 주석작업은, 도메인 특화된 단일형 핵심어휘와 다단어(MWE) 핵심패턴들을 FST 방식으로 구조화하는 DECO-LGG 언어자원에 기반하여 반자동 언어데이터 증강(SSP) 방식을 통해 진행되었다. 이 과정을 통해 20여만 건의 후기글 문서(230만 어절)로 구성된 EVAD 평가주석데이터셋이 생성되었다. 여성의류 도메인의 평가분석을 위한 '평가속성(ASPECT)' 성분으로 14가지 유형이 분류되었고, 각 '평가속성'에 연동된 '평가내용(VALUE)' 쌍으로 전체 35가지의 {ASPECT-VALUE} 카테고리가 분류되었다. 본 연구에서 구축된 EVAD 평가주석 데이터의 성능을 평가한 결과, F1-Score 0.91의 성능 평가를 획득하였으며, 이를 통해 향후 다른 도메인으로의 확장된 적용 가능성이 유효함을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.12 no.5
• /
• pp.688-698
• /
• 2009

The market for Internet fashion/coordination shopping malls has been enormously increased year by year. However, online shoppers feel inconvenient because most of Internet shopping malls still rely on item classifications by category and do not provide the functionality in terms of which shoppers can find clothes they want. In an effort to build a fashion/coordination system for women's dress adopting the Heuristic-based method, one of the Context-based methods, we present a method for defining characteristics of a woman's dress as attributes and their inheritance relations, which can be input by a product manager. We also compare and analyze various methods for recommending the most similar clothes.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.5 s.153
• /
• pp.699-710
• /
• 2006

The objective of this study was to identify the texture-related components of woven fabrics and to develop a multidimensional perceptual structure map to represent the tactile textures. Eighty subjects in clothing and tektite industries were selected for multivariate data on each fabric of 30 using the questionnaire with 9 pointed semantic differential scales of 20 texture-related adjectives. Data were analyzed by factor analysis, hierarchical cluster analysis, and multidimensional scaling(MDS) using SPSS statistical package. The results showed that the five factors were selected and composed of density/warmth-coolness, stiffness, extensibility, drapeability, and surface/slipperiness. As a result of hierarchical cluster analysis, 30 fabrics were grouped by four clusters; each cluster was named with density/warmth-coolness, surface/slipperiness, stiffness, and extensibility, respectively. By MDS, three dimensions of tactile texture were obtained and a 3-dimensional perceptual structure map was suggested. The three dimensions were named as surface/slipperiness, extensibility, and stiffness. We proposed a positioning perceptual map of fabrics related to texture naming system(TNS). To classify the textural features of the woven fabrics, hierarchical cluster analysis containing all the data variations, even though it includes the errors, may be more desirable than texture-related multidimensional data analysis based on factor loading values in respect of the effective variables reduction without losing the critical variations.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.46 no.6
• /
• pp.1142-1160
• /
• 2022

Text data plays a significant role in understanding and analyzing trends in consumer, business, and social sectors. For text analysis, there must be a corpus that reflects specific domain knowledge. However, in the field of fashion, the professional corpus is insufficient. This study aims to develop a taxonomy and thesaurus that considers the specialty of fashion products. To this end, about 100,000 fashion vocabulary terms were collected by crawling text data from WSGN, Pantone, and online platforms; text subsequently was extracted through preprocessing with Python. The taxonomy was composed of items, silhouettes, details, styles, colors, textiles, and patterns/prints, which are seven attributes of clothes. The corpus was completed through processing synonyms of terms from fashion books such as dictionaries. Finally, 10,294 vocabulary words, including 1,956 standard Korean words, were classified in the taxonomy. All data was then developed into a web dictionary system. Quantitative and qualitative performance tests of the results were conducted through expert reviews. The performance of the thesaurus also was verified by comparing the results of text mining analysis through the previously developed corpus. This study contributes to achieving a text data standard and enables meaningful results of text mining analysis in the fashion field.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.31 no.12
• /
• pp.1721-1732
• /
• 2007

This study identified types of information source, and explored a path model for consumer information search by shopping attributes in the context of online decision making. Participants completed self-administered questionnaires during regularly scheduled classes. A total of 219 usable questionnaires were obtained from respondents who enroll at universities in the southwestern region of the United States. For data analysis, factor analysis and path model estimation were used. Consumer information source was classified into three types for online clothing purchases: Online source, Offline retail source, and Mass media. Consumers were more likely to rely on offline retail source for online clothing purchases, than other sources. In consumer information search by shopping attributes, online sources were more likely to be related to transaction-related attributes(e.g., incentive service), whereas offline retail source(e.g., displays in stores, manufacturer's catalogs and pamphlets) were more likely to be related to product and market related attributes(e.g., aesthetics, price) when purchasing clothing online. Also, the path model emphasizes the effect of shopping attributes on traditional retailer search behavior, leading to online purchase intention for clothing. This study supports consumer information search by attributes, and discusses a managerial implication of multi-channel retailing for apparel.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.44 no.2
• /
• pp.354-368
• /
• 2020

Accurate and versatile image data-sets are essential for fashion AI research and AI-based fashion businesses based on a systematic attribute classification system. This study constructs a color and texture attribute hierarchical classification system by collecting fashion item images and analyzing the metadata of fashion items described by consumers. Essential dimensions to explain color and texture attributes were extracted; in addition, attribute values for each dimension were constructed based on metadata and previous studies. This hierarchical classification system satisfies consistency, exclusiveness, inclusiveness, and flexibility. The image tagging to confirm the usefulness of the proposed classification system indicated that the contents of attributes of the same image differ depending on the annotator that require a clear standard for distinguishing differences between the properties. This classification system will improve the reliability of the training data for machine learning, by providing standardized criteria for tasks such as tagging and annotating of fashion items.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.25 no.9
• /
• pp.1621-1632
• /
• 2001

본 연구는 소비자의 실제적인 의복 소비 행동을 설명할수 있는 가치 개념을 제시하기 위하여 의복 소비가치의 구체적 유형을 밝히고, 적합하고 신뢰성 있는 의복 소비가치 척도를 구성 할 수 있는 기초자료를 제시 하고자 하였다. 본 연구에서는 Sheth(1991)의 소비 가치 이론과 의류학 및 소비자 행동분야의 다양한 이론을 토대로 초점집단면접(Focus Group Interview)을 통하여 소비가치에 대한 탐색적 접근을 시도한 결과를 논의하였다. 의복의 구매와 착용의 선택상황에 영향을 미치는 소비가치는 Sheth(1991)의 5가지 소비가치 유형인 기능적 가치, 사회적 가치, 감정적 가치, 진귀적 가치, 상황적 가치 및 의복제품의 특성에 따른 자기표현적 가치로 분류되었다. 기능적 가치는 물리적 속성, 물리적 기능, 도구적 성과와 관련되었으며, 사회적 가치는 사회계층, 준거집단, 인구통계 적 특성 집단, 문화-민족적 집단과의 관련성 에 대 한 가치로 구성되었다. 감정적 가치는 긍정적, 부정적 감정 및 심미성 요인으로 구성되었으며, 진취적 가치는 다양성추구행동 요인 및 유행성의. 새로움 추구 요인과 관련되었다 또한 상황적 가치는 의복착용상황, 구매상황, 커뮤니케이션 상황으로 구성되었으며, 자기표현적 가치는 성격, 이미지 표현, 개성추구, 유행추구 등의 요인으로 구성되었다. 본 연구의 이러한 결과를 바탕으로 소비가치에 대한 양적 연구를 실시한다면, 보다 객관적인 구조를 파악하고 신뢰성 있는 측정 문항을 개발할 수 있을 것이다.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.22 no.3
• /
• pp.374-383
• /
• 1998

Apparel Quality was one of the most important elements to evaluate the reputations of companies and products which affect the consumer's purchasing behavior. From researches on apparel quality, there was no common concept of quality as well as no common dimensions. The purposes of this study were to identify apparel quality concept and to classify the multi-dimensional concept of apparel quality. The research was carried out in theoretical as well as empirical studies. The theoretical study was conducted to find out apparel quality concept and divide apparel quality concept into four dimensions groups. The empirical study followed the theoretical study to confirm the multi-dimensional concept of apparel quality. The empirical study was investigated that the questionnaire was administered to 634 housewives in Seoul, Kwangju, and Busan during the fall of 1996. The data were analysed by LISREL analysis. This study identified that apparel quality was characteristics of consumer's desires for apparel. The results of the theoretical study verified that apparel quality concept was organized into four different dimensions: physical attribute, physical function, instrumental performance, and expressive performance.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.30 no.12 s.159
• /
• pp.1697-1707
• /
• 2006

Relentless advances in information technology are constantly transforming market dynamics of the retail industry. RFID is an emerging innovative technology that can reduce labor costs, improve inventory control and increase sales by effective business processes. Apparel retailers need to recognize the benefits of RFID and identify critical success factors. By focusing on apparel retailers, this study attempts (1) to identify the reality of RFID associated with benefits; and (2) to prospect the implementation of RFID in apparel retailing. We conducted a focus group interview with selected six panels who were experts of retail industry in the United States to obtain data regarding RFID attributes. Content analysis was used to generate related excerpts and classify 31 attributes of RFID benefits from the meaningful 173 responses. For experience of RFID, retailers were familiar with RFID technology and expressed the belief that RFID basically would support an existing retail system for speed to markets. However, retailers addressed the level of experience with RFID technology that they were still in the early adoption stage among few innovative companies. The content analysis identified five dimensions of RFID benefits for apparel retailing: Visibility and Velocity, Revenue Enhancement, Customer Service, Security, and Employee Productivity. This result lends support to the belief that RFID has a significant potential to streamline supply chain management, store operation and customer service for apparel retailing. This study provides intellectual and managerial implications far practitioners and researchers by postulating the effective use of RFID in the apparel retail industry.