• 제목/요약/키워드: paper textile

검색결과 644건 처리시간 0.028초

영역교차법, 왜곡각 분류자 및 명암도 상관행렬 특징자를 이용한 실시간 섬유 성량 검사 시스템 (Real-Time Textile Dimension Inspection System Using Zone-Crossing Method, Distortion Angle Classifier and Gray-Level Co-occurrence Matrix Features)

  • 이응주;이철희
    • 한국멀티미디어학회논문지
    • /
    • 제3권2호
    • /
    • pp.112-120
    • /
    • 2000
  • 본 논문에서는 섬유 제직 공정시 섬유 제품의 질에 영향을 미칠수 있는 섬유 결함, 결함의 위치 검출 뿐만 아니라 이동중인 섬유의 왜곡각 분류 및 섬유의 밀도를 측정할 수 있는 실시간 섬유 성량 검사 시스템을 구현하였다. 구현된 시스템에서는 잡음 문제와 실시간 처리를 위하여 광학적 렌즈로부터 섬유의 위사 부분만을 추출한 후 영역 교차법을 적용하여 섬유의 밀도를 측정하였으며, 획득된 위사 영상으로부터 평균 기울기와 가우시안 기울기 분류자를 사용하여 고속 이동 섬유 가공 공정시 발생할 수 있는 섬유의 왜곡각 분류를 통해 왜곡각 보정을 하였다. 또한 명암도 상관 행렬 특징자를 이용하여 섬유의 결함 검사와 겸함 위치를 추출하도록 하였다. 제안한 알고리즘을 적용하여 구현한 섬유 성량 검사 시스템은 고속 이동 섬유 가공 공정에 있어서 실시간으로 섬유의 밀도 계산과 섬유 결함 검출이 가능하며 섬유 염색, 제직 및 가공공정에 있어서 섬유의 상태를 모니터링 및 제어함으로써 고품질의 섬유 제품 생산이 가능하다.

  • PDF

A Defect Detection Algorithm of Denim Fabric Based on Cascading Feature Extraction Architecture

  • Shuangbao, Ma;Renchao, Zhang;Yujie, Dong;Yuhui, Feng;Guoqin, Zhang
    • Journal of Information Processing Systems
    • /
    • 제19권1호
    • /
    • pp.109-117
    • /
    • 2023
  • Defect detection is one of the key factors in fabric quality control. To improve the speed and accuracy of denim fabric defect detection, this paper proposes a defect detection algorithm based on cascading feature extraction architecture. Firstly, this paper extracts these weight parameters of the pre-trained VGG16 model on the large dataset ImageNet and uses its portability to train the defect detection classifier and the defect recognition classifier respectively. Secondly, retraining and adjusting partial weight parameters of the convolution layer were retrained and adjusted from of these two training models on the high-definition fabric defect dataset. The last step is merging these two models to get the defect detection algorithm based on cascading architecture. Then there are two comparative experiments between this improved defect detection algorithm and other feature extraction methods, such as VGG16, ResNet-50, and Xception. The results of experiments show that the defect detection accuracy of this defect detection algorithm can reach 94.3% and the speed is also increased by 1-3 percentage points.

의복용 자기공진형 무선전력전송 시스템을 위한 평면형 직물공진기의 설계 및 연구 (Analysis and Design of Planar Textile Resonator for Wearable Magnetic Resonance-Wireless Power Transfer)

  • 강석현;정창원
    • 전자공학회논문지
    • /
    • 제53권8호
    • /
    • pp.119-126
    • /
    • 2016
  • 본 논문에서는 의복용 무선전력전송 시스템을 구축을 위한 평면형 직물공진기를 제안하고, 공진기에 사용된 의복용 직물기판의 재질별 특성을 분석하였다. 평면형 직물공진기는 공진주파수가 1-10 MHz가 되도록 직물기판 위에 전도성 물질로 루프 및 코일을 평면 설계하였다. 의복용으로 많이 사용되고 있는 폴리에스테르 섬유와 면을 직물기판으로 사용하였으며, 평면 루프와 코일은 동테이프(copper tape)와 실버페이스트(silver paste)로 설계하였다. 자기공진형 무선전력전송 시스템에 적용된 직물의 재질별 특성을 분석하기 위해 송신부와 수신부를 대칭으로 설계하였다. 실험 결과, 낮은 유전상수 및 비교적 두꺼운 두께를 가진 직물기판과 표면저항이 작은 도체성 재질의 패턴(루프 및 코일)으로 제작되었을 때, 의복용 무선전력전송 시스템이 높은 전송효율을 보였다. 본 연구를 통해 제안된 평면형 직물 공진기는 무선전력전송 기술의 영역을 의복용으로 넓힐 수 있는 가능성을 보여주었다.

한북직물업체의 생산 및 유통구조에 관한 연구 (A Study on the Economic Performance of the Textile Industry for Korean traditional Clothes)

  • 조효숙
    • 복식
    • /
    • 제34권
    • /
    • pp.135-150
    • /
    • 1997
  • The purpose of this study was to inves-tigate the economic performance of the textile industry for the Korean traditional clothes. The content of this paper had two pars; The first part was for the macroeconomic aspects such as location production employments and the produc-tion facilities of the textile industries. The second part was for the microeconomic aspects such as business type branding method fabric type R&D efforts sourc-ing and the distributional channel The major results were as follows: 1.) Most textile firms for the korean traditional clothes were located in Gongju for man-made fibers and in Jinju for silk fabrics. 2) The size of the textile industry in terms of the number of business produc-tion amount the number of employee de-creased during 1994 and 1995 due to the decreasing demand. 3) Over the half of the textile firms produced raw fabric products while only 20% of them were involved in additional dyeing and /or printing finish which re-sulted in low value added production 4) The R&D effort of the textile indus-try for the Korean traditional clothes was very low due to the market uncertainty lack of technological knowledge and most of all small size of the firms 5) Most raw materials for the textile in -dustry were imported with high(25%) tariff rates resulting in price increase and thus low competitiveness in the market. 6) The textile producers sole about the 70% of their products to the wholesalers while selling the rest to the retailers di-rectly. This showed the dual structure of the distribution channel in the textile products. These results suggested some implica-tions for the firms the policy makers and the researchers. The firms should develop new and improved products to increase and create consumer demand by intensive R&D efforts. The government policy ma-kers should give financial supports the firms with R&D investment and legal help such as lowing tariff rate for the raw ma-terials. The researchers from the academy could help the textile industry with the advanced technological knowledge and up-date information for the consumer fashion demand.

  • PDF

Textile 기반의 협력적 필터링 개인화 기술을 이용한 패션 디자인 추천 시스템 개발 (Development of Fashion Design Recommender System using Textile based Collaborative Filtering Personalization Technique)

  • 정경용;나영주;이정현
    • 한국정보과학회논문지:컴퓨팅의 실제 및 레터
    • /
    • 제9권5호
    • /
    • pp.541-550
    • /
    • 2003
  • 소재 개발의 프로세스가 고객 중심으로 다변화 되어가는 생활 환경 속에서 소비자의 감성과 선호도를 파악하는 것은 제품 판매 전략의 중요한 성공요소가 되고 있다. 본 연구에서는 사용자의 감성과 선호도를 중심으로 소재를 개발하는 방법의 하나로 협력적 필터링 개인화 기법을 응용하여 패션 디자인 추천 시스템(FDRS)을 제안한다. Textile 기반의 협력적 필터링 개인화 기술에서, 사용자들간의 유사도 가중치를 계산하기 위해서 피어슨 상판 계수(Pearson Correlation Coefficient)를 사용한다. 소재에 대한 사용자의 감성이나 선호도에 대한 Textile의 대표 감성 형용사를 추출함으로써 소재 개발을 위한 감성 형용사 데이타베이스를 구축한다. 패션 디자인 추천 시스템(FDRS)은 구축된 감성 형용사 데이타베이스를 기반으로 성향이 비슷한 사용자에게 Textile 디자인을 추천한다. 패션 디자인 추천 시스템으로 개발하여 시스템의 논리적 타당성과 유효성을 검증하기 위해 실험적인 적용을 시도하고자 한다.

H&M 콜라보레이션에 참여한 패션 디자이너 브랜드의 자체 제품과 콜라보레이션 제품에 활용된 텍스타일 패턴디자인 연구 (A study on the textile pattern design of fashion designers' brands and H&M collaboration collections)

  • 이은옥
    • 복식문화연구
    • /
    • 제21권1호
    • /
    • pp.93-116
    • /
    • 2013
  • This paper explored and compared the textile pattern and motive design of fashion designers' brands and H&M collaboration collections. In particular, this study put it focus on textile pattern design of seven fashion design brands such as Roverto Cavalli and Versace, etc., which were collaborated with H&M. The color, motive type, motive layout, motive expression, and pattern drawing technique were collected from fashion internet sites over the five year period, and then were cross-sectionally examined and compared based on their color, motive type, motive layout, motive expression, and pattern drawing technique of products between fashion designers' brands and H&M collaboration collections. The analyses showed the following results: First, the similar color, motive type, motive layout, motive expression, and pattern were found between fashion designers' brands and H&M collaboration collections, in order to show the perspective texture of products to consumers. Second, H&M collaboration brands demonstrated unique textile design of H&M rather than the trendy design patterns. Finally, the textile design pattern used in H&M collection was more restricted in terms of motive expression technique and chromaticity than that used in fashion designers' brands.

An Improved Defect Detection Algorithm of Jean Fabric Based on Optimized Gabor Filter

  • Ma, Shuangbao;Liu, Wen;You, Changli;Jia, Shulin;Wu, Yurong
    • Journal of Information Processing Systems
    • /
    • 제16권5호
    • /
    • pp.1008-1014
    • /
    • 2020
  • Aiming at the defect detection quality of denim fabric, this paper designs an improved algorithm based on the optimized Gabor filter. Firstly, we propose an improved defect detection algorithm of jean fabric based on the maximum two-dimensional image entropy and the loss evaluation function. Secondly, 24 Gabor filter banks with 4 scales and 6 directions are created and the optimal filter is selected from the filter banks by the one-dimensional image entropy algorithm and the two-dimensional image entropy algorithm respectively. Thirdly, these two optimized Gabor filters are compared to realize the common defect detection of denim fabric, such as normal texture, miss of weft, hole and oil stain. The results show that the improved algorithm has better detection effect on common defects of denim fabrics and the average detection rate is more than 91.25%.

대구지역 섬유산업 스트림 공급망 협력체계 구축과 국제경쟁력 강화 방안 (International Competitive Improvement through Stream Supply Chain Cooperative System Building of Textile Industry in the Daegu District)

  • 류건우;김승호
    • 통상정보연구
    • /
    • 제12권2호
    • /
    • pp.3-27
    • /
    • 2010
  • This paper covers a plan to build supply chain cooperation systems among stream of the textile industry to strengthen international competitiveness. To obtain the study objective, it has been reviewed the theoretical rationale relating to organizational cooperation model and discussion and performed the case study that analyzed stream group and participated firms to the textile stream policy project. The analyzed stream cooperative types that measured configuration of cooperative degree and productive type are new market creation, technology improvement, relation maintenance, and relation cease. Two types - new market creation and technology improvement - have significant effect of the textile stream cooperation. Key successful factors of these two effective types are the external intervention of specialized consulting organization and build internal coordination and integrated mechanism to the cooperative stream group and participated firms.

  • PDF

섬유패션관련 전시회 참여 실태조사 (An Exploratory Study of Textile and Fashion Trade Show Exhibiting Management)

  • 박광희;김문영;여은아
    • 한국의류산업학회지
    • /
    • 제11권4호
    • /
    • pp.566-573
    • /
    • 2009
  • The purpose of this paper was to collect the information of textile and fashion trade show exhibiting such as the exhibition objectives, trade show selection criteria, reasons for not exhibiting, and exhibition performance. The data were collected from textile and fashion companies which participated in the Preview in Daegu or Seoul Fashion Sourcing Fair, or through the Research Company. The results showed that the most heavily weighted factor among reasons for not exhibiting was "high cost" and the most important exhibiting objective was "identifying the need and the preference of potential customers". "The quality and the quantity of sales lead" was ranked highly among exhibiting selection criteria. Also, the future of exhibition industry was also recognized positively and "effective PR and marketing activities" was assigned high importance among services provided by the organizer.