• 품질경영학회지
• /
• 제42권2호
• /
• pp.165-177
• /
• 2014

Purpose: This study analyzes the strategical priority to improve eco-labelling certification system, focused on biodegradable resin. Methods: This study will come up with measures to operate the eco-Label certification system related to biodegradable products more effectively and efficiently by discovering various problems related to the system, using causal loop diagram and AHP analysis. Results: This study shows that the government should play more important role while firms could also serve their roles in the initial and stabilizing stages of the eco-labelling certification system, in order to vitalize the eco-Label certification system more effective. Conclusion: This study addresses strategic eco-labelling policies on governmental and firm's operation and providers guidance to practitioners in addressing strategic decision relating to eco-labelling certification system.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 춘계학술대회 논문집
• /
• pp.225-230
• /
• 2004

A cold ＆ hot rolling coil production line of iron nill consists of a kind of coherent automatic process, but an automatic labelling process still had technical difficulties in the automation of its process. The reason for difficulties in building an automatic process is that quantitative data for each rolled coil from every shipping is not easy to receive from the previous process. it is not possible to apply for a general and simple purpose robot that is actually worked through a taught position to the process because the size and direction of the coi1 has differed on every shipping. From these reasons. we introduce a robot vision system to accept an expected variable situation and to ensure the stability and flexibility of the process. This paper examines a study applied for similar cases and finds the position and direction of relied coil using the moment invariant algorithm proposed by Hu. In addition. the camera calibration and position error compensation algorithm is applied by the analysis of the relationship of transition in a space coordinate system. The construction of a robot vision system proposed by this paper is a more intellectual system than that of the automatic labelling system. which is already used to the Daihen steel nill of NEW JAPAN steel mill co. Ltd in Japan, and shows a better independent operation in the field of production.

• 대한의생명과학회지
• /
• 제8권3호
• /
• pp.161-165
• /
• 2002

Apoptosis can be difficult to detect in routine histological sections. Since extensive DNA fragmentation is an important characteristic of this process, visualization of DNA breaks could greatly facilitate the identification of apoptotic cells. Several techniques for the qualitative and quantitative detection of this process have been established; recently, an in situ nick end-labelling technique based on the detection of DNA fragmentation, which is a molecular characteristic of apoptotic cell death, was described. Applying this method to paraffin sections of rat tissues, sensitivity was observed to be inconsistently low with regard to the expected number of apoptotic cells. I describe a new modified method for formalin-fixed, paraffin-embedded tissue sections, pretense pretreatment to permeate the tissue sections that involves an TUNEL (terminal deoxynucleotidyl transferase-mediated dUTP nick end-labeling) is acknowledged as a method of choice in the rapid identification and quantification of the apoptotic cell fraction in paraffin tissue preparations. TUNEL was performed without apoptosis and with apopotosis samples to each of the three concentrations of proteinase K (10, 25, 40 mg/ml) pretreatments. In this study, I show that chemical pretreatments of the tissue sections in proteinase K (25 mg/ml for 15 min at room temperature) considerably enhances the sensitivity of this nick end labelling technique.

• 한국의류산업학회지
• /
• 제20권3호
• /
• pp.331-342
• /
• 2018

This paper enables stakeholders involved in textile industry to gain an overview of standards used for care labelling and help establish a common standard that could be used as a universal standard. This study provides a comprehensive and detailed analytical study of care labelling standards adopted by common countries in the textile market. It was found that the development of a universal system for care labeling could enhance the trade of textile articles and assist consumers in caring for textile articles. Universal care label systems could be characterized by two main features of inclusiveness and comprehensiveness. The range of instructions and symbols presented were found different among standards. Insignificant differences in symbols' shapes were found between standards for bleaching, ironing and professional cleaning. The washing process had the widest variety of instructions; in addition, options were provided by stated standards. Different meanings were found for similar shapes in some tumble drying symbols. The study findings show the importance of enhancing text based standards or the development of an understandable format across as many cultures as possible. The unification of symbols and meanings may be needed to provide global consumers consistent guidance. The efficiency of a detailed standard that provides and covers a wide range of instructions is an important aspect. The visibility and practicality of offering variable options/symbols in one standard is an important aspect for developing a universal care label system.

• 대한의용생체공학회:의공학회지
• /
• 제16권3호
• /
• pp.337-344
• /
• 1995

방사선 치료에 있어서 치료전 및 치료도중에 치료부위를 확인하기 위한 수단으로 보편적으로 사용되고 있는 포탈필름은 높은 에너지를 이용하여 촬영되는 것이므로 영상이 매우 흐리며 어둡다는 구조적인 문제점이 있다. 이러한 영상을 개선하기 위하여는 치료필드와 그 주변필드로 영상을 먼저 분할한 후, 각 필드 별로 영상처리를 해야만 한다. 본 연구에서는 소벨 탐지자, 레이블링 기법을 이용하여 최적의 문턱치를 찾아내어 포탈영상을 분할 한 후 형태학적 세선화기법들을 적용하여 포탈영상 분할하는 알고리즘을 제안하였다. 이 알고리즘은 포탈영상에서 불필요한 에지들은 제거하고 치료필드 에지만을 탐지하며 촬영조건이 수시로 변하는 임상적 환경에서 얻어지는 포탈영상들에 적용하여도 균일한 결과를 얻을 수 있다.

• 한국멀티미디어학회논문지
• /
• 제20권5호
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.222-224
• /
• 2022

객체 분할 분야의 딥러닝 기반 컴퓨터 비전 응용들은 성능을 향상하기 위하여 STOA 기법들이 사전학습하여 배포한 하이퍼파라미터와 모델을 통해 학습하는 전이학습 방법을 사용한다. 이 과정에서 사용되는 커스텀 데이터 셋들은 Ground Truth 정보를 생성하기 위한 라벨링 작업에서 시간이나 라벨러등의 많은 자원을 필요로 한다. 본 고에서는 딥러닝 신경망에서 사용되는 커스텀 데이터 셋 구축을 위하여 시간이나 라벨러등의 자원을 적게 사용할 수 있도록 객체 분할 기법을 활용한 자동 라벨링 구축 방법을 제시한다.

• 제어로봇시스템학회논문지
• /
• 제3권1호
• /
• pp.89-93
• /
• 1997

This paper describes the automatic testing system developed for powder metallurgy process using the visual inspection, and its some internal algorithms. The system consists of one unit from each of the five types of units; feeding, slot, vision inspection, volumn counter, and inferior good extractor units. Some applications of the system to powder metallurgy process has shown the possibility of reducing the rework and increasing the efficiency of operation.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.

• 한국산학기술학회논문지
• /
• 제15권8호
• /
• pp.4987-4998
• /
• 2014

최근 공산품에 나노기술의 활용이 점점 확대되고 다양한 나노제품이 출시되면서 나노물질의 인체 및 환경에 대한 유해성 문제가 주요한 사안으로 대두되고 있다. 이러한 위험성을 인식하여 EU 및 미국 등에서는 나노물질에 대한 규제를 강화하는 추세이다. 그러나 현재 국내에는 나노관련 법규가 미흡한 형편이다. 무엇보다도 소비자에게 밀접한 공산품의 나노물질 규제정책은 소비자의 안전을 위해 시급히 요구되고 있다. 이에 따라 본 연구에서는 규제정책 도입을 위한 기반연구로서 공산품에 함유된 나노물질에 대한 규제정책 도입을 위한 분석을 실시한다. 본 연구에서는 AHP(Analytic Hierarchy Process) 기법을 적용하여 규제정책을 평가하고 가장 적합도가 높은 최적 규제정책을 선택한다. 규제정책은 자율규제, 제품라벨링, 정부등록제를 대상으로 하며 정책평가기준은 시행성(효과성), 경제성, 수용성, 보호성으로 설정한다. 평가 결과 최대 적합도를 가지는 제품라벨링 정책을 최적 규제정책으로 선택한다.