• 정보처리학회논문지B
• /
• 제15B권5호
• /
• pp.397-406
• /
• 2008

한의학은 진단 및 치료에 있어 뛰어난 우수성을 가지고 있음에도 불구하고 서양의학에 비해 선호도가 떨어진다. 이는 질병 진단에 있어 객관적인 진단 결과를 제공해 주는 서양의학에 비해 한의학은 임상의의 직관에 의존하고 있기 때문이다. 따라서 한방 임상의들의 직관을 객관화하여 기기로 구현 한다면 한방에 대한 선호도 상승 및 한의학의 세계 시장 진출도 크게 증대할 것으로 여겨진다. 특히 한의학의 진단법 중 가장 뛰어난 진단법으로 평가되는 망진의 경우 다른 진단법에 비해 관련 연구가 거의 이루어 지지 않고 있다. 이는 망진의 가장 중요한 요소인 찰색에 있어 실제 색의 분석을 위한 디지털 기기에서의 색 분석 기준이 없기 때문이다. 이를 위해 본 논문에서는 찰색을 기기로 구현하기 위한 절대적인 색 기준의 설정을 제시하고자 한다. 따라서 색 분석을 위해 여러 가지 디지털 색체계를 비교 분석하여 찰색을 위해 어느 디지털 색체계가 가장 효율적인 색 체계인지를 제시하고자 한다. 아울러 실험 환경의 차이에 따라 발생할 수 있는 변수를 최대한 줄이기 위한 실험 환경 및 조건에 대한 표준화를 제안하고자 한다.

• Industrial Engineering and Management Systems
• /
• 제3권1호
• /
• pp.63-70
• /
• 2004

In this paper, we consider the adjustment of convergence on Color Display Tube (CDT). Convergence is a measure of how well the red, green and blue beams are physically aligned with each other to strike the same area on the screen. When misconvergence (convergence error) occurs, one way of compensating it is to attach several ferrite sheets on the inner part of Deflection Yoke (DY). We suggest an optimization model of misconvergence compensation process and report test results for 81 DY samples. As a result, more than 90% of the samples could be made to satisfy the required convergence criteria.

• 제어로봇시스템학회논문지
• /
• 제15권8호
• /
• pp.761-771
• /
• 2009

Detecting defects on FPD (Flat Panel Display) color filter before the full panel is made is important to reduce the manufacturing cost. Among many types of defects, the low contrast blemish such as Suzi Mura is difficult to detect using standard CCD cameras. Even skilled inspectors in the inspection line can hardly identify such defects using bare eyes. To overcome this difficulty, point spectrometer has been used to analyze the spectrum to differentiate such defects from normal color filters. However, scanning ever increasing-size color filters by a point spectrometer takes too long time to be used in real production line. We propose a system using a spectral camera which can be viewed as a line scan camera composed of an array of point spectrometers. Three types of lighting system that exhibit different illumination spectrums are devised together with a calibration method of the proposed spectral camera system. To visualize the defect areas, various processing algorithms to identify and to enhance the small differences in spectrum between defective and normal areas are developed. Experiments shows 85% successful visualization. of real samples using the proposed system.

• 한국전자통신학회논문지
• /
• 제11권1호
• /
• pp.107-112
• /
• 2016

나사는 산업의 모든 분야에서 널리 사용되는 중요한 부품이다. 최근에는 여러 가지 필요에 의해 다양한 칼라 나사가 출시되고 있다. 이에 따라 제조 공정상에서 실시간 품질 검사가 요구되고 있다. 본 논문에서는 칼라 정보와 동적 계획법(Dynamic Programming) 알고리듬을 이용한 칼라 나사 검사를 위한 표면 영역 자동 추출 알고리듬에 대해 다루도록 한다. 나사의 외곽 경계는 칼라 성분의 차이를 이용하여 보다 강인한 검출이 가능하도록 한다. 나사의 내부 경계는 직교 좌표계를 극좌표계로 변환후 흑백 이미지상에서 일정 영역의 밝기값 차이를 이용한 동적 계획법을 적용하여 추출하도록 한다. 실험에서는 동일한 인자값을 이용한 결과를 분석하도록 한다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2259-2262
• /
• 2003

This paper describes visual tracking procedure of the underwater mobile robot for nuclear reactor vessel inspection, which is required to find the foreign objects such as loose parts. The yellowish underwater robot body tend to present a big contrast to boron solute cold water of nuclear reactor vessel, tinged with indigo by Cerenkov effect. In this paper, we have found and tracked the positions of underwater mobile robot using the two color informations, yellow and indigo. The center coordinates extraction procedures is as follows. The first step is to segment the underwater robot body to cold water with indigo background. From the RGB color components of the entire monitoring image taken with the color CCD camera, we have selected the red color component. In the selected red image, we extracted the positions of the underwater mobile robot using the following process sequences: binarization labelling, and centroid extraction techniques. In the experiment carried out at the Youngkwang unit 5 nuclear reactor vessel, we have tracked the center positions of the underwater robot submerged near the cold leg and the hot leg way, which is fathomed to 10m deep in depth.

• 한국구조물진단유지관리공학회 논문집
• /
• 제20권4호
• /
• pp.77-83
• /
• 2016

근래에 송전철탑의 수명연장과 유지관리 비용 절감을 위한 관심이 증가하고 있다. 그러나 송전철탑 부재의 부식 열화도를 진단하는 재래적인 방법으로서 육안점검은 점검자 개인의 지식과 경험의 차이에 따라 오류를 야기하는 문제점을 내포하고 있다. 이러한 문제를 해결하기 위하여, 본 연구에서는 송전철탑 강 부재에 대한 부식열화 검사장비를 개발하였다. 개발된 검사장비는 부식열화 영상 촬영장치 및 컴퓨터 기반 진단 시스템으로 구성된다. 영상처리에 적합한 열화영상을 확보하기 위하여 촬영장치를 개발하여 촬영방법을 표준화하였으며, 진단 시스템은 RGB 컬러영상처리 기법에 기초하여 송전철탑 부재의 부식 열화도를 자동적으로 평가하도록 설계하였다. 개발된 부식열화 검사장비는 송전철탑 부식에 대한 최적 유지보수 시기를 결정하는 것에 도움이 될 것으로 기대된다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.637-640
• /
• 1999

In this Paper we show the LCD simulator for defect inspection using image processing algorithm and neural network. The defect inspection algorithm of the LCD consists of preprocessing, feature extraction and defect classification. Preprocess removes noise from LCD image, using morphology operator and neural network is used for the defect classification. Sample images with scratch, pinhole, and spot from real LCD color filter image are used. The proposed algorithms show that defect detected and classified in the ratio of 92.3% and 94.6 respectively.

• 대한한의학회지
• /
• 제21권3호
• /
• pp.113-118
• /
• 2000

Objectives : Stroke patients have continuously increased and many studies have been performed to predict their prognosis. Tongue Inspection is a diagnostic method that has been widely used in oriental medicine. The aim of this study was to examine if stroke patients' motor recovery might be related to tongue inspection. Methods : MBI(Modified Barthel Index) and tongue inspection of stroke patients within 3 days of onset were assessed on admission and at 10 days following admission. Results : Functional recovery was significantly better in those who showed favorable changes of tongue, especially in tongue coat color(P=0.030) and thick and thin tongue coat(P=0.092). Conclusions : The results suggest that tongue inspection can be used to predict a prognosis of early stage stroke patients.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1244-1248
• /
• 2003

This paper describes visual tracking procedure of the underwater mobile robot for nuclear reactor vessel inspection, which is required to find the foreign objects such as loose parts. The yellowish underwater robot body tends to present a big contrast to boron solute cold water of nuclear reactor vessel, tinged with indigo by Cerenkov effect. In this paper, we have found and tracked the positions of underwater mobile robot using the two color information, yellow and indigo. The center coordinates extraction procedures are as follows. The first step is to segment the underwater robot body to cold water with indigo background. From the RGB color components of the entire monitoring image taken with the color CCD camera, we have selected the red color component. In the selected red image, we extracted the positions of the underwater mobile robot using the following process sequences; binarization, labelling, and centroid extraction techniques. In the experiment carried out at the Youngkwang unit 5 nuclear reactor vessel, we have tracked the center positions of the underwater robot submerged near the cold leg and the hot leg way, which is fathomed to 10m deep in depth.

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.11-15
• /
• 2020

In a typical initial setup of a PCB component inspection system, operators should manually input various information such as category, position, and inspection area for each component to be inspected, thus causing much inconvenience and longer setup time. Although there are many deep learning based object detectors, RetinaNet is regarded as one of best object detectors currently available. In this paper, a method using an extended RetinaNet is proposed that automatically detects its component category and position for each component mounted on PCBs from a high-resolution color input image. We extended the basic RetinaNet feature pyramid network by adding a feature pyramid layer having higher spatial resolution to the basic feature pyramid. It was demonstrated by experiments that the extended RetinaNet can detect successfully very small components that could be missed by the basic RetinaNet. Using the proposed method could enable automatic generation of inspection areas, thus considerably reducing the setup time of PCB component inspection systems.