• Korean Journal of Optics and Photonics
• /
• v.13 no.4
• /
• pp.283-288
• /
• 2002

Unlike rigid parts, flexible parts can be deformed by contact force during assembly. In robotic assembly, information about their deformation as well as possible misalignment between the holes and their respective mating parts is essential for successful assembly. This paper presents a method to design a visual sensing system for measuring parts deformation and misalignment in flexible parts assembly. This paper performs ray-trace analysis of the system. A series of experiments for flexible parts assembly by using the implemented system are performed.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.231-234
• /
• 2006

과거 디스플레이 장치로서 사용되던 CRT를 대신하여, 상대적으로 두께가 않고 가벼운 영상장치인 평판 디스플레이(Flat Panel Display, FPD)의 사용이 급증하고 있다. 이렇게 평판표시장치(Flat Panel Display) 산업의 폭발적인 성장과 함께 새로운 공정개발을 통해 짧은 시간에 더 많은 양을 생산하고, 불량률을 낮추는가에 생산업체의 사활이 달려있다. 본 논문은 FPD 공정에서 품질을 결정하는 여러 요인 가운데 비중이 큰 박막 두께의 제어를 지능화 알고리즘을 통해 해결하고자 한다. 이는 불필요한 과정을 줄여 공정경비를 절감 및 소요시간을 단축하고, 정밀하게 두께를 측정하는 것을 가능하게 한다. 마지막으로, 제안한 알고리즘을 광 간섭 두께 측정기를 통해 얻은 실제 값을 가지고 시료의 두께를 측정한다.

• Resources Recycling
• /
• v.15 no.6 s.74
• /
• pp.3-9
• /
• 2006

In this study, a machine vision system using a color recognition method has been designed and developed to automatically sort out specified materials from a mixture, especially Cu and other non-ferrous metal scraps from a mixture of iron scraps. The system consists of a CCD camera, light sources, a frame grabber, conveying devices and an air-nozzle ejector, and is program-controlled by a image processing algorithms. The ejectors designed to be operated by an I/O interface communication with a hardware controller. In the functional tests of the system, its efficiency in the separation of Cu scraps from its mixture with Fe ones reaches to 90% or more at a conveying speed of 15m/min, and thus the system is proven to be excellent in terms of the separating efficiency. Therefore, it is expected that the system can be commercialized in the industry of shredder makers if an automated sorting system of high speed is realized.

• Proceedings of the Korean Institute of Resources Recycling Conference
• /
• 2005.05a
• /
• pp.57-61
• /
• 2005

In this study, the machine vision system for inspection using color recognition method have been designed and developed to automatically sort out a specified material such as Cu scraps or other non-ferrous metal scraps mixed in Fe scraps. The system consists of a CCD camera, light sources, a frame grabber, conveying devices and an air nozzled ejector, and is program-controlled by a image processing algorithm. The ejector is designed to be operated by an I/O interface communication with a hardware controller. The sorting examination results show that the efficiency of separating Cu scraps from the Fe scraps mixed with Cu scraps is around 90 % at the conveying speed of 15 m/min. and the system is proven to be excellent in terms of its efficiency. Therefore, it is expected that the system can be commercialized in shredder firms, if the high-speed automated sorting system will be realized.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.250-252
• /
• 2004

나노 기술의 개발과 마이크로어레이(microarray)의 등장으로 생물학자동을 한번에 보다 라르고 신속하게, 대량의 실험을 처리할 수 있게 되었다. 이와 발 맞추어 마이크로어레이를 이용한 다양한 실험 방법들이 개발되었다. 형광 염료(fluorescence dye)를 이 용한 관찰 방법 이 널리 이용되고 있으나, 관찰되는 형광 염료의 밝기가 실험 환경(pH, 온도)에 매우 민감하게 반응하며, 단백질을 포함한 많은 분자 물질들이 형광을 내지 않기 때문에 마이크로어레이를 이용한 분석 대상 물질들의 개수가 제한을 받는다. 본 논문에서는 직접적인 형광 염료의 사용 없이, SPR(Surface Plasmon Resonance)을 이용한 마이크로어레이 분석 시스템에서 스팟(spot)의 밝기(intensity)를 측정하기 위한 효율적인 전처리 과정을 제안하고자 한다. 전처리 과정은 크게 프로젝티브 왜곡 효과 제거, 스팟의 위치 추적, 스팟의 영역 추출, 정규화 된 스팟의 밝기 측정으로 나누어진다. 특히, 이러한 과정을 거쳐서 측정된 밝기는 반응 유무의 관찰뿐만이 아니라, 실험 물질의 양적인 측정에도 이용되기 때문에 정확한 스팟의 밝기 측정에 중점을 두고자 한다.

• Investigative Magnetic Resonance Imaging
• /
• v.4 no.1
• /
• pp.7-13
• /
• 2000

Purpose : To assess the distortion of MRI with the Leksell stereotactic radiosurgery system in variable pulse sequence and imaging plane through phantom study, to find most adequate imaging plane and pulse sequence for stereotactic radiosurgery system. Materials and methods : We made the phantoms for MRI and get images in variable conditions and analyzed the image distortion using image analysis program, and statistically using paired student t-test. Results : The transeverse plane images had acceptable error ranges bless than 1.5mm) in all pulse sequence in both the analysis of fiducial marker in stereotactic G-frame and the phantom study. The coronal plane images had unacceptable large errors (more than 1.7mm) in the analysis of fiducial marker in the stereotactic G-frame, but had corrected small errors (less than 1.5mm) in the phantom study. Conclusion : We find from the phantom study that the present MR machines are adequate for stereotactic surgery system in frequently used pulse sequences, and imaging planes.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.5
• /
• pp.1996-2001
• /
• 2012

Visual inspection systems are widely proposed for the well formed surface materials like electronics parts. But the materials with ill reflection ability have many troubles when visual inspection system is introduced. We have developed a robust visual inspection system that can work well in spite of low reflection ratio and with much noise when truth model is not known in the mixed production line. A workpiece identification technique using k-means has been proposed to identify the type. Based on the identified type, a robust-to-noise segmentation method, called active contour, has been applied to segment the features from the image. Finally, Kalman filter has been applied to adapt the error variation. Experiment shows that performance is about to match the accuracy of manual measurement using projectors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.8
• /
• pp.1885-1894
• /
• 2014

There are various high-performance algorithms in the area of the existing VDSs (vehicle detection systems). However, they requires a large amount of computational time-complexity and their systems generally are very expensive and consumes high-power. This paper proposes real-time traffic information detection algorithm that can be applied to low-cost, low-power, and open development platform such as Android. This algorithm uses a vehicle's sub-shadow to set ROI(region of interest) and to count vehicles using a location of the sub-shadow and the vehicle. The proposed algorithm is able to count the vehicles per each roads and each directions separately. The experiment result show that the detection rate for going-up vehicles is 94.1% and that for going-down vehicles is 97.1%. These results are close to or surpasses 95%, the detection rate of commercial loop detectors.

• Journal of Software Assessment and Valuation
• /
• v.17 no.2
• /
• pp.75-81
• /
• 2021

Since plant growth is greatly influenced by moisture, it is important to control the soil to have optimal moisture for the plant being grown. Recently, researches on automatically analyzing plant growth information including soil moisture using spectral images are being conducted. However, hyperspectral images are difficult to use due to huge amount of data appearing in spectral bands. In this paper, we propose a method to solve the complexity of hyperspectral images using a CNN. Since the proposed method automatically analyzes the entire band of the target hyperspectral using deep learning, there is no need to make an effort to find a specific band for analysis of each image. In order to show the effectiveness of the proposed system, we conduct an experiment to analyze moistures using hyperspectral images obtained from soil.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.05a
• /
• pp.283-283
• /
• 2004

공장자동화는 국제사회 속에서 살아 남기 위한 필수 요건이 되었다. 값싼 인건비를 무기로 제품 경쟁에 뛰어 들고 있는 주변국가와 경쟁하기 위해서는 인건비 절감과 품질 향상이 필수적이다. 본 논문은 POS용 키보드의 생산공정 중에서 조립된 키보드 칼라 라벨을 자동 검사하는 시스템 개발을 최종목표로 하였다. 현재, 산업용으로 폭 넓게 사용되고 있는 머신 비전 측정시스템은 흑백의 영상과 비교적 간단한 물체에 초점을 맞추고 있다. 그러나, Fig.1의 POS용 키보드는 일반 컴퓨터용 키보드와는 달리 각각의 키가 칼라 라벨로 되어있기 때문에 기존의 흑백 머신 비전 시스템으로 자동화를 구축하기는 힘들다.(중략)