• Journal of Internet Computing and Services
• /
• v.21 no.6
• /
• pp.23-31
• /
• 2020

This study was carried out to generate various images of railroad surfaces with random defects as training data to be better at the detection of defects. Defects on the surface of railroads are caused by various factors such as friction between track binding devices and adjacent tracks and can cause accidents such as broken rails, so railroad maintenance for defects is necessary. Therefore, various researches on defect detection and inspection using image processing or machine learning on railway surface images have been conducted to automate railroad inspection and to reduce railroad maintenance costs. In general, the performance of the image processing analysis method and machine learning technology is affected by the quantity and quality of data. For this reason, some researches require specific devices or vehicles to acquire images of the track surface at regular intervals to obtain a database of various railway surface images. On the contrary, in this study, in order to reduce and improve the operating cost of image acquisition, we constructed the 'Defective Railroad Surface Regeneration Model' by applying the methods presented in the related studies of the Generative Adversarial Network (GAN). Thus, we aimed to detect defects on railroad surface even without a dedicated database. This constructed model is designed to learn to generate the railroad surface combining the different railroad surface textures and the original surface, considering the ground truth of the railroad defects. The generated images of the railroad surface were used as training data in defect detection network, which is based on Fully Convolutional Network (FCN). To validate its performance, we clustered and divided the railroad data into three subsets, one subset as original railroad texture images and the remaining two subsets as another railroad surface texture images. In the first experiment, we used only original texture images for training sets in the defect detection model. And in the second experiment, we trained the generated images that were generated by combining the original images with a few railroad textures of the other images. Each defect detection model was evaluated in terms of 'intersection of union(IoU)' and F1-score measures with ground truths. As a result, the scores increased by about 10~15% when the generated images were used, compared to the case that only the original images were used. This proves that it is possible to detect defects by using the existing data and a few different texture images, even for the railroad surface images in which dedicated training database is not constructed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.9
• /
• pp.2145-2152
• /
• 2013

Paper manufacturing industries have huge facilities with automatic equipments. Especially, in order to improve the efficiency of the paper manufacturing processes, it is necessary to detect the paper cutting defect effectively and to classify the causes correctly. In this paper, we review the problems of web monitoring system and web inspection system that have been traditionally used in industries for defect detection. Then we propose a novel paper cutting defect detection method based on the local binary pattern analysis and its implementation to mitigate the practical problems in industry environment. The proposed algorithm classifies the defects into edge-type and region-type and then it is shown that the proposed system works stably on the real paper cutting defect detection system.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.35 no.3
• /
• pp.193-199
• /
• 2015

Active thermography techniques have the capability of inspecting a broad range simultaneously. By evaluating the phase difference between the defected area and the healthy area, the technique indicates the qualitative location and size of the defect. Previously, the development of the defect detection method used a variety of materials and the test specimen was done. In this study, the proposed technique of lock-in is verified with artificial specimens that have different size and depth of subsurface defects. Finally, the defect detection capability was evaluated using comparisons of the phase image and the amplitude image according to the size and depth of defects.

• Proceedings of the KIEE Conference
• /
• 2002.07c
• /
• pp.1797-1799
• /
• 2002

$SF_6$ 가스로 절연되는 GIS (Gas Insulated Switchgear)는 매우 우수한 신뢰성을 확보하고 있지만 사고 발생 시 파급효과가 매우 크므로 상시 감시할 수 있는 진단기술이 요구된다. 본 논문에서는 GIS 내부에서 발생하는 신호를 검출하기 위해서 전기적인 방법과 비전기적인 측정 법을 통해 전자파. 초음파, 전류펄스를 측정하고 비교하였다. GIS 내부알루미늄도체에 침 결함을 고정시켜 전원전압 인가 시 발생되는 부분방전신호를 UHF, AE, CT센서로 검출하였다. 측정 결과 UHF센서와 CT센서로 검출되어진 신호는 매우 유사하게 측정되었고 초음파와 전자파를 검출한 결과 진행속도 차이로 발생되는 시간지연현상이 발생되었다. GIS내 부분방전발생 시 발생되는 전자파 스펙트럼 분석결과도 650MHz에서부터 935MHz까지의 주파수대역이 측정되었다. 이후에는 현장에서 운전중인 GIS내부에서 발생되는 결함들을 실제와 가깝게 모델링하여 발생되는 부분방전신호를 스펙트럼 분석하여 대역에 맞는 UHF센서 개발에 노력하고자 한다. 또한 결함의 종류와 형태에 따라 다르게 발생되는 부분방전신호를 검출하여 측정하고 이를 진단하는 연구가 계속 진행되어야 할 것으로 사료된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.10
• /
• pp.1195-1200
• /
• 2019

This paper proposes a detection algorithm for group testing. Group testing is a problem of finding a very small number of defect samples out of a large number of samples, which is similar to the problem of Compressed Sensing. In this paper, we define a noiseless group testing and propose a probabilistic algorithm for detection of defective samples. The proposed algorithm is constructed such that the extrinsic probabilities between the input and output signals exchange with each other so that the posterior probability of the output signal is maximized. Then, defective samples are found in the group testing problem through a simulation on the detection algorithm. The simulation results for this study are compared with the lower bound in the information theory to see how much difference in failure probability over the input and output signal sizes.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.869-873
• /
• 2007

본 논문은 고속으로 생산되는 제품의 영상을 캡쳐한 후 영상처리 기법 중 에지 추출 알고리즘을 응용하여 조명에 투과된 제품의 에지를 추출 및 필터링 하는 방법으로 결함 검출 시스템을 설계한다. 소형의 임베디드 기기에 패턴 매칭 영상처리 기법을 이용하여 결함을 검출하고 패턴의 비 매칭 정도를 기준점에 따라 정상 또는 불량 판정을 할 수 있는 어플리케이션을 개발하고 탑재하였고, 어플리케이션의 불량 판정 알고리즘으로는 NGC (Normalized GrayScale Corelation) 기법을 사용하였고 검출 판정 결과 적절한 판정값을 입력하는 것으로 기준 패턴과 형상이 다른 대상의 불량을 판정한다.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.20 no.6
• /
• pp.26-34
• /
• 2006

In this paper, We proposed he algorithm for defect extraction and a study of the stereo image modeling o inspect defect for the ball height of BGA(ball grid way) device using 2-dimensional images captured by the BGA device of using the high resolution CCD cameras. This paper propose the package/ball area extraction of BGA device part, the FOV(field of view) calibration part, the top point matching part, and ball height measurement method. Each BGA device propose extraction method by defect, Through the experiment, we verified the result.

• Proceedings of the KAIS Fall Conference
• /
• 2010.11a
• /
• pp.430-433
• /
• 2010

최근 모바일 기기로 획득된 영상을 이용한 다양한 분야의 연구가 활발히 진행되고 있으며, 스마트폰의 보급이 확대되면서 증강현실을 지원하고자 자연영상으로부터 문자정보를 추출 및 인식하여 이미지 검색을 가능하도록 하는 많은 연구도 진행되고 있다. 자연영상에서 한글문자 영역 검출은 한글문자 인식을 위한 전단계로서 다양한 환경에 노출된 문자영역을 정확히 검출하는 것이 인식 성능을 결정함으로 중요한 전처리 단계이다. 본 연구는 한글문자 영역의 에지 및 지역적 연결요소 성분 특징을 이용하여 한글문자 영역을 검출하는 방법을 제안한다. 에지 및 연결요소 성분의 특징을 검출하고, 그 결과를 레이블화하고 이를 분석함으로서 한글문자 후보 영역을 검출한다. 검출된 후보영역은 검증과정을 수행하여 최종적인 한글문자 영역을 추출한다. 제안한 방법은 다양한 환경에서 얻어진 자연영상을 대상으로 실험한 결과, 에지 및 연결요소 성분의 두 가지 특징을 결합함으로서 한글 문자영역 검출의 정확도를 향상하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2007.05a
• /
• pp.315-318
• /
• 2007

자동 얼굴 인식, 표정 인식과 같은 얼굴 영상과 관련된 다양한 연구 분야는 일반적으로 입력 얼굴 영상에 대한 정규화가 필요하다. 사람의 얼굴은 표정, 조명 등에 따라 다양한 형태변화가 있어 입력 영상 마다 정확한 대표 특징 점을 찾는 것은 어려운 문제이다. 특히 감고 있는 눈이나 작은 눈 등은 검출하기 어렵기 때문에 얼굴 관련 연구에서 성능을 저하시키는 주요한 원인이 되고 있다. 이에 다양한 변화에 강건한 눈 검출을 위하여 본 논문에서는 눈의 텍스처 정보를 이용한 눈 검출 방법을 제안한다. 얼굴 영역에서 눈의 텍스처가 갖는 특성을 정의하고 두 가지 형태의 Eye 필터를 정의하였다. 제안된 방법은 Adaboost 기반의 얼굴 영역 검출 단계, 조명 정규화 단계, Eye 필터를 이용한 눈 후보 영역 검출 단계, 눈 위치 점 검출 단계 등 총 4단계로 구성된다. 실험 결과들은 제안된 방법이 얼굴의 자세, 표정, 조명 상태 등에 강건한 검출 결과를 보여주며 감은 눈 영상에서도 강건한 결과를 보여준다.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.33 no.1
• /
• pp.34-39
• /
• 2013

In the advanced research deducted infrared thermography (IRT) test using 4 inch pipe with artificial wall-thinning defect to measure on the wall-thinned nuclear pipe components. This study conducted for defect detection condition of nuclear small-bore pipe research using deducted condition in the advanced research. Defect process is processed by change for defect length, circumferential direction angle, wall-thinning depth. In the used equipment IR camera and two halogen lamps, whose full power capacitany is 1 kW, halogen lamps and Target pipe experiment performed to the distance of the changed 1 m, 1.5 m, 2 m. To analysis of the experimental results ensure for the temperature distribution data, by this data measure for defect length. artificial defect of 4 inch pipe is high reliability in the 2 m, but small-bore pipe is in the 1.5 m from the defect clearly was detected.