• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.1403-1407
• /
• 2007

The bogie of Rolling Stock is the basic rolling component. It operates the train body, guides the body considering various tracks and offers comfort to passengers. We can verify the safety level of bogie about all factors through the first -grade scenario of Preliminary Hazard Analysis, but especially the horizontal acceleration sensor, equipped in each power bogie and trailer bogie, is the device, which makes it possible to test bogie instability and uncomfortable body movements by the method, similar to actual train driving, and in this context the necessity of this device becomes important. This paper would classify the main functions of driving sub system and examine the reliability, availability, maintainability and safety, which are main factors of RAMS. Especially, we would realize the bogie instability sensor with a simulator and offer the content in analyzing the data by the statistical method, which are obtained through the connected test with OBCS.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.23 no.58
• /
• pp.1-16
• /
• 2000

To develop a generic ERP(Enterprise Resource Planning) system which can accommodate various types of manufacturing enterprises, object-oriented methods are commonly applied from analysis to implementation. The objective of OO-ERP (Object-Oriented ERP) systems is the reusability of business objects(components). In practice, one of the critical features for the reusable OO-ERP system would be the capability of interfacing with distributed, heterogeneous data repositories. Consequently, it is essential to provide data repository transparency in OO-ERP systems - business objects do not take care of the locations and types of data repositories. In this paper, we propose Data Object Layer(DOL) that supports such transparency. DOL is a horizontal component through which OO-ERP systems can be seamlessly connected with diverse data repositories.

• Proceedings of the KIEE Conference
• /
• 1995.07b
• /
• pp.1002-1005
• /
• 1995

This paper presents an enhanced preprocessing and recognition algorithm for automatic vehicle license plate recognition system. The algorithm first applies horizontal gradient filter followed by thresholding and mathematical morphology operation for preprocessing. The final stage of the preprocessing is the application of connected component analysis in order to estimate the license plate region. For the recognition of the serial numbers of the plates, we developed a very effective algorithm. We call this zerocrossing count algorithm. This paper presents a detail of this algorithm and compare the performance with a template matching algorithm which utilizes correlation coefficient.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.805-808
• /
• 2001

본 논문은 비디오 영상에서 내용 기반 검색을 위한 비디오 텍스트를 검출하는 방법을 제안한다. 영어와 달리 한글과 같이 다중 분할된 문자가 포함된 비디오 텍스트를 자동으로 검출하기 위해 형태와 크기 및 위치 정보를 이용하고 이러한 정보들은 K-mean 클러스트링 알고리즘을 이용해 얻어진 템플릿의 형태로 표현 된다. 연결 성분 분석(connected component analysis)방법을 통해 비디오 영상을 분할하고, 잡음을 제거한 후 정확한 문자 성분을 검출하기 위해 클러스터 기반의 템플릿 매칭을 한다. 제안된 방법은 정확도와 에러율에서 기존의 방법보다 효과적 이었다.

• Proceedings of the KIEE Conference
• /
• 2003.07b
• /
• pp.1353-1355
• /
• 2003

Total six units of 3kW photovoltaic (PV) system and data acquisition system (DAS) are constructed for analyzing performance of PV system at field demonstration test center of Gwang-Ju in Korea. As climatic and irradiation conditions are varied, operation characteristics of the PV system are collected and analyzed in data-acquisition system. Furthermore, not only performance test of each PV system component such as PV module and power conditioning system, but also performance of total PV system e.g. system efficiency, electric power and loss factor at the site are reviewed.

• Proceedings of the KOSOMBE Conference
• /
• v.1996 no.11
• /
• pp.357-362
• /
• 1996

A way of quantitatively describing the tissue architecture we have investigated when developing a computer program for malignancy grading of transitional cell bladder carcinoma. The minimum spanning trees, MST was created by connecting the center points of the nuclei in the tissue section image. These nuclei were found by thresholding the image at an automatically determined threshold followed by a connected component labeling and a watershed algorithm for separation of overlapping nuclei. Clusters were defined in the MST by thresholding the edge lengths. For these clusters geometric and densitometric features were measures. These features were compared by multivariate statistical methods to the subjective grading by the pathologists and the resulting correspondence was 85% on a material of 40 samples.

• Smart Media Journal
• /
• v.5 no.3
• /
• pp.30-34
• /
• 2016

Nowadays, there are a lot of Korean documents, which often need to be identified in one of printed or handwritten text. Early methods for the identification use structural features, which can be simple and easy to apply to text of a specific font, but its performance depends on the font type and characteristics of the text. Recently, the bag-of-words model has been used for the identification, which can be invariant to changes in font size, distortions or modifications to the text. The method based on bag-of-words model includes three steps: word segmentation using connected component grouping, feature extraction, and finally classification using SVM(Support Vector Machine). In this paper, bag-of-words model based method is proposed using SURF(Speeded Up Robust Feature) for the identification of machine printed and handwritten text in Korean documents. The experiment shows that the proposed method outperforms methods based on structural features.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07b
• /
• pp.850-852
• /
• 2005

차량을 포함하는 임의의 영상에서 번호판 추출은 다양한 조명조건 및 배경, 촬영 각도, 번호판 종류 등의 요인으로 인해 고도의 영상처리 과정을 필요로 한다. 본 논문에서는 실제 환경에서 발생할 수 있는 이러한 요인들에 대해 강건한 번호판 추출 방법을 제안한다. 제안하는 방법은 입력영상의 RGB 성분들을 색상성분과 영암성분으로 분리할 수 있는 칼라모델 HSI로 변환하고 H(hue)와 S(saturation)성분을 이용하여 번호판의 배경색상을 고려한 칼라 퍼지지도를 구성한다. 또한, I(intensity)성분을 이용하여 에지밀도를 추출하고 에지밀도 지도에 기반한 영역분리 퍼지지도를 생성한다. 마지막으로, 후보영역 탐색을 위해 칼라 퍼지지도와 영역분리 퍼지지도를 결합하고, 연결성분 해석(Connected Component Analysis)을 통해 ROI(Region Of Interest)를 추출한다. 제안하는 방법의 유효성 검증을 위해 조명 및 촬영 각도에 제한을 거의 두지 않고 촬영된 차량 영상 410장을 실험 영상으로 사용하였다. 실험 결과에서는 $97.1\%$의 효과적인 추출 성공률을 볼 수 있었다.

• Journal of the Semiconductor & Display Technology
• /
• v.9 no.2
• /
• pp.79-85
• /
• 2010

In this paper, we propose a web inspection system (WIS) for real-time detection of paper defects which can cause critical fractures during papermaking process. Our system incorporates high speed line-scan camera, lighting system, and detection algorithm to provide robust and precise detection of paper defects in real-time. Since edge defects are very crucial to the paper fractures, our system focuses on the edge region of the paper instead of inspecting the whole paper area. In our algorithm, image projection and sub-pixel operation are utilized to detect the edge defects precisely and connected component labeling and shape analysis techniques are adopted to extract various kinds of the region defects. Experimental results revealed that our web inspection system is very efficient for detecting paper defects during papermaking processes.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.2
• /
• pp.41-46
• /
• 2018

This paper proposes a new method for the number recognition on dot matrix LED display. The proposed method uses morphological processing that dilates dots of numbers and connects the dots into strokes. The size of numbers is normalized using horizontal projection because the gaps of dots are different according to the size of numbers. The numbers are segmented by connected component analysis and finally, template matching method recognizes the segmented numbers. The proposed method is implemented using C language in Raspberry Pi system with a camera module for a real-time image processing. Experiments were conducted by using various dot matrix LED displays. The results show that the proposed method is successful for the number recognition on dot matrix LED display.