• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.8 no.6
• /
• pp.453-459
• /
• 2015

In this paper, we propose a new digit recognition method based on opened enclosure. In the proposed method, each digit is divided into two parts, an upper part and a lower part, which are based on a cutting line that is modified depending on the number of intersection points. In the simulation, the performance evaluation through the data acquisition and application of the proposed algorithm was carried out and the result was presented.

• Bulletin of the Korean Space Science Society
• /
• 2010.04a
• /
• pp.28.3-28.3
• /
• 2010

위성이 궤도를 운용함에 있어서 원으로 운용되는 저궤도(LEO)에서는 대기저항(Drag)에 의한 섭동 영향이 가장 크게 미친다. 이 연구에서는 대기저항 섭동에 의해 감소되는 위성의 고도를 전기추력기를 이용하여 고도를 유지할 때 이를 해석적인 측면에 대해 살펴보고 지구 관측 위성에서 많이 쓰이는 태양 동기 궤도(SSO)에 적용하여 궤도를 유지하는 방법에 대해 알아보았다. 태양활동에 의한 대기의 밀도변화를 John kennewell의 모델을 통해 예측하여 대기저항에 의해 감소되는 고도량을 구하고 위성에서 추력(thrust)을 줄 때는 Gaussian Variation of Parameters식을 이용하여 해석적인 방법으로 궤도 장반경의 증가량을 구하였다. 위성에 추력을 줄때 이심률이 증가하게 되는 문제는 구속조건으로 이심률 값의 최대 허용치를 정하여 증가하는 것을 방지하도록 하였다. 또한 $J_2$ 섭동에 의해 가장 영향을 받는 승교점(Ascending Node)과 추력에 의해 변화할 수 있는 근지점(Perigee)을 살펴보고 궤도 유지를 위한 적절한 추력 방향을 구하였다. 각각의 궤도 요소의 변화를 살펴보고 일반적인 태양 동기 궤도 위성의 제원을 이용하여 궤도 유지에 적용하였다. 저궤도 위성의 궤도 유지에 대한 복잡한 수치적인 방법으로 궤도요소의 변화를 정확하게 구하지만 해석적인 방법으로도 위성의 궤도 유지를 위한 정보를 얻을 수 있었다. 이를 저궤도 위성의 궤도 운용과 변화 예측에 적용할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1420-1423
• /
• 2015

기존의 영상처리 및 컴퓨터 비전 기술은 X-ray, 군사용 사진, CCTV 영상과 같은 제한적인 상황에서 주로 사용되었다. 스마트폰이 보급되면서 고해상도의 사진을 어디서든 촬영할 수 있게 되었고, 고성능 디바이스를 이용하여 촬영된 영상을 즉시 가공 및 처리가 가능하게 되었다. 그 결과 영상처리 기술이 이전보다 다양하고 좀 더 일반적인 분야에서도 쓰이게 되었다. 그러나 영상처리 기술은 조건이 제한될수록 처리가 용이하며, 일반적인 이미지들을 처리하기 위해서는 고려해야 할 사항이 많다. 특히 두피 영상 분석의 경우 머리카락이 겹치는 부분이나 그림자, 머리카락이 밀집하여 상대적으로 어두워지는 부분 등을 고려해야 하는 어려움이 있으며 현재까지 영상처리를 이용한 두피영상 분석에 대한 연구는 많지 않은 것이 현실이다. 본 논문에서는 스마트폰에 부착하는 포터블 카메라로 촬영된 두피영상을 분석하여 모발의 두께를 측정하는 기법을 제시한다. 먼저 영상에 대한 전처리로 Contrast stretching과 이 진화 과정을 수행한다. 얻어진 이진화 영상에 대해 머리카락의 Skeleton을 추출하고 각 pixel의 각도(angle)를 이용하여 법선을 구한다. 계산된 법선과 머리카락 사이의 교점을 구한 후 두 점사이의 거리를 통해 모발의 두께를 계산한다. 계산된 두께와 현미경을 이용하여 측정한 모발의 실제 두께와 비교하여 제안된 기법의 정확도를 평가한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1278-1290
• /
• 2008

This paper proposes a preprocessing method and a neural network based character recognizer to enhance the overall performance of the license plate recognition system. First, plate outlines are extracted by virtual line matching, and then the 4 vertexes are obtained by calculating intersecting points of extracted lines. By these vertexes, plate image is reconstructed as rectangle-shaped image by bilinear transform. Finally, the license plate is recognized by the neural network based classifier which had been trained using delta-bar-delta algorithm. Various license plate images were used in the experiments, and the proposed plate normalization enhanced the recognition performance up to 16 percent.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.29 no.1
• /
• pp.71-80
• /
• 2011

Thresholding is important step for detecting binary change/non-change information in the unsupervised change detection. This study proposes new unsupervised change detection method using Hyperion hyperspectral images, which are expected with data increased demand. A graph is drawn with applying the range average method for the result value through pixel-based similarity measurement, and thresholding value is decided at the maximum distance point from a straight line. The proposed method is assessed in comparison with expectation-maximization algorithm, coner method, Otsu's method using synthetic images and Hyperion hyperspectral images. Throughout the results, we validated that the proposed method can be applied simply and had similar or better performance than the other methods.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.4
• /
• pp.866-876
• /
• 1996

A feature extraction method for the objects that have a circular cross section is proposed.To implement a robust recognition system which can effectively deal with various types of 2-dimensional image and 3-dimensional image, both 2- dimensional information and 3-dimensional information should be collectively extracted and combined for the optimum. For this, this paper presents a feature extraction method for 3-dimensional objects, particularly for the objects with a circular cross section which most objects in the real world are known to have. Firstly, the Z gradient is proposed to extract the shape information from those objects. Using this information, normal vectors are derived from the surface patches. The intersection points between the vectors are applied to the geometric feature extraction.Also, for more accurate recognition, a feature extraction method for between surface regions is proposed.Finally, the extraction method of function information is investigated for the final recognition process.The usefulness of the proposed method is proved through the experimentation.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.7 no.6
• /
• pp.27-33
• /
• 1993

In order to improve complicated construction and complex control which are didvantage of optimal PWM technique aimed at harmonic elimination method, this paper presented MRA(Mode1 Reference Adaptive) PWM technique that gating signal of inverter is generated by comparing the reference signal with the induced feedback signal at the reference model of load. Design of controller is composed of microprocessor and analog circuit. MRA PWM technique used in the paper is able to compensate the degradation of voltage efficiency to be generated by the ratio of the output voltage to the DC supply voltage being low for using conventional sinusoidal PWM technique. When the trapezoidal signal is employed as the reference signal. the low order harmonics of line current can be reduced and the switching pattern is made by on-line computation using comparatively simple numerical analysis.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.2
• /
• pp.473-480
• /
• 2013

In this paper, location recognition algorithm is developed to improve the accuracy using improve Trilateration. The location recognition algorithm is first calculate the location refer to the measured signal power. Error can be occurred when measure distance with arranged node in specific location. If the distance data is received from node (receiver, coordinator), Node selected for location calculation is defined through section. If the distance data is received from node (receiver, coordinator), Node selected for location calculation is defined through section. Second, we apply algorithm of section filtering. If there are 4 sections in node, we consider 1 section to 6 location recognition coordinates. A special characteristic drawback of RF is that the actual distance is actually farther than the calculated received distance data. This is error is incurred when the signal strength increases. We reduce the location recognition error by applying an improved algorithm as secondary after filtering primary through section filtering.

• The KIPS Transactions:PartA
• /
• v.17A no.4
• /
• pp.189-196
• /
• 2010

This paper presents an improved marker detection algorithm using hybrid features such as corner, line segment, region, and adaptive threshold values, etc. In usual augmented reality environments, there are often marker occlusion and poor illumination. However, existing ARToolkit fails to recognize the marker in these situations, especially, partial concealment of marker by user, large change of illumination and dim circumstances. In order to solve these problems, the adaptive threshold technique is adopted to extract a marker region and a corner extraction method based on line segments is presented against marker occlusions. In addition, a compensating method, corresponding the marker size and center between registered and extracted one, is proposed to increase the template matching efficiency, because the inside marker size of warped images is slightly distorted due to the movement of corner and warping. Therefore, experimental results showed that the proposed algorithm can robustly detect the marker in severe illumination change and occlusion environment and use similar markers because the matching efficiency was increased almost 30%.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.18 no.3
• /
• pp.225-240
• /
• 2006

In order to calculate bending moments of rectangular plates with three edges clamped the other free subjected to both a uniform load and a triangular load, a finite difference equation for the non-dimensional governing equation are presented and numerical solutions with different aspect ratios and/or number of grid points are analyzed. The finite difference solutions are obtained by use of grid points up to 11,520 and the optimum grid points according to aspect ratios of the plate are presented as well. The obtained numerical solutions are shown to satisfy the given x moment boundary condition at the free edge, which can not be satisfied in Levy's analytical solutions and peculiar behaviour of the calculated moments is observed around the corners between the free edge and fixed ones. The numerical solutions of bending moments subjected to both a uniform load and a triangular load are compared with the corresponding analytical solutions which are shown in very good agreement on the solution domain except the neighborhood of the free edge.