• Proceedings of the Korean Society of Computer Information Conference
• /
• 2009.01a
• /
• pp.223-226
• /
• 2009

유해 영상 검출은 유해 동영상을 내용 기반으로 검색하고 차단하기 위한 방법의 하나로써, 유해 동영상 추적 시스템의 전체 성능을 좌우하는 중요한 기술이다. 기존의 유해 영상 검출은 웹 사이트 내에 음란 콘텐츠를 추출함으로 유해 사이트를 차단하는데 사용되었으며, 주로 RGB 비율, Histogram 등을 이용한 Skin color와 Edge를 추적한 Texture를 기반으로 유해 영상을 검출하였다. 그러나 기존 방식은 UCC 유해 동영상과 같이 저화질 영상에서의 유해 여부를 판단하기에는 정확성이 낮다. 따라서 본 논문에서는 영상 크기에 따른 고/저화질 분류를 이용하여 동영상에서 보다 효과적인 유해 영상 검출할 수 있는 방법을 제안한다. 제안 방법의 성능을 확인하기 위해 고/저화질 분류 사용의 유/무에 따른 검출 실험을 하였으며, 그 결과 분류를 방법이 기존 방법보다 12%의 성능이 향상됨을 알 수 있었다.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.12
• /
• pp.60-70
• /
• 1999

An efficient automatic inspection system for Floating Seal is developed, The proposed system consists of a high resolution line scan camera, microcomputer, and PLC (Programmable Logic Controller). In order to perform rapid inspection, The ROI (Region of Interest) is extracted from the original image. There are types of defects; shape defects and surface defects. Each features of defects are captured by edge detect, segmentation, morphological operation, and threshold analysis. PLC controller is used to synchronize the whole system and store the inspection results temporarily to reduce the overhead of microcomputer. As a result, the system is being utilized successfully in a teal inspection line.

• Journal of electromagnetic engineering and science
• /
• v.13 no.1
• /
• pp.16-21
• /
• 2013

This study presents the angular effects of virtual vertices inserted for effective treatment of the boundary edge laid on an infinite conducting surface in a half-space scattering problem. We investigated the angular effects of virtual vertices by first computing the radar cross section (RCS) of a specific scatterer; i.e., a tilted conducting plate in contact with the ground surface, by inserting the virtual vertex in half-space. Here, the electric field integral equation is used to solve this problem with various virtual vertex angles (${\theta}_{\nu}$) and conducting plate inclination angles (${\theta}_r$) ranging from $0^{\circ}$ to $180^{\circ}$. The effects of the angles ${\theta}_{\nu}$ and ${\theta}_r$ on the RCS computation are clearly shown with numerical results with and without the virtual vertices in free- and half-spaces.

• Journal of information and communication convergence engineering
• /
• v.6 no.4
• /
• pp.444-447
• /
• 2008

In this paper, we proposed the recognition system of car license plates to mitigate traffic problems. The processing sequence of the proposed algorithm is as follows. At first, a license plate segment is extracted from an acquired car image using morphological features and color information, and noises are eliminated from the extracted license plate segment using line scan algorithm and Grassfire algorithm, and then individual codes are extracted from the license plate segment using edge tracking algorithm. Finally the extracted individual codes are recognized by an FCM algorithm. In order to evaluate performance of segment extraction and code recognition of the proposed method, we used 100 car images for experiment. In the results, we could verify the proposed method is more effective and recognition performance is improved in comparison with conventional car license plate recognition methods.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.11
• /
• pp.1103-1116
• /
• 1991

The characteristics of transform coefficients of discrete Gabor transform and the performances of their progressive coding are investiganted. The adaptive transform coding SAC is used for the progressive transmission. Exprerimental results show that although DGT has relatively low energy compaction property and coding efficiency, it yields good quality with greaty reduced block artifact and good edge at each stage of the progressive transmission.

• Proceedings of the KAIS Fall Conference
• /
• 2002.05a
• /
• pp.106-108
• /
• 2002

반도체 physical layout design rule이 작아짐에 따라 Proximity effect와 overlay가 Pattern 구현에 크게 영향을 미치고 있다. Metal layer와 contact의 부족한 overlay margin으로 overlay 불량이 발생하고, 감소한 space margin으로 인해 bridge와 같은 문제가 나타난다. 따라서, resolution을 향상시키고, 최소한의 overlay margin을 확보함으로써 미세 pattern의 구현을 가능하게 한다. 이를 위해 OPC와 attPSM 같은 분해능향상기술이 사용된다. 그러나 attPSM의 사용은 원하지 않는 pattern이 생성되는 sidelobe와 같은 문제가 발생한다. 따라서 serial image simulation올 통해 추출한 rule을 rule-based correction에 적용하여 sidelobe현상을 방지한다. 그리고 overlay margin 부족으로 나타나는 문제는 metal layer와 contact overlap되는 영역의 line edge를 확장하고, rule checking을 통해 최소한의 space margin을 확보하여 해결한다 따라서 overlay error를 rule-based correction을 사용하여 효과적으로 방지한다.

• Journal of the Korean Society for Precision Engineering
• /
• v.19 no.8
• /
• pp.108-115
• /
• 2002

In measuring step for reverse engineering of sculptured surfaces, computer vision system is used to simplify the complicated surface by boundary edge detection method that minimizes the measuring error. The measured data by Coordinate measuring machine is clouded data points of surfaces which is segmented surface using image process. In this research, the measured data is approximated as NURBS surfaces by new suggested algorithm. The position and number of control points, selection of parametric values and compensation of weight factors are proposed. Finally, surface model is simulated and improved resulting performance is obtained.

• International Journal of Contents
• /
• v.9 no.4
• /
• pp.16-21
• /
• 2013

Vision system is an indispensable part of constructing the chess-playing robot. Chessboard detection and pieces localization in the captured image of robot's camera are important steps for processes followed such as pieces recognition, move calculation, and robot controlling. We present a method for detecting the Janggi chessboard and pieces based on the edge and color feature. Hough transform combined with line extraction is used for segmenting the chessboard and warping it to form the rectangle shape in order to detect and interpolate the lines of chessboard. Then we detect the existence of pieces and their side by applying the saliency map and checking the color distribution at piece locations. While other methods either work only with the empty chessboard or do not care about the piece existence, our method could detect sufficiently side and position of pieces as well as lines of the chessboard even if the occlusion happens.

• The Journal of Korea Robotics Society
• /
• v.12 no.2
• /
• pp.217-227
• /
• 2017

Crosswalk detection is an important part of the Pedestrian Protection System in autonomous vehicles. Different methods of crosswalk detection have been introduced so far using crosswalk edge features, the distance between crosswalk blocks, laser scanning, Hough Transformation, and Fourier Transformation. However, most of these methods failed to detect crosswalks accurately, when they are damaged, faded away or partly occluded. Furthermore, these methods face difficulties when applying on real road environment where there are lot of vehicles. In this paper, we solve this problem by first using a region based binarization technique and x-axis histogram to detect the candidate crosswalk areas. Then, we apply Support Vector Machine (SVM) based classification method to decide whether the candidate areas contain a crosswalk or not. Experiment results prove that our method can detect crosswalks in different environment conditions with higher recognition rate even they are faded away or partly occluded.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.126-132
• /
• 2000

This paper presents a facial expression recognition based on Gabor wavelets that uses a fuzzy C-means(FCM) clustering algorithm and neural network. Features of facial expressions are extracted to two steps. In the first step, Gabor wavelet representation can provide edges extraction of major face components using the average value of the image's 2-D Gabor wavelet coefficient histogram. In the next step, we extract sparse features of facial expressions from the extracted edge information using FCM clustering algorithm. The result of facial expression recognition is compared with dimensional values of internal stated derived from semantic ratings of words related to emotion. The dimensional model can recognize not only six facial expressions related to Ekman's basic emotions, but also expressions of various internal states.