• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.919-920
• /
• 2008

In this paper, we present early processing techniques for visual inspection of metallic parts. Since metallic surfaces give rise to specular reflections, it is difficult to extract object boundaries using elementary segmentation techniques such as edge detection or binary thresholding. In this paper, we present two techniques for finding object boundaries on micro bit images. First, we explain a technique for detecting blade boundaries using a directional correlation mask. Second, a line and angle extraction technique based on Harris corner detector and Hough transform is described. These techniques have been effective for detecting blade boundaries, and a number of experimental results are presented using real images.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1891-1894
• /
• 2003

본 논문에서는 분할 영상 좌보계 (split image coordinate: SIC)를 제안하여 3차원 영상의 주요 특징 중의 하나인 유, 무한 소실점을 그 위치의 무한성이나 카메라의 보정과 관계없이 정확하게 자동 추출하였다. 제안한 방법에서는 가우시안 구 (Gaussian sphere) 기반의 기존 방법들과는 달리 영상 공간을 누적 공간으로 활용함으로써 카메라 보정이나 영상의 사전정보가 없어도 원 영상의 정보 손실 없이 소실점을 추출할 수 있고, 영상을 무한대까지 확장한 후 분할하여 재정의 함으로써 유, 무한 소실점을 모두 추출할 수 있도록 하였다. 정확한 소실점의 검출을 위하여 직선 검출 과정에서는 방향성 마스크 (mask)를 사용하였으며, 직선들의 군집화 (clustering) 과정에서는 기울기 히스토그램 방법과 수평/수직 군집화 방법을 적응적으로 적용하였다. 제안한 방법을 합성 영상 및 건축물 (man-made environment) 영상에 적용시켜 유, 무한 소실점들을 효과적이고 정확하게 찾을 수 있음을 확인하였다.

• Journal of Internet Computing and Services
• /
• v.5 no.1
• /
• pp.59-66
• /
• 2004

Symmetry region searching can extract face region without a prior information in an image by using symmetric. However, this method requires a plenty of the computation time because the mask size to process symmetry region searching must be larger than the size of object such as eye, nose and mouth in face. in this paper, it proposed symmetric by using symmetry region searching and Wavelet Transform to reduce computation time of symmetry region searching, and It was applied to this method in an original image. To extract exact face region, we also experimented face region searching by using domain division in extraction region.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.11a
• /
• pp.273-275
• /
• 2011

본 논문에서는 허프변환 및 HSV 색변환을 이용한 효율적인 차선검출의 최적화 알고리즘을 제안한다. 차선 검출의 고속화를 위해 차선과 카메라의 위치를 감안하여 고정된 관심영역(ROI_LB)을 정하고 검출 영역을 감소시킨다. 정해진 관심영역 내에서 허프변환을 적용해 차선을 검출하고 이를 위해 Sobel Mask와 Threshold를 사용한다. 또한, HSV 색 공간을 이용하여 황색 선과 백색 선을 구별해내며 차선 이동 시에 "MOVEMENT"이라는 문자열을, 중앙선을 넘어가면 "DANGEROUS"이라는 문자열을 출력한다. 제안하는 방법의 실험 결과는 복잡한 도로 동영상에서 효과적으로 차선을 인식하고 색 구별을 하였으며 제안 방법의 유효성을 검증하기 위해 다양한 실제 차선 패턴을 대상으로 한 실험결과를 제시한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.7
• /
• pp.625-631
• /
• 2010

This paper proposes lane recognition algorithm using lane prominence technique to extract lane candidate. The lane prominence technique is combined with embossing effect, lane thickness check, and lane extraction using mask. The proposed lane recognition algorithm consists of preprocessing, lane candidate extraction and lane recognition. First, preprocessing is executed, which includes gray image acquisition, inverse perspective transform and gaussian blur. Second, lane candidate is extracted by using lane prominence technique. Finally, lane is recognized by using hough transform and least square method. To evaluate the proposed lane recognition algorithm, this algorithm was applied to the detection of lanes in the rainy and night day. The experiment results showed that the proposed algorithm can recognize lane in various environment. It means that the algorithm can be applied to lane recognition to drive unmanned vehicles.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.1272-1273
• /
• 2009

We demonstrate conformal phosphor coating and patterning methods on light emitting diodes (LEDs) using image processing based optofluidic maskless lithography (IP-OFML) system in microfluidic channels. IP-OFML allows a real-time detection and dynamic mask generation for packaging of randomly dispersed microchips. Our system detects each chip by considering rotation of the chip through image processing regardless of their arrangement error. Therefore, it precisely packages the chip making conformal polymer layer.

• Journal of Sensor Science and Technology
• /
• v.14 no.5
• /
• pp.357-361
• /
• 2005

Low-stress silicon nitride (LSN) thin films with embedded metal line have been developed as free standing structures to keep microspheres in proper locations and localized heat source for application to a chip-based sensor array for the simultaneous and near-real-time detection of multiple analytes in solution. The LSN film has been utilized as a structural material as well as a hard mask layer for wet anisotropic etching of silicon. The LSN was deposited by LPCVD (Low Pressure Chemical Vapor Deposition) process by varing the ratio of source gas flows. The residual stress of the LSN film was measured by laser curvature method. The residual stress of the LSN film is 6 times lower than that of the stoichiometric silicon nitride film. The test results showed that not only the LSN film but also the stack of LSN layers with embedded metal line could stand without notable deflection.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.24 no.1
• /
• pp.97-101
• /
• 1987

The edge, a discontinuity or abrupt change in the gray-level or color, is a fundamentally important primitive feature of an image necessary for the image analysis and classification. Two-dimensional 3x3 compass gradient operators (ex. Sobel, Prewitt, and Kirsch operators)are commonly used in the edge detection and usually detect 8 compass directional components. In this paper, we present a new interpretation of the relationships between the resulting 8 gradient magnitudes and the 8 intensity values of neighboring pixels which are covered by the two-dimensional 3x3 mask. It is expected that a new gradient edge operator may be designed by changing the eigenvalues in the transform domain and the fast optical edge operator may be implemented by using the optical system.

• Journal of Korea Multimedia Society
• /
• v.25 no.4
• /
• pp.568-574
• /
• 2022

In this paper, direction normalization and CNN deep learning are used to develop a more reliable license plate recognition system. The existing license plate recognition system consists of three main modules: license plate detection module, character segmentation module, and character recognition module. The proposed system minimizes recognition error by adding a direction normalization module when a detected license plate is inclined. Experimental results show the superiority of the proposed method in comparison to the previous system.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.325-327
• /
• 2021

코로나19 전염병 예방을 위한 공공장소에서의 마스크 착용이 의무화되고 있다. 그러나 사람들이 다양한 이유로 마스크를 제대로 착용하지 않아 감염에 노출되는 위험이 발생하고 있다. 이러한 방역 문제를 해결하고 본 논문은 영상을 인식하여 마스크를 쓴 얼굴과 쓰지 않은 얼굴을 검출하는 방식을 제안한다. 제안 방법은 마스크 착용자와 비착용자 얼굴 영상을 딥러닝 기반의 YOLO 네트워크로 학습하여, 마스크 착용 유무를 판별한다. 동일 YOLO 네트워크에 대해 여러가지 조건으로 학습을 수행하고, 학습에 사용되지 않은 검증 데이터를 이용해 정확도가 가장 높은 네트워크의 가중치를 선택하였다. 실험결과, 마스크 착용자는 67.2%, 미착용자는 39.8%의 판별 정확도를 보였다. 미착용자에 대해 낮은 정확도를 보인 이유는 학습 데이터의 부족으로 판단되며, 이를 보완하기 위하여 더 많은 학습데이터를 제작하여 성능을 개선시키고자 한다.