• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2004.11a
• /
• pp.195-202
• /
• 2004

일반적으로 운송 컨테이너의 식별자들은 크기나 위치가 정형화되어 있지 않고 외부 잡음으로 인하여 식별자의 형태가 변형될 수 있기 때문에 일정한 규칙으로 찾기는 힘들다. 본 논문에서는 이러한 특성을 고려하여 컨테이너 영상에 대해 Canny 마스크를 이용하여 에지를 검출하고, 검출된 에지 정보에서 영상획득 시 외부 광원에 의해 수직으로 길게 발생하는 잡음들을 퍼지추론 방법을 적용하여 제거한 후에 수직 블록과 수평 블록을 검출하여 컨테이너의 식별자 영역을 추출하고 이진화 한다. 이진화된 식별자 영역에 대해 검정색의 빈도수를 이용하여 흰바탕과 민바탕을 구분하고 윤곽선 추적 알고리즘을 적용하여 개별 식별자를 추출한다. 추출된 개별 식별자의 인식은 개선된 퍼지 RBF 네트워크를 제안하여 적용한다. 제안된 퍼지 RBF 네트워크는 퍼지 C-Means 알고리즘을 중간층으로 적용하고 중간층과 출력층 간의 학습에는 일반화된 델타 학습 방법과 Delta-bar-Delta 알고리즘을 적용하여 학습 성능을 개선한다. 실제 컨테이너 영상을 대상으로 실험한 결과, 기존의 식별자 추출 방법보다 제안된 식별자 추출 방법이 개선되었고 기존의 퍼지 RBF 네트워크 보다 제안된 퍼지 RBF 네트워크가 컨테이너 식별자의 학습 및 인식에 우수함을 확인하였다.

• Proceedings of the IEEK Conference
• /
• 2000.11b
• /
• pp.112-115
• /
• 2000

This paper describes the algorithm, architecture and design of the circuit implementing motion tracing features based on the edge detection. The Sobel operation was used to compute the edges of moving objects. Motion tracing is performed by searching for the center of the edges for each frame and adding those centers. The edger and the centers of the moving object from camera were displayed in the monitor and verified using Xillinx FPGA.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.472-474
• /
• 2002

본 논문에서는 복잡한 영상에서 얼굴 영역의 윤곽선을 검출하는 방법을 제안하였다. 이를 위하여 얼굴의 칼라 정보에 기반한 액티브 컨투어 모델을 이용하였다. 얼굴의 칼라 정보는 색채칼라 공간(chromatic color space)에서 2D-Gaussian모델로 나타내어지는 스킨 칼로 모델로 표현 되었다. 실험결과 제안된 방법은 복잡한 영상뿐 아니라 잡음이 많은 영상에서 하나 또는 여러 개의 얼굴 영역을 추출할 수 있었다.

• Journal of Korea Multimedia Society
• /
• v.7 no.1
• /
• pp.27-34
• /
• 2004

This thesis proposes a face detection algorithm using the color and edge informations in color image. The proposed algorithm segments skin color by Cb and Cr in YCbCr coordinates. Then face candidate regions are made after morphological filtering and labeling. For the regions, the Sobel vortical operation and horizontal projection are performed in the Y luminance components. The peak value indicates the eye location. Similarly, the chin location is detected by the Sobel horizontal operation and horizontal projection. The computer simulation shows that the proposed method gains similar detection rates of previous method and prevent facial region from including neck by detection of chin.

• Journal of KIISE:Software and Applications
• /
• v.34 no.5
• /
• pp.447-454
• /
• 2007

TFT-LCD(Thin Film transistor liquid crystal display) has become actively used front panel display technology with increasing market. Intrinsically there is region of non uniformity with low contrast that to human eye is perceived as defect. As the gray level difference between the defect and the background is hardly distinguishable, conventional thresholding and edge detection techniques cannot be applied to detect the defect. Between the patterned and un-patterned LCD defects, this paper deals with un-patterned LCD defects by using independent component analysis, adaptive thresholding and skewness. Our method showed strong results even on noised LCD images and worked successfully on the manufacturing line.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.2
• /
• pp.462-466
• /
• 2005

The extraction and recognition of shipping container's identifier is difficult since the scale or the location of identifiers are not fixed-form and input images have some external noises. In this paper, based on these facts, first, edges are detected from input images using canny masking, and regions of container's Identifiers are extracted by applying horizontal and vertical histogram method to canny masked images. We use a fuzzy thresholding method to binaries the extracted container's identifier regions, and contour tracking algorithm to extract individual identifiers. In experimental results, we confirmed that the proposed method is superior In performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.5 no.10
• /
• pp.497-502
• /
• 2016

Shape Contexts Recognition(SCR) is a technology recognizing shapes such as figures and objects, greatly supporting technologies such as character recognition, motion recognition, facial recognition, and situational recognition. However, generally SCR makes histograms for all contours and maps the extracted contours one to one to compare Shape A and B, which leads to slow progress speed. Thus, this paper has made simple yet more effective algorithm with optimized contour, finding the outlines according to shape figures and using the improved Douglas-Peucker algorithm and Harris corner detector. With this improved method, progress speed is recognized as faster.

• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.257-266
• /
• 2004

This paper proposes caricature generation system that uses shading mechanism that extracts textural features of face. Using this method, we can get more realistic caricature. Since this system If vector-based, the generated character's face has no size limit and constraint. so it is available to transform the shape freely and to apply various facial expressions to 2D face. Moreover, owing to the vector file's advantage, It can be used in mobile environment as small file size This paper presents methods that generate vector-based face, create shade and synthesize the shade with the vector face.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.137-139
• /
• 2011

영상에서의 경계선 추출은 원 영상의 노이즈에 의해 크게 영향을 받는다. 따라서 먼저 그 노이즈들을 제거할만한 어떤 방법들이 필요하다. Mean Shift 알고리즘은 이러한 목적에 부합되는 유연한 함수로서, 별로 중요하지 않은 정보와 민감한 노이즈 부분을 점점 제거하는데 알맞다. 여기서는 Canny 알고리즘을 사용하여 중점으로 하는 영상에서의 윤곽선을 찾아낸다. 그리고 테스트 하고 이전의 유일한 Canny 알고리즘 보다 결과가 좋음을 알아낸다.

• Journal of Korea Multimedia Society
• /
• v.6 no.2
• /
• pp.224-229
• /
• 2003

In this paper, an effective skeleton method is proposed in order to obtain an enhanced digital image of skeleton line. The edge-detection method is applied in the preprocessing stage and after that, the modified Parallel method is applied to obtain the improved image of skeleton line. The existing parallel methods are Zhang, Lu and Wang, and Paul methods. Firstly, a parallel process method Is applied, and the proposed method is applied that the original is compared with the four neighbor pixels and four corner pixels of mask. In conclusion, the proposed method shows an improved connectivity and quality of skeleton line.