• Proceedings of the Korea Multimedia Society Conference
• /
• 2004.05a
• /
• pp.163-166
• /
• 2004

본 논문은 3차원 형상 인식시스템으로부터 스캔 한 3차일 영상 데이터의 깊이정보에 3차원 에지를 추출하여 워터마크를 삽입하는 알고리즘을 제안한다. 제안한 알고리즘에서는 3차원 수직 평형 형상 인식기로 object scanning을 한 데이터 값들을 추출한다. 이 추출된 값들의 특성은 2차원 영상 즉 x, y축에 각각의 픽셀에 깊이정보를 가지는 3차원영상으로서 기존의 3차원영상과는 다른 차이를 가지며 영상의 품질이 우수하며 많은vertex 정보와 메쉬 정보를 가지고 있다. 따라서 획득된 데이터에서 x좌표와 y좌표는 영상에 있어서 위치를 나타내는 정보이고, T좌표는 3차원영상을 형성하는 깊이 정보들이다. 3차원 형상 인식시스템에서 스캔 한 3차원 얼굴영상으로부터 에지를 검출하여 에지가 존재하는 위치에 워터마크를 삽입하는 알고리즘을 제안하였다. 본 논문에서 제안한 워터마킹 알고리즘의 성능 평가를 위한 모의실험 한 결과 워터마크가 삽입된 모텔의 절단(cropping), 리메쉬(remesh) 및 메쉬간소화(mesh simplification) 공격에 대한 견고성이 우수함을 확인함으로써 3차원형상 인식 시스템에 직접적인 워터마크 삽입이 가능함을 증명하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.2 s.46
• /
• pp.53-62
• /
• 2007

In this paper, it can propose that Fuzzy Wavelet Morphology Neural Networks for the edge detection algorithm with being robustly a unclear boundary parts by brightness difference and being less sensitivity on direction to be detected the edges of images. This is applying the Fuzzy Wavelet Morphology Operator which can be simple the image robustly without the loss of data to DTCNN Structure for improving defect which carrys out a lot of operation complexly. Also, this color image can segment Y image with YCbCr space color model which has a lossless feature information of edge boundary sides effectively. This paper can offer the simulation of color images of 50ea for the performance verification of the proposal algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2001.10a
• /
• pp.600-602
• /
• 2001

본 논문은 웨이블릿 필터를 이용하여 홍채영상의 에지를 검출하고 패턴매칭 기법을 적용하여 홍채의 결함조직에 대한 위치를 추정하는 연구이다. 필터는 웨이블릿 변환을 이용한 2차원 주파수 영역의 고역통과 필터를 사용하여 홍채영상의 에지를 검출하고, 이를 표준진단패턴과 오버랩 매칭으로 결함조직을 검출한다. 실험결과 처리속도가 기존의 에지검출기법에 비해 처리속도향상과 에지검출영상의 PSNR 증가에 따라 오버랩 패턴매칭기법에 의한 인식률에서 92%로 홍채결함조직을 자동 진단시스템에 응용 가능하다.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.10
• /
• pp.35-47
• /
• 2010

To complement inaccurate edge information and detect correctly the boundary of a vehicle in an image, an extended edge analysis technique is presented in this paper. The vehicle is detected using the bottom boundary generated by a vehicle and the road surface and the left and right side boundaries of the vehicle. The proposed extended edge analysis method extracts the horizontal edge by merging or dividing the nearby edges inside the region of interest set beforehand because various noises deteriorates the horizontal edge which can be a bottom boundary. The horizontal edge is considered as the bottom boundary and the vertical edges as the side boundaries of a vehicle if the extracted horizontal edge intersects with two vertical edges which satisfy the vehicle width condition at the height of the horizontal edge. This proposed algorithm is more efficient than the other existing methods when the road surface is complex. It is proved by the experiments executed on the roads having various backgrounds.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.6
• /
• pp.19-27
• /
• 2010

This paper proposes a method for enhancing detection performance and reducing computational cost when detecting a human face by applying B-spline active contour to the frame difference of consecutive images. Firstly, the method estimates amount of user's motion using kurtosis. If the kurtosis is smaller than a pre-defined threshold, it is considered that the amount of user's motion is insufficient and thus the contour fitting is not applied. Otherwise, the contour fitting is applied by exploiting the fact that the amount of motion is sufficient. Secondly, for the contour fitting, difference edges are detected by combining the distance transformation of the binarized frame difference and the edges of current frame. Lastly, the face is located by assigning the contour fitting process to the detected difference edges. Kurtosis-based motion amount estimation can reduce a computational cost and stabilize the results of the contour fitting. In addition, distance transformation-based difference edge detection can enhance the problems of contour lag and discontinuous difference edges. Experimental results confirm that the proposed method can reduce the face localization error caused by the contour lag and discontinuity of edges, and decrease the computational cost by omitting approximately 39% of the contour fitting.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10c
• /
• pp.601-603
• /
• 2002

이 논문은 명암(grayScale)을 갖는 텍스트 문서 영상을 위한 새로운 워터마킹 알고리즘을 제안한다. 텍스트 문서 영상을 여러 블록으로 나누었을 때, 블록 영상들의 에지 방향 히스토그램이 유사하다는 부분 영상의 일관성이라는 특성을 갖는다. 이러한 특성을 이용하여 블록의 에지 방향 히스토그램을 조작하여 신호를 삽입한다. 다양한 공격에 대한 실험을 통하여 알고리즘의 강인성과 비인지성을 분석하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.683-686
• /
• 2010

본 논문은 영상 내에서 영역을 분할하여 영상 잡음을 효과적으로 제거하는 기법을 제안한다. 제안한 방법을 통해 잡음 영상을 영역 분할 경우 잡음부분까지 영역 분할되는 문제가 발생하기 때문에 잡음 영상을 저대역(Low-pass) 필터를 통과함으로써 잡음을 최소화한다. 저대역 필터를 통과한 영상에서 에지를 추출하여 비정상적인 에지의 추출을 방지함으로써 영상이 가진 근본적인 에지를 정확하게 추출한다. 획득한 에지 정보를 바탕으로 각 영역간의 히스토그램의 평균 오차를 이용하여 영역을 분할한다. 분할된 영역은 각 영역별로 저대역(Low-pass) 필터를 통과시킴으로써 영역에 맞는 잡음 제거를 통해서 더욱 빠르고 효과적으로 제거한다. 본 논문의 방법은 기존의 학습을 통한 잡음 제거 방법과 다르게 학습 시간이 요구되지 않으며, Non-local Means의 방법과 다르게 큰 연산량을 요구하지 않기 때문에 유사한 성능으로 빠른 잡음 제거를 할 수 있다.

• Journal of Advanced Marine Engineering and Technology
• /
• v.24 no.2
• /
• pp.82-89
• /
• 2000

Edge detection is the first step and very important step in image analysis. In this paper, proposed edge detection operators based on informations of edge types and it is different from other classical edge detection operators such as gradient and surface fitting operators. The first, we defined characteristics of edge types such as localization, thinness, length. The second, we defined valid edge types and ideal edge pixel positions in $3\times3$window based on edge characteristics of edge types. And we proposed edge detection algorithm and twelve windows based on valid edge types. In specially, proposed algorithm was shown better performence of edge detection than other operators such as gradient operator and the LoG(Laplacian of Gaussian) operator of zero crossings.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.2 s.40
• /
• pp.53-63
• /
• 2006

A discrete wavelet transform(DWT)-based image watermarking algorithm is proposed in this paper, the proposed method decompose the original image into four subsampled images. Subsampled images are transformed by 2 level DWT, respectively. The proposed method embeds the watermark into one of the subsampled DWT images using edge table that represents dege characteristics of the original image. Without an original image, a watermark is extracted through comparison one subsampled DWT image inserted the watermark with the rest of the submapled DWT images. many exiting methodes do not adequately estimate edge regions where intensities are changed abruptly. The proposed method address with an edge table. Also, even if the watermark is embedded into a low frequency area, our method preserves the image quality. The vality of the proposed method is demonstrated through the PSNR test and subjective image quality that human eyes feel.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.8
• /
• pp.1540-1546
• /
• 2017

Digital image processing is widely used in various fields including the military, medical, image recognition system, robot and commercial sectors. But in the process of acquiring and transmitting digital images, noise is generated by various external causes. There are various types of general noise depending on the cause and form, but AWGN and impulse noise is one of the leading methods. Removing noise during image processing is essential to the pre-treatment process such as segmentation, image recognition and characteristic extraction. As such, this paper suggests an algorithm that distinguishes the non-edge area and edge area using the Canny edge to apply different filters to different areas in order to effectively remove noise from the image. To verify the effectiveness of the suggested algorithm, it was compared against existing methods using zoom images, edge images and PSNR(peak signal to noise ratio).