• 한국멀티미디어학회논문지
• /
• 제7권12호
• /
• pp.1692-1699
• /
• 2004

Many researchers have developed various techniques for detection of human faces in ordinary still images. Face detection is the first imperative step of human face recognition systems. The two main problems of human face detection are how to cutoff the running time and how to reduce the number of false positives. In this paper, we present frontal and near-frontal face detection algorithm in still gray images using a thick edge image and neural network. We have devised a new filter that gets the thick edge image. Our overall scheme for face detection consists of two main phases. In the first phase we describe how to create the thick edge image using the filter and search for face candidates using a whole face detector. It is very helpful in removing plenty of windows with non-faces. The second phase verifies for detecting human faces using component-based eye detectors and the whole face detector. The experimental results show that our algorithm can reduce the running time and the number of false positives.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권2호
• /
• pp.116-120
• /
• 2006

This paper discusses an approach for detecting a new edge in color images. The color image is to be represented by a vector field, and the color image edges are detected as differences in the local vector statistics. This method is based on the calculation for the vector angle between two adjacent pixels. Unlike Euclidean distance in RGB space, the vector angle distinguishes the differences in chromaticity, independent of luminance or intensity. The proposed approach can easily accommodate concepts, such as variable template edge detection, as well as the latest developments in vector order statistics for color image processing. In this paper, it is used not a conventional fixed template operator but a variable template operator The variable template is implemented and experimental results for digital color images are included.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2008년도 하계종합학술대회
• /
• pp.823-824
• /
• 2008

In this paper, we propose a robust and fast digital image stabilization algorithm based on edge detection. The proposed algorithm exploits sobel operator to obtain edge image and fast detects irregular conditions with analyzing an edge information of the image. Experimental results show that the proposed algorithm can gain better performance in the sense of speed and precision comparing with full-block search method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권7호
• /
• pp.3217-3238
• /
• 2018

In this paper, a depth image up-sampling method is put forward by using pixel classifying and jointed bilateral filtering. By analyzing the edge maps originated from the high-resolution color image and low-resolution depth map respectively, pixels in up-sampled depth maps can be classified into four categories: edge points, edge-neighbor points, texture points and smooth points. First, joint bilateral up-sampling (JBU) method is used to generate an initial up-sampling depth image. Then, for each pixel category, different refinement methods are employed to modify the initial up-sampling depth image. Experimental results show that the proposed algorithm can reduce the blurring artifact with lower bad pixel rate (BPR).

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2003년도 추계종합학술대회
• /
• pp.479-482
• /
• 2003

영상으로부터 검출된 에지는 원 영상에 대한 위치와 모양 등에 대한 다양한 정보를 포함하고 있으므로, 이러한 에지를 검출하기 위한 많은 연구가 이루어지고 있다. 그리고, 최근 신호처리 분야의 새로운 기법으로 제시된 웨이브렛 이론들의 발전과 더불어 웨이브렛 변환은 영상의 에지를 포함한 특이점들을 분석하는 분야에 널리 응용되고 있다. 따라서, 본 논문에서는 영상의 라인 폭에 의존하지 않는 웨이브렛 함수를 사용하여, 웨이브렛 변환 데이터의 국부 최대값과 기울기의 방향, 그리고 위치 정보로부터 원 영상의 에지를 검출하였다.

• 전자공학회논문지B
• /
• 제31B권6호
• /
• pp.71-80
• /
• 1994

The purpose of this paper is to explore the use of fuzzy set theory for image processing and analysis. As an application example, the fuzzy method of edge detection is proposed to extract the edges of raised characters on tires.In general, Sobel, Prewitt, Robert and LoG filters are used to detect the edge, but it is difficult to detect the edge because of ambiguity of representations, noise and general problems in the interpretation of tire image. Therefore, in his paper, the fuzzy property plane has been extracted from the spatial domain using the ramp-mapping function. And then the ideas of fuzzy MIN and MAX are applied in removing noise and enhancement of the image simultaneously. From the result of MIN and MAX procedure a new fuzzy singleton is generated by extracting the difference between adjacent membership function values. And the edges are extracted by applying fuzzy $\alpha$-cut set to the fuzzy singletion, Finally, these ideas are applied to the tire images.

• 전자공학회논문지S
• /
• 제34S권3호
• /
• pp.84-96
• /
• 1997

In this paper an efficient morphologica algorithm for reducing gaussian and impulse noise in gray-scale image is presented. Based on the edge information the input image is partitioned into a flat region and an edge region, then different algorithms are selectively applied to each region. in case of impulse noise, MGR (morphologica grayscale reconstruction) algorithm with directional SE (structuring element) is applied to the flat region. For theedge region opening-closing (closing-opening) is used instead of dialation (erosion), so that the remaining noise around large objects can be removed. In case of gaussian noise, 5*5 OCCO(opening closing closing opening) and 3*3 DMF(directional morphological filter ) are used for the flat region and the edgeregion, respectively. In order to remove discontinuity at the edge boundary, the algorithm uses 3*3 OCCO around the edge region to reconstruct the final image. Experimetnal results have shown that the proposed algorithm achieves a high performance in terms of noise removal, detail preservation, and NMSE.

• Journal of Astronomy and Space Sciences
• /
• 제33권4호
• /
• pp.313-318
• /
• 2016

Communication, Ocean And Meteorological Satellite (COMS) Meteorological Imager (MI) images are processed for radiometric and geometric correction from raw image data. When intermediate image data are matched and compared with reference landmark images in the geometrical correction process, various techniques for edge detection can be applied. It is essential to have a precise and correct edged image in this process, since its matching with the reference is directly related to the accuracy of the ground station output images. An edge detection method based on neural networks is applied for the ground processing of MI images for obtaining sharp edges in the correct positions. The simulation results are analyzed and characterized by comparing them with the results of conventional methods, such as Sobel and Canny filters.

• 한국정보처리학회논문지
• /
• 제3권3호
• /
• pp.471-477
• /
• 1996

본 논문에서는 톨연산에 기초한 화상의 경계선 추출 방법을 제안 한다. 첫째로 3$\times$3 window내 에서 경계라고 고려 할 수 있는 구조를 고려하여 톨 멤버쉽 함수를 계산 한다. 이후를 교집합연산과 합집합 연산을 행하며 계산의 편의를 위해 정규화를 행한다. 최종적으로 ;엔트로피 개념에 기초한 thresholding을 행함으로써 경계를 추출 하고자 한다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권10호
• /
• pp.489-496
• /
• 2016

병리 정보시스템(Pathological Information System: PIS)은 매일 수천 장씩 생산되는 환자 병리 이미지를 관리하는데 활용되고 있으며, 이 이미지 정보들을 어떻게 효과적으로 처리할 것인지는 병리 정보 처리에 있어서 중요한 연구 과제 중 하나이다. 이미지의 외곽선을 추출하는 것은 병리 이미지 처리에 있어 가장 중요한 작업이지만 현재 사용되는 알고리즘은 정확도에 있어 많은 개선점을 가지므로, 본 논문에서는 이미지의 외곽선 검측에 있어서 기존의 Canny 알고리즘의 원리를 바탕으로 적응적 임계값 설정이 가능하며 눈금자를 임계값 설정의 기준으로 삼는 방식을 제안하여 기존 외곽선 추출 방식보다 정확한 방식을 제안한다. 제안 방식은 기존 방식과의 비교실험을 통해 성능을 검증하였으며, 이 실험에서는 임의로 선정된 병리 이미지 군, 기존 방식으로는 식별이 제한되었던 병리 이미지 군 및 의도적으로 노이즈를 추가한 이미지 군을 대상으로 실험하였고, 실험 결과를 비교하여 제안하는 이미지 외곽선 식별 방식의 향상된 성능을 증명했다.