• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.916-918
• /
• 2015

Image processing is being spotlighted as an important sector with increasingly diverse applications as the society advances into a sophisticated digital information age. Especially, the image restoration as the core technology of image processing, many studies are being progressed. In this paper, in order to restore the damaged image in the Salt and Pepper noisy environment, a modified adaptive switching median filter where the size of local mask can be varied according to the noise density was proposed. And using the PSNR as the standard for objective decision making of the improvement effect, it was compared with the existing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2259-2264
• /
• 2014

For edge detection methods, there are Sobel, Prewitt, Roberts and Canny edge detector, and these methods have insufficient detection characteristics in the image corrupted by the impulse noise. Therefore in this paper, in order to improve these disadvantages of the previous methods and to effectively detect the edge in the impulse noise environment, using the $5{\times}5$ mask, the noise factors within the $3{\times}3$ mask based on the central pixel is determined, and depending on its status, for noise-free it is processed as is, and if noise is found, by obtaining the estimated mask using the adjacent pixels of each factor, an algorithm that detects the edge is proposed.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.9-16
• /
• 2010

Moving object detection is to detect foreground object different from background scene in a new incoming image frame and is an essential ingredient process in some image processing applications such as intelligent visual surveillance, HCI, object-based video compression and etc. Most of previous object detection algorithms are still computationally heavy so that it is difficult to develop real-time multi-channel moving object detection in a workstation or even one-channel real-time moving object detection in an embedded system using them. Foreground mask correction necessary for a more precise object detection is usually accomplished using morphological operations like opening and closing. Morphological operations are not computationally cheap and moreover, they are difficult to be rendered to run simultaneously with the subsequent connected component labeling routine since they need quite different type of processing from what the connected component labeling does. In this paper, we first devise a fast and precise foreground mask correction algorithm, "Neighbor Foreground Pixel Propagation (NFPP)" which utilizes neighbor pixel checking employed in the connected component labeling. Next, we propose a novel moving object detection method based on the devised foreground mask correction algorithm, NFPP where the connected component labeling routine can be executed simultaneously with the foreground mask correction. Through experiments, it is verified that the proposed moving object detection method shows more precise object detection and more than 4 times faster processing speed for a image frame and videos in the given the experiments than the previous moving object detection method using morphological operations.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.922-924
• /
• 2015

Recently, the image processing technologies using the public media such as the film, TV, camera and advertisement have been rapidly developed. However, the deterioration occurs with the image in the process of data processing, transmission and storage, and the typical cause of such deterioration is the salt and pepper noise. Typical filters to remove the salt and pepper noise include CWMF(center weighted median filter) and AMF(adaptive median filter) but such filters bring more or less insufficient characteristics of noise removal and visual error as the noise density gets higher. Thus, this paper proposed the median filter which applied the local mask segmented to 4 areas in order to remove the salt and pepper noise effectively and used PSNR(peak signal to noise ratio) as a criterion of judgment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.782-784
• /
• 2013

As digital image processing technologies are developing, edges are being utilized in various areas. In the existing edge detection methods, there are mask methods which utilize Sobel, Prewitt, Roberts, Laplacian operator etc. To realize these existing edge detection methods is simple. But, in case that AWGN(additive white Gaussian noise) added images are processed, edge detection characteristics are slightly insufficient. Therefore, the edge detection algorithm using the standard deviation of local mask was suggested in this paper to compensate for the drawbacks in the existing detection methods and the suggested algorithm in AWGN environments showed excellent edge detection characteristics.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.328-330
• /
• 2015

Edge is a characteristic information that can easily obtain the size, direction and location of objects included in the image, and the edge detection is utilized as a preprocess processing in various image processing application sectors such as object detection and object recognition, etc. For the conventional edge detection methods, there are Sobel, Prewitt and Roberts. These existing edge detection methods are easy to implement but the edge detection characteristics are somewhat insufficient as fixed weighted mask is applied. Therefore, in order to compensate the problems of existing edge detection methods, in this paper, an edge detection algorithm was proposed after applying the weighted value according to the standard deviation and means within the local mask.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2016.05a
• /
• pp.676-678
• /
• 2016

Noise occurs in the process of obtaining, transmission, and processing in image processing systems and these noises lower the resolution of image and cause visual errors. Currently, a representative filter to remove salt and pepper noise is SMF(standard median filter) but it is inadequate in preserving edge as the noise field expands. Therefore, for salt and pepper noise enviroment, the study suggested and algorithm that are places with original pixel when the central pixel is non-noise and process by applying weighted value on areas with less local mask pixel changes when there is noise.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.9
• /
• pp.2173-2179
• /
• 2015

In digital era image processing has been utilized in a variety of media such as TV, camera and smart phone. Typically salt and pepper noise are generated by various causes during the analysis, identification, and processing of image data. Principal filters such as SMF, CWMF, and AMF have been used to remove these noise. But the existing filters fall short of edge preservation and noise elimination in high noise densities. Thus, a processing algorithm, on which the size of deformable mask varies depending on the noise density, is proposed to remove salt and pepper noise effectively in this study. The performance of the proposed method was evaluated compared with the existing methods using PSNR.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.655-657
• /
• 2002

본 논문에서는 스테레오 영상에서 두 영상간의 깊이(Depth) 정보를 이용해서 영역을 기반으로 한 영상매칭을 수행한 추 사람의 얼굴 영역을 결정한다 영역 결정은 설정된 탐색 윈도우에 의해 좌, 우 영상간의 MSE(Minimum Square Error)를 검색하는 알고리즘을 제안한다. 매칭 과정에서 발생하는 영역 오류를 보정하기 위해서 타원 마스크를 이용하는 방법을 제안하며 실행 시간을 줄이기 위하여 2D 도메인에서 쿼드트리(Quad-tree) 윈도우를 사용한다.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2001.06a
• /
• pp.95-98
• /
• 2001

본 논문은 뇌의 축방향(axial sect ion)에 대하여 촬영한 뇌의 자기공명 영상(Magnetic Resonance Imaging)을 대상으로 뇌의 영역만을 분리하기 위한 방법을 제안하고 있다. MR영상은 슬라이스마다 다른 분포값을 가지기 때문에 각 슬라이스 별로 조직의 특성을 파악하여 뇌의 영역을 분리하였다. 히스토그램의 명암값 분포를 분석하여 배경과 뇌를 둘러싸고 있는 외피를 제거하고 라벨링(label1ing) 알고리즘을 적용하여 뇌만 분리 할 수 있도록 하는 마스크 영상을 만들어 이것을 이용하여 원영상으로부터 뇌의 영역만을 분리하였다.