• Journal of KIISE
• /
• v.43 no.4
• /
• pp.437-449
• /
• 2016

Previous image processing techniques based on plane-to-plane transformations cannot be utilized for spherical panoramic images. In this paper, we propose a new method to inpaint a spherical panoramic image using exemplar, which is deformed by the location of the patch. Our proposed method makes the deformed exemplar patch by latitude and uses it as the reference patch to restore the damaged area. The exemplar-based inpainting method is based on the planar image coordinate system and thus the classical method cannot be applied to the spherical panoramic image. The merit of our proposed method is the fact that it is not dependent on the location of the damaged area. From the experimental results, we proved that our proposed method satisfies the original purpose of the exemplar-based inpainting technique for the spherical panoramic image.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.12
• /
• pp.130-139
• /
• 2014

Undesired camera shaking can make a blur effect, which causes a degradation of video quality. We propose an efficient method of removing the blur effects on video captured from a single camera. The proposed method has a sequential process that is applied to each frame. The first stage is to estimate the camera motion for each frame. In order to estimate the camera motion, we compute the optical flow using 3 consecutive frames. Then a patch-wise image deconvolution is applied. During the deconvolution, edge prediction is used to improve the quality of image deconvolution. After patch-wise image deconvolution, deblurred patches are integrated into an image to produce a deblurred frame. The above process is performed for each frame. The experimental result shows that the proposed method removes the blur effect efficiently.

• Korean Journal of Geomatics
• /
• v.1 no.1
• /
• pp.43-49
• /
• 2001

Although many kinds of stereo matching method have been developed in the field of computer vision and photogrammetry, wrong matches are not easy to avoid. This paper presents a new method to reduce wrong matches after matching, and experimental results are reported. The main idea is to analyze the histogram of the image attribute differences between each pair of image patches matched. Typical image attributes of image patch are the mean and the standard deviation of gray value for each image patch, but there could be other kinds of image attributes. Another idea is to check relative position among potential matches. This paper proposes to use Gaussian blunder filter to detect the suspicious pair of candidate match in relative position among neighboring candidate matches. If the suspicious candidate matches in image attribute difference or relative position are suppressed, then many wrong matches are removed, but minimizing the suppression of good matches. The proposed method is easy to implement, and also has potential to be applied as post processing after image matching for many kinds of matching methods such as area based matching, feature matching, relaxation matching, dynamic programming, and multi-channel image matching. Results show that the proposed method produces fewer wrong matches than before.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.186-189
• /
• 2019

Image inpainting is an image processing technique that restores an image by naturally filling the empty or damaged regions in an image. In this paper, we present a new image inpainting technique that can suppress the generation of texture garbage which is one of the artifacts of existing exemplar-based image inpainting. Unlike the existing technique, only the stationary source patch is sampled as the exemplar patch based on the assumption of spatial stationarity of the texture. This prevents the texture garbage, which is an inconsistent piece of texture from being copied to the target region. Experimental results show that the texture synthesis using the proposed method produces more natural inpainting results than the existing method.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10b
• /
• pp.376-381
• /
• 1992

This paper presents an expert system for the segmentation of a 2.5-D image. The results of two segmentation approaches, edge-based and region-based, are combined to produce a consistent and reliable segmentation. Rich information embedded in the 2.5-D image is utilized to obtain a view independent surface patch description of the image, which can facilitate object recognition considerably.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.23 no.1
• /
• pp.1-11
• /
• 2005

The propose of this study investigated the reproduction of color image on a CRT monitor, for a range of different values of monitor gamma. We have used the GOG(gain-offset-gamma) model of the behavior of CRT. Color difference have been computed in a color space, based on the CIELAB color appearance model. The 133 patch defined linearly color sample and 24 patch defined printing color target were used, and were subjected to the influence of nine different gamma value. The result shows that netural color is increasing the decrease range of luminance black color than white color. These results concern correct in the context display of color reproduction.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.2
• /
• pp.156-160
• /
• 2008

A localization system to estimate the position as well as movement direction of mobile robots is proposed in this paper. This system implements a camera fixed on a robot and color patches evenly distributed and mounted on the planar ceiling. Different permutations of patch colors code information about robot localization. Thus, extraction of color information from patch images leads to estimation of robot position. Additionally, simple geometric indicators are combined with patch colors to estimate robot's movement direction. Since only the distribution of patch colors has to be known, the analysis of patch images to is relatively fast and simple. The proposed robot localization system has been successfully tested for navigation of sample mobile robot. Obtained test results indicate the robustness and reliability of proposed technique for robot navigation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.11a
• /
• pp.125-126
• /
• 2014

안개 제거 알고리즘은 single image에서 대기값(Airlight)와 대기의 빛 전달량(Transmission)을 추정하여 안개로 인한 빛의 산란에 의해 생긴 Contrast 감소 및 채도의 왜곡과 같은 영상 왜곡을 보정해줌으로써 안개 영상에서 안개를 효과적으로 제거해준다. 하지만 기존의 안개 제거 알고리즘은 안개 영상에 특화되었기 때문에 안개가 없는 영상에 알고리즘을 시행 할 경우 색상과 명암에 왜곡을 불러 일으킬 수 있다. 이에 따라 알고리즘을 수행하기 앞서 안개 량을 측정하고 그 결과에 따라 안개 제거 알고리즘에 제거 정도 가중치나 알고리즘 수행 여부를 판단할 필요가 있다. 본 논문은 기존 안개 제거 알고리즘들이 영상의 patch를 사용하여 빛 전달량(Transmission)을 추정한다는 것을 이용하여 빛 전달량을 구함과 동시에 안개 량을 판단하는 알고리즘을 개발하였다. 안개량을 측정하기 위해 각 patch의 pixel 분포 특성과 patch의 빛 전달량(Transmission)을 구하기 위한 특정 값과 실제 pixel의 명암(Intensity)을 비교하여 안개 량을 측정한다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.47 no.6
• /
• pp.26-34
• /
• 2010

The mutual coupling of a pair of microstrip patch antennas on a finite grounded dielectric substrate is influenced by the diffracted field of surface waves from the edges of a substrate. The effective dielectric constant of a grounded dielectric substrate determines the distance between the antenna center and the edge of a substrate to obtain the minimum mutual coupling between a pair of microstrip patch antennas. The optimum substrate size with the minimum mutual coupling is easily calculated using the image method. The optimum substrate sizes using the linage method are in good agreement with the results obtained by the full wave simulation.