• Journal of information and communication convergence engineering
• /
• v.20 no.3
• /
• pp.195-203
• /
• 2022

Noise generated during image acquisition and transmission can negatively impact the results of image processing applications, and noise removal is typically a part of image preprocessing. Denoising techniques combined with nonlocal techniques have received significant attention in recent years, owing to the development of sophisticated hardware and image processing algorithms, much attention has been paid to; however, this approach is relatively poor for edge preservation of fine image details. To address this limitation, the current study combined a steering kernel technique with adaptive masks that can adjust the size according to the noise intensity of an image. The algorithm sets the steering weight based on a similarity comparison, allowing it to respond to edge components more effectively. The proposed algorithm was compared with existing denoising algorithms using quantitative evaluation and enlarged images. The proposed algorithm exhibited good general denoising performance and better performance in edge area processing than existing non-local techniques.

• Journal of Korea Multimedia Society
• /
• v.13 no.10
• /
• pp.1463-1473
• /
• 2010

In this paper, we propose a modified watershed algorithm to extract more correct edge and reduce processing time. Two new algorithms are proposed in this paper. The first one is applying two conventional watershed expansion methods known as rainfall and immersion simulation jointly. We analyze the advantage and problem of each simulation and then propose a new expansion method that keeps the advantage and removes the problem in order to extract more correct edge and reduce processing time. The second is a new priority decision algorithm to obtain more correct edge of a region. Some zero-crossing points of gradient are expected to be edge of a region but the conventional method has a limitation that it cannot extract those points as edge. Therefore we propose a new priority decision algorithm for watershed in order to get more correct edge. We compare the proposed method with the conventional method through experiments and prove that the proposed method can extract more correct edge of region.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.10
• /
• pp.1551-1558
• /
• 2022

We propose a two-tier cooperative computing system comprised of a mobile device and an edge server for partial offloading of multi-branch structures in Fog/Edge Computing environments in this paper. The proposed system includes an algorithm for splitting up application service processing by using reconstructive linearization techniques for multi-branch structures, as well as an optimal collaboration algorithm based on partial offloading between mobile device and edge server. Furthermore, we formulate computation offloading and CNN layer scheduling as latency minimization problems and simulate the effectiveness of the proposed system. As a result of the experiment, the proposed algorithm is suitable for both DAG and chain topology, adapts well to different network conditions, and provides efficient task processing strategies and processing time when compared to local or edge-only executions. Furthermore, the proposed system can be used to conduct research on the optimization of the model for the optimal execution of application services on mobile devices and the efficient distribution of edge resource workloads.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.12
• /
• pp.2343-2348
• /
• 2006

Image magnification is among the basic image processing operations. The most commonly used technique for image magnification are based on interpolation method(such as nearest neighbor, bilinear and cubic interpolation). However, the magnified images produced by the techniques that often appear a variety of undesirable image artifacts such as 'blocking' and 'blurring' or too takes the processing time into the several processing for image magnification. In this paper, we propose image magnification method which uses input image's sub-band information such as edge information to enhance the image magnification method. We use the whole image and not use the one's neighborhood pixels to detect the edge information of the image that isn't occurred the blocking phenomenon. And then we emphasized edge information to remove the blurring phenomenon which incited of edge information. Our method, which improves the performance of the traditional image magnification methods in the processing time, is presented. Experiment results show that the proposed method solves the drawbacks of the image magnification such as blocking and blurring phenomenon, and has a higher PSNR and Correlation than the traditional methods.

• International journal of advanced smart convergence
• /
• v.10 no.4
• /
• pp.278-288
• /
• 2021

Recently, IoT systems are cloud-based, so that continuous and large amounts of data collected from sensor nodes are processed in the data server through the cloud. However, in the centralized configuration of large-scale cloud computing, computational processing must be performed at a physical location where data collection and processing take place, and the need for edge computers to reduce the network load of the cloud system is gradually expanding. In this paper, a cluster system consisting of 6 inexpensive Raspberry Pi boards was constructed to perform fast data processing. And we propose "Kubernetes cluster system(KCS)" for processing large data collection and analysis by model distribution and data pipeline method. To compare the performance of this study, an ensemble model of deep learning was built, and the accuracy, processing performance, and processing time through the proposed KCS system and model distribution were compared and analyzed. As a result, the ensemble model was excellent in accuracy, but the KCS implemented as a data pipeline proved to be superior in processing speed..

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.7
• /
• pp.1518-1523
• /
• 2012

Due to development of visual media in various industrial sectors, the importance of image processing is increasing. Among the various image processing areas, edge detection is utilized widely for various fields such as object recognition, object segmentation, the medical and other industries. Edge includes the critical factors of images like size, direction and location. Then conventional methods such as Sobel, Prewitt, Roberts and Laplacian are proposed to detect edge. However, edge detection property of these methods is declined when they are applied to the image which corrupted by AWGN(Additive White Gaussian Noise). Therefore, an algorithm using modified weighted filter is proposed in this paper and our method has excellent property on edge detection.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.1
• /
• pp.26-31
• /
• 2010

We proposed a new directional edge based interpolation, DEBI, by combining two weighted directional information to reduce blurred edges and annoying artifacts. Four isotropic gradient masks are employed in defining edge directions and they are proven to hold a first order derivative relation with respect to a rotating coordinate. Two minimum gradients among four absolute directional results are shown to be sufficient to describe slant edges efficiently. Compared with widely used bilinear and bicubic interpolation methods, the proposed algorithm results in a noticeable improvement along edge area.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.92-96
• /
• 2010

Deinterlacing methods are usually divided into inter-field deinterlacing and intra-field deinterlacing. The most common method of intra-field deinterlacing is the linear method which uses line doubling or line averaging. There are also some edge-enhancement methods such as ELA(Edge Based Line Average) and modified ELA. However, the linear interpolation generates edge blurring or staircase artifacts. The methods using ELA or modified ELA show poor deinterlacing at various types of edges because of insufficient edge information in a certain direction. This paper presents an intra-field deinterlacing algorithm that considers the interpolation based on edges in 7 directions and an edge line in the horizontal direction. It demonstrates better picture quality by reducing the staircase phenomenon of object in the conventional methods.

• Journal of Information Processing Systems
• /
• v.17 no.5
• /
• pp.1004-1019
• /
• 2021

To solve the problems of the low image contrast, fuzzy edge details and edge details missing in noisy image fusion, this study proposes a noisy infrared and visible light image fusion algorithm based on non-subsample contourlet transform (NSCT) and an improved bilateral filter, which uses NSCT to decompose an image into a low-frequency component and high-frequency component. High-frequency noise and edge information are mainly distributed in the high-frequency component, and the improved bilateral filtering method is used to process the high-frequency component of two images, filtering the noise of the images and calculating the image detail of the infrared image's high-frequency component. It can extract the edge details of the infrared image and visible image as much as possible by superimposing the high-frequency component of infrared image and visible image. At the same time, edge information is enhanced and the visual effect is clearer. For the fusion rule of low-frequency coefficient, the local area standard variance coefficient method is adopted. At last, we decompose the high- and low-frequency coefficient to obtain the fusion image according to the inverse transformation of NSCT. The fusion results show that the edge, contour, texture and other details are maintained and enhanced while the noise is filtered, and the fusion image with a clear edge is obtained. The algorithm could better filter noise and obtain clear fused images in noisy infrared and visible light image fusion.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.100-103
• /
• 2014

Currently, edge detection is utilized in various areas. Edge detection is the preprocessing process for image processing in general, and this is a technology that is considered essential for image processing. According, research on this subject is carried out incessantly. Edge has important image related elements such as size, direction and location of the object of an image. Numerous methods were proposed for the detection. Among them, the representative methods are Sobel, Prewitt, Roberts, Laplacian. However, these existing methods are rather lacking when it comes to the edge detection characteristics in case of the image with mixed noise. Therefore, this study presented edge detection method that utilizes median and average values for the elements depending on the size and location of local mask.