Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal of Korea Multimedia Society
Journal Basic Information
Journal DOI :
Korea Multimedia Society
Editor in Chief :
Volume & Issues
Volume 15, Issue 12 - Dec 2012
Volume 15, Issue 11 - Nov 2012
Volume 15, Issue 10 - Oct 2012
Volume 15, Issue 9 - Sep 2012
Volume 15, Issue 8 - Aug 2012
Volume 15, Issue 7 - Jul 2012
Volume 15, Issue 6 - Jun 2012
Volume 15, Issue 5 - May 2012
Volume 15, Issue 4 - Apr 2012
Volume 15, Issue 3 - Mar 2012
Volume 15, Issue 2 - Feb 2012
Volume 15, Issue 1 - Jan 2012
Selecting the target year
Development of Elliptical Fitting Based Recognition Method for Melon Harvesting Robot
Won, Chulho ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1273~1283
DOI : 10.9717/kmms.2012.15.11.1273
In this paper, vision-based positioning algorithm for melon harvesting robot is presented. RGB value of the input image was converted into HSI value then, melon area was extracted after performing the binarization using HUE value. After morphological filtering was applied to remove noise, outermost boundary points were obtained using border following and convex hull method. Elliptical fitting for melons was perform by the RANSAC algorithm, the center point of ellipse, the length of the short and long axis, and rotation angle were obtained. We verified the effectiveness of the proposed method by various simulation experiments and confirmed actual feasibility of the proposed method by applying to the real melon.
Multiple Ship Object Detection Based on Background Registration Technique and Morphology Operation
Kim, Won-Hee ; Arshad, Nasim ; Kim, Jong-Nam ; Moon, Kwang-Seok ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1284~1291
DOI : 10.9717/kmms.2012.15.11.1284
Ship object detection is a technique to detect the existence and the location of ship when ship objects are shown on input image sequence, and there are wide variations in accuracy due to environmental changes and noise of input image. In order to solve this problem, in this paper, we propose multiple ship object detection based on background registration technique and morphology operation. The proposed method consists of the following five steps: background elimination step, noise elimination step, object standard position setting step, object restructure step, and multiple object detection steps. The experimental results show accurate and real-time ship detection for 15 different test sequences with a detection rate of 98.7%, and robustness against variable environment. The proposed method may be helpful as the base technique of sea surface monitoring or automatic ship sailing.
Identification Method of Geometric and Filtering Change Regions in Modified Digital Images
Hwang, Min-Gu ; Cho, Byung-Joo ; Har, Dong-Hwan ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1292~1304
DOI : 10.9717/kmms.2012.15.11.1292
Recently, digital images are extremely forged by editors or advertisers. Also, amateurs can modify images throughout easy editing programs. In this study, we propose identification and analytical methods for the modified images to figure out those problems. In modified image analysis, we classify two parts; a filtering change and a geometric change. Those changes have an algorithm based on interpolation so that we propose the algorithm which is able to analyze a trace on a modified area. With this algorithm, we implement a detection map of interpolation using minimum filter, laplacian algorithm, and maximum filter. We apply the proposed algorithm to modified image and are able to analyze its modified trace using the detection map.
A Study on Image Segmentation Method Based on a Histogram for Small Target Detection
Yang, Dong Won ; Kang, Suk Jong ; Yoon, Joo Hong ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1305~1318
DOI : 10.9717/kmms.2012.15.11.1305
Image segmentation is one of the difficult research problems in machine vision and pattern recognition field. A commonly used segmentation method is the Otsu method. It is simpler and easier to implement but it fails if the histogram is unimodal or similar to unimodal. And if some target area is smaller than background object, then its histogram has the distribution close to unimodal. In this paper, we proposed an improved image segmentation method based on 1D Otsu method for a small target detection. To overcome drawbacks by unimodal histogram effect, we depressed the background histogram using a logarithm function. And to improve a signal to noise ratio, we used a local average value by the neighbor window for thresholding using 1D Otsu method. The experimental results show that our proposed algorithm performs better segmentation result than a traditional 1D Otsu method, and needs much less computational time than that of the 2D Otsu method.
A Vision Based Guideline Interpretation Technique for AGV Navigation
Byun, Sungmin ; Kim, Minhwan ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1319~1329
DOI : 10.9717/kmms.2012.15.11.1319
AGVs are more and more utilized nowadays and magnetic guided AGVs are most widely used because their system has low cost and high speed. But this type of AGVs requires high infrastructure building cost and has poor flexibility of navigation path layout changing. Thus it is hard to applying this type of AGVs to a small quantity batch production system or a cooperative production system with many AGVs. In this paper, we propose a vision based guideline interpretation technique that uses the cheap, easily installable and changeable color tapes (or paint) as a guideline. So a vision-based AGV with color tapes is effectively applicable to the production systems. For easy setting and changing of AGV navigation path, we suggest an automatic method for interpreting a complex guideline layout including multi-branches and joins of branches. We also suggest a trace direction decision method for stable navigation of AGVs. Through several real-time navigation tests with an industrial AGV installed with the suggested technique, we confirmed that the technique is practically and stably applicable to real industrial field.
Heart Valve Stenosis Region Detection Algorithm on Heart Sounds
Lee, G.H. ; Lee, Y.J. ; Kim, M.N. ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1330~1340
DOI : 10.9717/kmms.2012.15.11.1330
In this paper, a new algorithm is proposed for the heart valves stenosis region detection using heart sounds. Many researches for detecting primary components or removing heart murmurs have been studied, but their performances are degraded at abnormal heart sounds such as aortic stenosis and mitral stenosis because of large heart murmurs. In this paper, heart murmur detection method is proposed based on noise intensity function. The proposed noise intensity function detect the primary components S1, S2, then set session up using S1, S2. And then noise intensity function was computed using autocorrelation value of each session. The proposed noise intensity function estimated noise intensity of each sessions and detected heart murmurs. According to simulation results, the proposed algorithm has better performance than former study for detecting heart valve stenosis region.
Correction of Rotated Objects in Medical Images Using the Mojette Transform
Jung, Hyang-Mi ; Kim, Ji-Hong ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1341~1348
DOI : 10.9717/kmms.2012.15.11.1341
In this paper, an efficient scheme for correcting rotated objects in medical images using the Mojette transform is presented. The Mojette transform is a kind of discrete Radon transform, where the transform domain is represented by a set of projections. The Mojette transform currently studied in the image compression area is modified for detecting the rotation angle of objects in medical images. First, in order to find accurate rotation angle, the projection value in the Mojette transform is determined by using pixels on the projection line and in addition the linear interpolation of pixels adjacent to the line. Second, at each projection angle, only one projection is implemented for reducing the amount of the calculation in the process of the Mojette transform. Finally, the projection in the Mojette transform is carried out at the predetermined ROI(Region Of Interest) at which the objects are not cropped or added by rotating the image. The simulation results show that the proposed method has good performance for correcting the rotation angle in medical images.
A Study on the Structured Weakness Classification for Mobile Applications
Son, Yunsik ; Oh, Se-Man ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1349~1357
DOI : 10.9717/kmms.2012.15.11.1349
In recent years, security accidents which are becoming the socially hot issue not only cause financial damages but also raise outflow of private information. Most of the accidents have been immediately caused by the software weakness. Moreover, it is difficult for software today to assure reliability because they exchange data across the internet. In order to solve the software weakness, developing the secure software is the most effective way than to strengthen the security system for external environments. Therefore, suggests that the coding guide has emerged as a major security issue to eliminate vulnerabilities in the coding stage for the prevention of security accidents. Developers or administrators effectively in order to use secure coding coding secure full set of security weaknesses organized structurally and must be managed. And the constant need to update new information, but the existing Secure Coding and Security weakness is organized structurally do not. In this paper, we will define and introduce the structured weakness for mobile applications by the surveys of existing secure coding and coding rules for code analysis tools in Java.
A Physical Sequence Estimation Scheme for Passive RFID Tags using Round Trip Scan
Lee, Joo-Ho ; Kwon, Oh-Heum ; Song, Ha-Joo ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1358~1368
DOI : 10.9717/kmms.2012.15.11.1358
A tag sequence estimation scheme is to estimate the physical sequence of passive RFID tags that are linearly spread using the movement of a RFID reader. Since RFID readers communicate with the passive tags by very weak radio waves, scanning passive tags are unstable. In this paper, we applied round-trip scanning of a reader to enhance the tag sequence estimation. Proposed scheme first determines the turning point of the reader movement, and then estimates the sequence of the tags using the tag sets scanned in each read cycles. Test experiments show that the proposed scheme can improve the estimation accuracy.
2D Industrial Image Registration Method for the Detection of Defects
Lee, Youngjoo ; Lee, Jeongjin ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1369~1376
DOI : 10.9717/kmms.2012.15.11.1369
In this paper, we propose 2D industrial image registration method for the detection of defects. Proposed method performs preprocessing to smooth the original image with the preservation of the edge for the robust registration against general noise. Then, x-direction gradient magnitude image and corresponding binary image are generated. Density analysis around neighborhood regions per pixel are performed to generate feature image for preventing mis-registration due to moire-like patterns, which frequently happen in industrial images. Finally, 2D image registration based on phase correlation between feature images is performed to calculate translational parameters to align two images rapidly and optimally. Experimental results showed that the registration accuracy of proposed method for the real industrial images was 100% and our method was about twenty times faster than the previous method. Our fast and accurate method could be used for the real industrial applications.
A Mouse Control Method Using Hand Movement Recognition
Kim, Jung-In ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1377~1383
DOI : 10.9717/kmms.2012.15.11.1377
This paper proposes a human mouse system that replaces mouse input by human hand movement. As the resolution of monitors increases, it is not quite possible, due to the resolution difference between web cameras and monitors, to place the cursor in the entire range of a monitor by simply moving the pointer which recognizes the position of the hand from the web camera. In this regard, we propose an effective method of placing the position of the mouse, without repeating the returning hand movements, in the corners of the monitor in which the user wants it to be. We also proposes the recognition method of finger movements in terms of using thumb and index finger. The measurement that we conducted shows the successful recognition rate of 97% that corroborates the effectiveness of our method.
Development of a functional game device and Contents for improving of brain activity through finger exercise
Ahn, Eun-Young ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1384~1390
DOI : 10.9717/kmms.2012.15.11.1384
It is well known that the exercising and stimulating of fingers have an important bearing on the brain. We take note of the fact and develope a game device for improving one's health and brain ability in respect of the education and training. Especially, we develope the device focused on the balanced exercising of five finger for improving brain function. The game device is possible to used in two-ways, namely online and off-line mode. In online mode, the device is connected with other visual devices such as smart phone and smart TV and communicated with Bluetooth and it is used as a MMI(multi-modal interface) device. Whereas, in off-line mode the game device works independently and it makes possible to enjoy auditorial and tactual games without video images for promotion of brain activity and emotional cultivation. For certification of the device, we implement two games(a fishing game for off-line mode and a shooting game for online mode) for people of all age, especially good for the elderly. It is usable as a game device to offering the elderly a great help for preventing impairment of the cognitive functions.
Realtime Clock Skew Estimator for Time Synchronization in Wireless Sensor Networks of WUSB and WBAN
Hur, Kyeong ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1391~1398
DOI : 10.9717/kmms.2012.15.11.1391
Time synchronization is crucial in wireless sensor networks such as Wireless USB and WBAN for diverse purposes from the MAC to the application layer. This paper proposes online clock skew estimators to achieve energy-efficient time synchronization for wireless sensor networks. By using recursive least squares estimators, we not only reduce the amount of data which should be stored locally in a table at each sensor node, but also allow offset and skew compensations to be processed simultaneously. Our skew estimators can be easily integrated with traditional offset compensation schemes. The results of simulation and experiment show that the accuracy of time synchronization can be greatly improved through our skew compensation algorithm.
Generating Dynamic Virtual Light Sources by Interpolating HDR Environment Maps
Hwang, Gyuhyun ; Park, Sanghun ;
Journal of Korea Multimedia Society, volume 15, issue 11, 2012, Pages 1399~1408
DOI : 10.9717/kmms.2012.15.11.1399
The light source is an important visual component that empirically affects the color and illumination of graphic objects, and it is necessary to precisely store and appropriately employ the information of all light sources in the real world in order to obtain photo-realistic composition results. The information of real light sources can be accurately stored in HDR environment maps; however, it is impossible to create new environment maps corresponding to dynamic virtual light sources from a single HDR environment map captured under a fixed lighting situation. In this paper, we present a technique to dynamically generate well-matched information for arbitrarily selected virtual light sources using HDR environment maps created under predefined lighting position and orientation. Using the information obtained from light intensity and distribution analysis, our technique automatically generates HDR environment maps for virtual light sources via image interpolation. By applying the interpolated environment maps to an image-based lighting technique, we show that virtual light can create photo-realistically rendered images for graphic models.