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 17, Issue 12 - Dec 2014
Volume 17, Issue 11 - Nov 2014
Volume 17, Issue 10 - Oct 2014
Volume 17, Issue 9 - Sep 2014
Volume 17, Issue 8 - Aug 2014
Volume 17, Issue 7 - Jul 2014
Volume 17, Issue 6 - Jun 2014
Volume 17, Issue 5 - May 2014
Volume 17, Issue 4 - Apr 2014
Volume 17, Issue 3 - Mar 2014
Volume 17, Issue 2 - Feb 2014
Volume 17, Issue 1 - Jan 2014
Selecting the target year
Implementation of 2D Active Shape Model-based Segmentation on Hippocampus
Izmantoko, Yonny S. ; Yoon, Ho-Sung ; Adiya, Enkhbolor ; Mun, Chi-Woong ; Huh, Young ; Choi, Heung-Kook ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 1~7
DOI : 10.9717/kmms.2014.17.1.001
Hippocampus is an important part of brain which is related with early memory storage and spatial navigation. By observing the anatomy of hippocampus, some brain diseases effecting human memory (e.g. Alzheimer, schizophrenia, etc.) can be diagnosed and predicted earlier. The diagnosis process is highly related with hippocampus segmentation. In this paper, hippocampus segmentation using Active Shape Model, which not only works based on image intensity, but also by using prior knowledge of hippocampus shape and intensity from the training images, is proposed. The results show that ASM is applicable in segmenting hippocampus from whole brain MR image. It also shows that adding more images in the training set results in better accuracy of hippocampus segmentation.
A Fire Detection Using Color and Movement of Flames
Cho, KyoungLae ; Bae, Sung-Ho ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 8~14
DOI : 10.9717/kmms.2014.17.1.008
In this paper, we propose a new fire detection method using moving features and colors of flames in video sequences. It uses YCbCr color space to separate the luminance from the chrominance components more effectively than RGB color space. In the proposed method, moving regions of flames are detected by cumulating the difference of luminance between two consecutive images and generate candidate flame regions by using the color of flames. Finally, it decides whether the candidate flame regions are flames or not by using their temporal changes of the areas. Experimental results show that the proposed method performs better in segmenting fire regions compared with the conventional fire detection method in video sequences.
Loitering Detection Solution for CCTV Security System
Kang, Joohyung ; Kwak, Sooyeong ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 15~25
DOI : 10.9717/kmms.2014.17.1.015
In this paper, we propose a loitering detection using trajectory probability distribution and local direction descriptor for intelligent surveillance system. We use a background modeling method for detecting moving object and extract the motion features from each moving object for making feature vectors. After that, we detect the loitering behavior person using K-Nearest Neighbor classifier. We test the proposed method in real world environment and it can achieve real time and robust detection results.
Improvement of Retrieval Performance Using Adaptive Weighting of Key Frame Features
Kim, Kang-Wook ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 26~33
DOI : 10.9717/kmms.2014.17.1.026
Video retrieval and indexing are performed by comparing feature similarities between key frames in shot after detecting a scene change and extracting key frames from the shot. Typical image features such as color, shape, and texture are used in content-based video and image retrieval. Many approaches for integrating these features have been studied. However, the issue of these approaches is how to appropriately assign weighting of key frame features at query time. Therefore, we propose a new video retrieval method using adaptively weighted image features. We performed computer simulations in test databases which consist of various kinds of key frames. The experimental results show that the proposed method has better performance than previous works in respect to several performance evaluations such as precision vs. recall, retrieval efficiency, and ranking measure.
Analysis of Commute Time Embedding Based on Spectral Graph
Hahn, Hee-Il ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 34~42
DOI : 10.9717/kmms.2014.17.1.034
In this paper an embedding algorithm based on commute time is implemented by organizing patches according to the graph-based metric, and its performance is analyzed by comparing with the results of principal component analysis embedding. It is usual that the dimensionality reduction be done within some acceptable approximation error. However this paper shows the proposed manifold embedding method generates the intrinsic geometry corresponding to the signal despite severe approximation error, so that it can be applied to the areas such as pattern classification or machine learning.
Propensity Analysis of Political Attitude of Twitter Users by Extracting Sentiment from Timeline
Kim, Sukjoong ; Hwang, Byung-Yeon ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 43~51
DOI : 10.9717/kmms.2014.17.1.043
Social Network Service has the sufficient potential can be widely and effectively used for various fields of society because of convenient accessibility and definite user opinion. Above all Twitter has characteristics of simple and open network formation between users and remarkable real-time diffusion. However, real analysis is accompanied by many difficulties because of semantic analysis in 140-characters, the limitation of Korea natural language processing and the technical problem of Twitter is own restriction. This thesis paid its attention to human's political attitudes showing permanence and assumed that if applying it to the analytic design, it would contribute to the increase of precision and showed it through the experiment. As a result of experiment with Tweet corpus gathered during the election of national assemblymen on 11st April 2012, it could be known to be considerably similar compared to actual election result. The precision of 75.4% and recall of 34.8% was shown in case of individual Tweet analysis. On the other hand, the performance improvement of approximately 8% and 5% was shown in by-timeline political attitude analysis of user.
A Study on the Fault Analysis and Security Assessment for Smart Card Management System
Jang, Soo-Mi ; Park, Man-Gon ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 52~59
DOI : 10.9717/kmms.2014.17.1.052
These days, smart card management system(SCMS) have been broadly used for security conformability, efficiency of issuance management, key management and expert management in the smart card market. SCMS is composed of card management, issuance management, key management, application management, and issuers management systems. SCMS enables card issuers from banks, credit card companies, and telecommunications companies to provide these cards to card users. And then SCMS enables card users to download new programs to chips for use of these cards successively and provide related smart card data in safety and efficiency. In this paper, we propose a framework for security assessment and an efficient method for security improvement through fault analysis which is more effective.
Selective control of multiple devices via finger recognition
Chang, Ho-Jung ; Kim, Tae-Hyun ; Yoon, Youngmi ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 60~68
DOI : 10.9717/kmms.2014.17.1.060
Extensive researches on PC control system via interaction between PC and users are being conducted recently, especially on human finger recognition in the electronic devices. Heretofore, researches on methods to improve the accuracy of finger recognition in a single device and to control the devices with it have been the mainstream, whereas many different industries where finger recognition become more utilized are demanding researches on methods to selectively control the system of multiple devices for applications in various environments and situations. This article demonstrates attempts to selectively control one of two devices through finger recognition. Along with this, experiments conducted with 6 variable conditions are demonstrated here, where the optimal condition to increase the rate of successful selective finger recognition between two devices is studied.
An Acceleration Technique of Terrain Rendering using GPU-based Chunk LOD
Kim, Tae-Gwon ; Lee, Eun-Seok ; Shin, Byeong-Seok ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 69~76
DOI : 10.9717/kmms.2014.17.1.069
It is hard to represent massive terrain data in real-time even using recent graphics hardware. In order to process massive terrain data, mesh simplification method such as continuous Level-of-Detail is commonly used. However, existing GPU-based methods using quad-tree structure such as geometry splitting, produce lots of vertices to traverse the quad-tree and retransmit those vertices back to the GPU in each tree traversal. Also they have disadvantage of increase of tree size since they construct the tree structure using texture. To solve the problem, we proposed GPU-base chunked LOD technique for real-time terrain rendering. We restrict depth of tree search and generate chunks with tessellator in GPU. By using our method, we can efficiently render the terrain by generating the chunks on GPU and reduce the computing time for tree traversal.
Evaluating Pre-defined Kinetic Typography Effects to Convey Emotions
Lee, Joonhwan ; Kim, Dongwhan ; Wee, Jieun ; Jang, Sooyeun ; Ha, Seyong ; Jun, Soojin ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 77~93
DOI : 10.9717/kmms.2014.17.1.077
Kinetic typography has been suggested to express emotions in computer-mediated communication (CMC) by empowering static texts with dynamic attributes, where conversations occur primarily in text-based forms. In this work, we investigate whether pre-defined kinetic typography effects are capable of delivering emotions, and further, which specific attributes of kinetic typography arouse such emotions. The results show that emotional response of users were corresponding to the emotions intended by experts, indicating that pre-defined kinetic typography is an applicable way to express emotions consistently in CMC. Also, results demonstrate some key attributes that derive certain levels of mood and energy respectively. Energy level turned out to be affected by the font size, transparency, direction of movement, amount of movement, velocity, and acceleration of the text, while mood level was influenced by the transparency, direction of movement, regularity in movement, and speed of the text.
Developing a Mobile Application for Asthma Management and User Test
Jeong, Yoonkwon ; Park, Chan-Sun ; Park, Jongha ; Kim, Hee-Cheol ; Jung, Euitay ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 94~103
DOI : 10.9717/kmms.2014.17.1.094
Asthma is a chronical disease which could be controled by constant management and the patients may lead their daily lives if they are properly supervised. South Korea is one of the most wired nations, and its penetration rate of smart phones will exceed 80% of entire population this year, so managing asthma and communicating with medical staffs with mobile applications, will be very reasonable solution. In this study, medical staffs, developers and UI/UX experts co-worked developed an Android-based application for asthma management. To tell the effectiveness and availability, we made asthma sufferers use this mobile application for more than six months. After six months we surveyed and interviewed the patients. We could find merits and demerits of the applications and we finally suggested new guidelines for version 2.0.
Development and Assessment of Multi-sensory Effector System to Improve the Realistic of Virtual Underwater Simulation
Kim, Cheol-Min ; Youn, Jae-Hong ; Kang, Im-Chul ; Kim, Byung-Ki ;
Journal of Korea Multimedia Society, volume 17, issue 1, 2014, Pages 104~112
DOI : 10.9717/kmms.2014.17.1.104
With recent development of virtual reality technology, coupled with the growth of the marine industry, virtual underwater simulation systems are under development in various studies, for educational purposes and to simulate virtual reality experiences. Current literature indicates many underwater simulation systems to date have focused on the quality of visual stimulus delivered through three-dimensional graphics user interface, limiting the reality of the experience. In order to improve the quality of the reality delivered by such virtual simulations, it is crucial to develop multi-sensory technology rather than focus on the conventional audio-visual interaction, which limits experiencer from the sense of underwater immersion and existence within the simulation. This work proposes the immersive multi-sensory effector system, delivering the users with a more realistic underwater experience. The sense of reality perceived was evaluated, as the main factor of the virtual reality system.