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 16, Issue 12 - Dec 2013
Volume 16, Issue 11 - Nov 2013
Volume 16, Issue 10 - Oct 2013
Volume 16, Issue 9 - Sep 2013
Volume 16, Issue 8 - Aug 2013
Volume 16, Issue 7 - Jul 2013
Volume 16, Issue 6 - Jun 2013
Volume 16, Issue 5 - May 2013
Volume 16, Issue 4 - Apr 2013
Volume 16, Issue 3 - Mar 2013
Volume 16, Issue 2 - Feb 2013
Volume 16, Issue 1 - Jan 2013
Selecting the target year
A Novel Feature Selection Method for Output Coding based Multiclass SVM
Lee, Youngjoo ; Lee, Jeongjin ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 795~801
DOI : 10.9717/kmms.2013.16.7.795
Recently, support vector machine has been widely used in various application fields due to its superiority of classification performance comparing with decision tree and neural network. Since support vector machine is basically designed for the binary classification problem, output coding method to analyze the classification result of multiclass binary classifier is used for the application of support vector machine into the multiclass problem. However, previous feature selection method for output coding based support vector machine found the features to improve the overall classification accuracy instead of improving each classification accuracy of each classifier. In this paper, we propose the novel feature selection method to find the features for maximizing the classification accuracy of each binary classifier in output coding based support vector machine. Experimental result showed that proposed method significantly improved the classification accuracy comparing with previous feature selection method.
A Similarity Measurement and Visualization Method for the Analysis of Program Code
Lee, Youngjoo ; Lee, Jeongjin ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 802~809
DOI : 10.9717/kmms.2013.16.7.802
In this paper, we propose the similarity measurement method between two program codes by counting the frequency and length of continuous patterns of specifiers and keywords, which exist in two program codes. In addition, we propose the visualization method of this analysis result by formal concept analysis. Proposed method considers adjacencies of specifiers or keywords, which have not been considered in the previous similarity measurements. Proposed method can detect the plagiarism by analyzing the pattern in each function regardless of the order of function call and execution. In addition, the result of the similarity measurement is visualized by the lattice of formal concept analysis to increase the user understanding about the relations between program codes. Experimental results showed that proposed method succeeded in 96% plagiarism detections. Our method could be applied into the analysis of general documents.
A Context-Aware Information Service using FCM Clustering Algorithm and Fuzzy Decision Tree
Yang, Seokhwan ; Chung, Mokdong ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 810~819
DOI : 10.9717/kmms.2013.16.7.810
FCM (Fuzzy C-Means) clustering algorithm, a typical split-based clustering algorithm, has been successfully applied to the various fields. Nonetheless, the FCM clustering algorithm has some problems, such as high sensitivity to noise and local data, the different clustering result from the intuitive grasp, and the setting of initial round and the number of clusters. To address these problems, in this paper, we determine fuzzy numbers which project the FCM clustering result on the axis with the specific attribute. And we propose a model that the fuzzy numbers apply to FDT (Fuzzy Decision Tree). This model improves the two problems of FCM clustering algorithm such as elevated sensitivity to data, and the difference of the clustering result from the intuitional decision. And also, this paper compares the effect of the proposed model and the result of FCM clustering algorithm through the experiment using real traffic and rainfall data. The experimental results indicate that the proposed model provides more reliable results by the sensitivity relief for data. And we can see that it has improved on the concordance of FCM clustering result with the intuitive expectation.
Speed Improvement of SURF Matching Algorithm Using Reduction of Searching Range Based on PCA
Kim, Onecue ; Kang, Dong-Joong ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 820~828
DOI : 10.9717/kmms.2013.16.7.820
Extracting unique features from an image is a fundamental issue when making panorama images, acquiring stereo images, recognizing objects and analyzing images. Generally, the task to compare features to other images requires much computing time because some features are formed as a vector which has many elements. In this paper, we present a method that compares features after reducing the feature dimension extracted from an image using PCA(principal component analysis) and sorting the features in a linked list. SURF(speeded up robust features) is used to describe image features. When the dimension reduction method is applied, we can reduce the computing time without decreasing the matching accuracy. The proposed method is proved to be fast and robust in experiments.
Lung Segmentation Considering Global and Local Properties in Chest X-ray Images
Jeon, Woong-Gi ; Kim, Tae-Yun ; Kim, Sung Jun ; Choi, Heung-Kuk ; Kim, Kwang Gi ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 829~840
DOI : 10.9717/kmms.2013.16.7.829
In this paper, we propose a new lung segmentation method for chest x-ray images which can take both global and local properties into account. Firstly, the initial lung segmentation is computed by applying the active shape model (ASM) which keeps the shape of deformable model from the pre-learned model and searches the image boundaries. At the second segmentation stage, we also applied the localizing region-based active contour model (LRACM) for correcting various regional errors in the initial segmentation. Finally, to measure the similarities, we calculated the Dice coefficient of the segmented area using each semiautomatic method with the result of the manually segmented area by a radiologist. The comparison experiments were performed using 5 lung x-ray images. In our experiment, the Dice coefficient with manually segmented area was
for the proposed method. Effective segmentation methods will be essential for the development of computer-aided diagnosis systems for a more accurate early diagnosis and prognosis regarding lung cancer in chest x-ray images.
Reversible Watermarking based Video Contents Management and Control technique using Biological Organism Model
Jang, Bong-Joo ; Lee, Suk-Hwan ; Kwon, Ki-Ryong ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 841~851
DOI : 10.9717/kmms.2013.16.7.841
The infectious information hiding system(IIHS) is proposed for secure distribution of high quality video contents by applying optimized watermark embedding and detection algorithms to video codecs. And the watermark as infectious information is transmitted while target video is displayed or edited by codecs. This paper proposes a fast and effective reversible watermarking and infectious information generation for IIHS. Our reversible watermarking scheme enables video decoder to control video quality and watermark strength actively for by adding control code and expiration date with the watermark. Also, we designed our scheme with low computational complexity to satisfy it`s real-time processing in a video codec, and to prevent time or frame delay during watermark detection and video restoration, we embedded one watermark and one side information within a macro-block. Experimental results verify that our scheme satisfy real-time watermark embedding and detection and watermark error is 0% after reversible watermark detection. Finally, we conform that the quality of restored video contens is almost same with compressed video without watermarking algorithm.
High Quality Volume Rendering Using the Empty Space Jittering and the Sampling Alignment Method
Kye, Heewon ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 852~861
DOI : 10.9717/kmms.2013.16.7.852
When users use medical volume rendering applications, selecting specific region of volume data and observing the region by magnification is a common process.As the wood-grain artifact is arise from the magnified image, the jittered sampling technique has been used to remove the problem. However, the jittered sampling leads to some noise along the volume edge. In this research, we reveal the reason of the noise, and present a solution. To remove the wood-grain artifact without the noise, we propose the empty space jittering and the sampling alignment method. Using these methods, we can produce high quality volume rendering images without noticeable time consuming.
Interference Resolving Radio Resource Allocation Scheme in a TDD-OFDMA/FDD-CDMA Hierarchical Over lay Cellular System
Lee, Yeonwoo ; Kim, Kyung-Ho ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 862~869
DOI : 10.9717/kmms.2013.16.7.862
In order to support a cell-independent traffic asymmetry, the conventional TDD system cannot avoid crossed time slot (CTS) interference. Moreover, the TDD/FDD hierarchical overlay cellular systems is taken into account as a generally accepted cell model in a heterogeneous radio environment. In this paper, we propose an interference resolving radio resource allocation technique in a TDD-OFDMA cellular system that overlays a FDD-CDMA cell. In our proposed scheme, we exploit under-used FDD-CDMA uplink resource by TDD mobile abiding by a region based time slot(TS) allocation which in turn mitigates CTS interference considerably. It is demonstrated that combined with under-used resource utilization scheme based on mobile`s location, the proposed technique can reduce CTS interference considerably and support the asymmetric traffic in TDD system.
A Fingerprint Classification Method Based on the Combination of Gray Level Co-Occurrence Matrix and Wavelet Features
Kang, Seung-Ho ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 870~878
DOI : 10.9717/kmms.2013.16.7.870
In this paper, we propose a novel fingerprint classification method to enhance the accuracy and efficiency of the fingerprint identification system, one of biometrics systems. According to the previous researches, fingerprints can be categorized into the several patterns based on their pattern of ridges and valleys. After construction of fingerprint database based on their patters, fingerprint classification approach can help to accelerate the fingerprint recognition. The reason is that classification methods reduce the size of the search space to the fingerprints of the same category before matching. First, we suggest a method to extract region of interest (ROI) which have real information about fingerprint from the image. And then we propose a feature extraction method which combines gray level co-occurrence matrix (GLCM) and wavelet features. Finally, we compare the performance of our proposed method with the existing method which use only GLCM as the feature of fingerprint by using the multi-layer perceptron and support vector machine.
Elements for Evaluating the Usability of the Web-Based Infographic Design
Kwon, Hyo-Jeong ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 879~887
DOI : 10.9717/kmms.2013.16.7.879
In the recently diversified web environment, the existing methodologies for studying and evaluating the usability of infographics have limit in being applied to new user experience environment. To ensure effective web design that considers various user environments, research needs to be done for such usability of infographics that executes `simplification and compression of information`. The purpose of this study is to understand the expandability of web-based infographic design, re-establish its concept, and produce the elements involved in the usability evaluation to come up with effective data on user experience. It is expected that this study will be used as a basic research for elucidating the connection to type-based or experienced-based data through convergence of various areas of information technology in the continuously transforming smart media environment.
Conceptual Metaphor based on Embodied Cognition
Kim, Hyung-Woo ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 888~896
DOI : 10.9717/kmms.2013.16.7.888
The existing interface study has been focused on rhetorical metaphor based on a cognitive viewpoint in traditional objectivism. But the existing study viewpoint about the interface shows logical limitation by the changes in media environment. This study suggests conceptual metaphor based on embodied cognition for an alternative to solve the limitation, and research logical suitability of the existing interface environment. The result of this study is as follow; The first, the embodied cognitive viewpoint provides the interface as a space for holistic recognition communication, and the conceptual metaphor based on embodied cognition provides a well-structured metaphor logic and is a suitable metaphor to explain complicated metaphor structure. The second, the container image schema provides concrete and detailed metaphor structure than previous metaphor when it comes to explaining desktop metaphor by offering subsidiary image schema from `IN-OUT-BOUNDARY` image schema. The third, path image schema is possible to make a concrete logic and works off the laxity and confusion of logical structure in existing metaphor by offering subsidiary image schema from `SOURCE-PATH-GOAL` image schema. The conceptual metaphor based on embodied cognition is expected to be a basic theory to explain interfaces for various media environment by thinking of human physical experience as container and path image schema.
Design of a set of One-to-Many Node-Disjoint and Nearly Shortest Paths on Recursive Circulant Networks
Chung, Ilyong ;
Journal of Korea Multimedia Society, volume 16, issue 7, 2013, Pages 897~904
DOI : 10.9717/kmms.2013.16.7.897
The recursive circulant network G(N,d) can be widely used in the design and implementation of parallel processing architectures. It consists of N identical nodes, each node is connected through bidirectional, point-to-point communication channels to different neighbors by jumping
- 1. In this paper, we investigate the routing of a message on
, a special kind of RCN, that is key to the performance of this network. On
we would like to transmit k packets from a source node to k destination nodes simultaneously along paths on this network, the
packet will be transmitted along the
. In order for all packets to arrive at a destination node quickly and securely, we present an
routing algorithm on
for generating a set of one-to-many node-disjoint and nearly shortest paths, where each path is either shortest or nearly shortest and the total length of these paths is nearly minimum since the path is mainly determined by employing the Hungarian method.