• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.1
• /
• pp.135-142
• /
• 2013

Contour detection is important for many computer vision applications, such as shape discrimination and object recognition. In many cases, local luminance changes turn out to be stronger in textured areas than on object contours. Therefore, local edge features, which only look at a small neighborhood of each pixel, cannot be reliable indicators of the presence of a contour, and some global analysis is needed. The novelty of this operator is that dilation is limited to Deluanary triangular. An efficient implementation is presented. The grouping algorithm is then embedded in a multi-threshold contour detector. At each threshold level, small groups of edges are removed, and contours are completed by means of a generalized reconstruction from markers. Both qualitative and quantitative comparison with existing approaches prove the superiority of the proposed contour detector in terms of larger amount of suppressed texture and more effective detection of low-contrast contour.

• Journal of KIISE:Software and Applications
• /
• v.31 no.3
• /
• pp.379-386
• /
• 2004

Video segmentation is a fundamental task in video indexing and it includes two kinds of shot change detections such as the abrupt transition and the gradual transition. The abrupt shot boundaries are detected by computing the image-based distance between adjacent frames and comparing this distance with a pre-determined threshold value. However, the gradual shot boundaries are difficult to detect with this approach. To overcome this difficulty, we propose the method that detects gradual transition in the MPEG compressed video using the HMM (Hidden Markov Model). We take two different HMMs such as a discrete HMM and a continuous HMM with a Gaussian mixture model. As image features for HMM's observations, we use two distinct features such as the difference of histogram of DC images between two adjacent frames and the difference of each individual macroblock's deviations at the corresponding macroblock's between two adjacent frames, where deviation means an arithmetic difference of each macroblock's DC value from the mean of DC values in the given frame. Furthermore, we obtain the DC sequences of P and B frame by the first order approximation for a fast and effective computation. Experiment results show that we obtain the best detection and classification performance of gradual transitions when a continuous HMM with one Gaussian model is taken and two image features are used together.

• Journal of the Korean Geographical Society
• /
• v.43 no.6
• /
• pp.981-1001
• /
• 2008

This research deals with cognitive characteristics of point symbols on the current tourist maps in terms of the communication theory in considering levels of symbolization and those of preference. The levels of symbolization are examined on the basis of the meaning of point symbols between map-makers and map-users. Preferences of point symbols are investigated by the tourist objects. As a result, when point symbols are expressed in conciseness, the meaning and interpretation about those symbols are highly accorded. And the point symbols that have familiarity by visual experience are preferred. Also, the higher symbolical levels symbols have, the more likely they are preferred. Through that fact, familiarity from the visual experience, conciseness in expression, concreteness of figures expressed in maps, and representativeness of visualized properties were deduced as factors that affect preferences. Those factors work to affect preference complicatedly, but familiarity is prior to simplicity in preferences. Likewise, ways that visualize information, contents that are expressed as images and familiarity in terms of cognitive characteristics make a relative difference in preferences and the levels of symbolization. On the basis of those cognitive characteristics, visual complexity and ambiguity should be removed and the higher symbolical level of point symbols for efficiency of map-reading should be developed.

• The Journal of the Korea Contents Association
• /
• v.11 no.7
• /
• pp.519-527
• /
• 2011

The e-Learning program is a multimedia data program consisting of texts, images, animation, audio and video. The development of an e-Learning program requires time and is a complex process, requiring cooperation and open-communication between all parties involved, particularly in the event of a problem. This study will analyze the e-Learning contents development process from the Social Negotiation Perspective. An appropriate process for the development of the program and effective decision-making guidelines for those parties involved will be recommended. Participants' viewpoints regarding program development and guidelines were studied qualitatively, while the evaluation of developed content employed both qualitative and quantitative research. The study found the following results. First, the development of an e-Learning program requires a clear goal and purpose. Second, the target group must be clearly identified. Third, all parties involved must share in the development process and its outcomes. Fourth, the party requesting the program must allocate the appropriate time and budget for the development group. Finally, the project requires a strong, capable leadership for effective decision-making.

• Journal of Biomedical Engineering Research
• /
• v.39 no.5
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.

• Korean Security Journal
• /
• no.34
• /
• pp.139-160
• /
• 2013

Growth of minors learning space that the school is a place where many students live. Students, but in the living space of these minors values of change and chaos that occurs in addition to school safety incidents typically occur many accidents and potential for accidents to occur. Tinking of these potential events. Indifferent about the safety of schools and teachers with the much more conscious of the safety of the students lean due to being generated. Body and life, and damage to property due to these events. Accidents due to wear and sometimes liability and indemnity issues surrounding tarnished with the image of the school and teachers look forward to hearing from parents about the school deterioration, resulting in an unfavorable impact. Therefor in this essay, we are presenting case analysis may occur or re-occur. Prevent accidents that can identify and Countermeasures against accidents that occur within the school.

• Journal of the Korean Geographical Society
• /
• v.51 no.1
• /
• pp.89-108
• /
• 2016

This paper aims to illustrate how the third generation bike sharing schemes (BSS) are operated in Korea and identify the possible factors that have made cities to adopt and maintain BSS successfully in Korea. For this, the paper selects the case of Nubija in Changwon as the representative and the most successful BSS case in Korea. It identifies three major factors that have made the city to adopt Nubija. First, Nubija was initiated as a part of the bigger project of 'Environmental Capital' aiming to develop the city as a world class green city attempted by the city government. Second, the mayor's willingness to learn and adopt European model cities of environmental capital and green transportation played a decisive role in developing Nubija. Third, the city government was able to implement BSS policy in a top-down manner so the policy process was relatively speedy and effective. Also Nubijia became a stable policy because the city has gained international reputation as a Korea's representative green city, and as a result, the city's BSS policy has passed the point of no return. In the future, channels should be made for active citizen participation in the decision making process of Nubija so that they can cooperate with the city government to develop Nubija further.

• Information Systems Review
• /
• v.9 no.1
• /
• pp.45-65
• /
• 2007

In medical industry, health insurance bill audit is unique and essential process in general hospitals. The health insurance bill audit process is very important because not only for hospital's profit but also hospital's reputation. Particularly, at the large general hospitals many related workers including analysts, nurses, and etc. have engaged in the health insurance bill audit process. This paper introduces a case of health insurance bill audit for finding reducible health insurance bill cases using decision tree induction techniques at a large general hospital in Korea. When supervised learning methods had been tried to be applied, one of major problems was data imbalance problem in the health insurance bill audit data. In other words, there were many normal(passing) cases and relatively small number of reduction cases in a bill audit dataset. To resolve the problem, in this study, well-known methods for imbalanced data sets including over sampling of rare cases, under sampling of major cases, and adjusting the misclassification cost are combined in several ways to find appropriate decision trees that satisfy required conditions in health insurance bill audit situation.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.44 no.4
• /
• pp.43-54
• /
• 2007

This paper presents design and verification of a face detection hardware for real time application. Face detection algorithm detects rough face position based on already acquired feature parameter data. The hardware is composed of five main modules: Integral Image Calculator, Feature Coordinate Calculator, Feature Difference Calculator, Cascade Calculator, and Window Detection. It also includes on-chip Integral Image memory and Feature Parameter memory. The face detection hardware was verified by using S3C2440A CPU of Samsung Electronics, Virtex4LX100 FPGA of Xilinx, and a CCD Camera module. Our design uses 3,251 LUTs of Xilinx FPGA and takes about 1.96${\sim}$0.13 sec for face detection depending on sliding-window step size, when synthesized for Virtex4LX100 FPGA. When synthesized on Magnachip 0.25um ASIC library, it uses about 410,000 gates (Combinational area about 345,000 gates, Noncombinational area about 65,000 gates) and takes less than 0.5 sec for face realtime detection. This size and performance shows that it is adequate to use for embedded system applications. It has been fabricated as a real chip as a part of XF1201 chip and proven to work.

• The Journal of the Korea Contents Association
• /
• v.13 no.2
• /
• pp.19-31
• /
• 2013

Since the high readable source codes help us to understand and modify the program, it is much easy to maintain them. The readability of source code is not only affected by the complexity of algorithms such as control structures but also affected by the coding styles such as naming and indentation. Although various coding standards have been presented for promoting the readability of source codes, it has been usually lost or ignored in a programming course. One of the reasons is that the coding standard is not a hard-and-false rule since it does not contribute to the performance of software. In this paper, we propose a simple automatic system, namely StyleJigsaw, which checks the style of the source codes written by C/C++ or Java. In this system, the coding style score is calculated and visualized as a jigsaw puzzle. To measure the educational effectiveness of StyleJigsaw, several experiments have been conducted on a class students in C++ programming course. According to the experimental results, the coding style score increased about 8.0 points(10.9%) on average using StyleJigsaw. Further, according to a questionnaire survey targeting the students who attended the programming course, about 88.5% of the students responded that StyleJigsaw was of help to learn the coding standards. We expect that the StyleJigsaw can be effectively used to encourage the students to obey the coding standards, resulting in high readable programs.