• Smart Media Journal
• /
• v.10 no.2
• /
• pp.22-29
• /
• 2021

In the past decade, deep learning has been applied to various medical image analysis tasks. Skeletal bone age estimation is clinically important as it can help prevent age-related illness and pave the way for new anti-aging therapies. Recent research has applied deep learning techniques to the task of bone age assessment and achieved positive results. In this paper, we propose a bone age prediction method using a deep convolutional neural network. Specifically, we first train a classification model that automatically localizes the most discriminative region of an image and crops it from the original image. The regions of interest are then used as input for a regression model to estimate the age of the patient. The experiments are conducted on a whole-body scintigraphy dataset that was collected by Chonnam National University Hwasun Hospital. The experimental results illustrate the potential of our proposed method, which has a mean absolute error of 3.35 years. Our proposed framework can be used as a robust supporting tool for clinicians to prevent age-related diseases.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.24-24
• /
• 2023

This presentation highlights the IAHR book, recently published last April, of which the author is the editor-in-chief, on the historical water projects and traditional water technologies of international interest in the Asian region, addressing information on past water projects (mostly before the 20th century) in the regions that are technically and culturally of interest and educationally valuable. The book explores historical water projects in these regions, presenting technologies used at the time, including calculation and forecasting methods, measurement, material, labor, methodologies, and even water culture. Through this book, it is expected that the old Asian wisdom of "reviewing the old and learning the new" would be realized to a certain extent in modern planning and practice of water projects. The book comprises a lead article that the presenter authored and five Parts representing China, Japan, Korea, South Asia, and Southeast Asia, respectively, followed by an invited one from Uzbekistan. Throughout the book, it is found that historically the Asian monsoon, affecting the Indian subcontinent and Southeast and East Asian regions, induced rice cultivation. It fundamentally needs proper irrigation systems, including reservoirs (dams) and canals, water wheels, and even rain gauges. Flood risks have been more common in Asia than Europe under this climate condition, as recognized in history. To utilize and sometimes overcome these climate conditions, people built and managed many historical and grandiose water projects and invented and used localized but sophisticated water-related technologies in the Asian region.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.36 no.6
• /
• pp.396-402
• /
• 1987

A Composite method of finite element and boundary integral methods is introduced to solve the magnetostatic field problems with open boundary. Only the region of prime interest is taken as the compution region where the finite element method is applied. The boundary conditions of the region are dealt with using boundary integral method. The boundary integration in the boundary integral method is done by numerical and analytical techniques repectively. The proposed method is applied to a simple linear problem, and the results are compared with those of the finite element method and the analytic solutions. It is concluded that the proposed method gives more accurate results than the finite element method under the same computing efforts.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.1003-1006
• /
• 1999

Hand segmentation and tracking is essential to the development of a hand gesture recognition system. This research features segementation and tracking of hand regions based the hue component of color. We propose a method that employs HSI color model, and segments and tracks hand regions using the hue component of color alone. In order to track the segmented hand regions, we only apply Kalman filter to a region of interest represented by a rectangle region. Initial experimental results show that the system accurately segments and tracks hand regions although it only uses the hue compoent of color. The system yields near real time throghput of 8 frames per second on a Pentium II 233MHz PC.

• Journal of Fisheries and Marine Sciences Education
• /
• v.28 no.3
• /
• pp.727-737
• /
• 2016

This study is aimed to analyze the economic effectiveness (direct fishing income effect) of the marine afforestation project in Gangneung region. Based on the surveyed data, the production values and costs of the marine afforestation project are estimated and compared to determine the economic validity of the marine afforestation project. Results show that the B/C ratio, as an indicator of economic evaluation, is 1.30 with an interest rate of 5.5%, indicating that the marine afforestation project in Gangneung region would be economically feasible under the current production and market conditions. However, it is expected that the economic effectiveness would be increased when considering benefits of recreational fishing and greenhouse gas reduction from the marine afforestation project.

• ETRI Journal
• /
• v.28 no.2
• /
• pp.239-242
• /
• 2006

In this letter, we propose a new functionality to scalable video coding (SVC), that is, the support of multiple region of interests (ROIs) for heterogeneous display resolution. The main objective of SVC is to provide temporal, spatial, and quality scalability of an encoded bitstream. The ROI is an area that is semantically important to a particular user, especially users with heterogeneous display resolutions. Less transmission bandwidth is needed compared to when the entire region is transmitted/decoded and then sub-sampled or cropped. To support multiple ROIs in SVC, we adopt flexible macroblock ordering (FMO), a tool defined in H.264, and based on it, we propose a way to encode and, independently, decode ROIs. The proposed method is implemented on the joint scalable video model (JSVM) and its functionality verified.

• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.592-601
• /
• 2013

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.

• Journal of information and communication convergence engineering
• /
• v.3 no.1
• /
• pp.56-61
• /
• 2005

In this paper, we present a video rate control scheme for storage and delivery in which the time-varying viewing interests are controlled by human gaze. To track the gaze, the pupil's movement is detected using the three-step process : detecting face region, eye region, and pupil point. To control bit rates, the quantization parameter (QP) is changed by considering the static parameters, the video object priority derived from the pupil tracking, the target PSNR, and the weighted distortion value of the coder. As results, we achieved human interfaced visual model and corresponding region-of-interest rate control system.

• Korean Journal of Heritage: History & Science
• /
• v.48 no.3
• /
• pp.204-219
• /
• 2015

International society, including the United Nations, has recently been making efforts to further promote a rapprochement of cultures in relation to alleviating military and political conflicts and other social clashes. In line with these efforts at the international level, there has been a growing interest on Central Asia and, in particular, on the Silk Road, which functioned as a trade route among ancient civilizations in the region and is also seen as a route that promoted cultural dialogue and exchanges. Given the amount of cross cultural dialogue and exchange, it is no surprise that intangible cultural heritage has historically been abundant and easily found in the region. However, this heritage was placed in considerable risk because heritage transmission critically weakened for seventy years under Soviet rule. Fortunately, since independence, there has been increasing interest in restoring community identity and reviving intangible heritage. Nevertheless, in spite of this interest, a lack of policies and cultural support in each country has made heritage safeguarding difficult. In this paper, I analyze the various phenomena that took place after the concept and international trends on ICH were introduced and speak about the experiences and outcomes obtained from collaborative network projects by ICHCAP and the Central Asian countries over the last six year. In addition, I would like take this opportunity to discuss how we can understand and develop collaboration in the intangible heritage field in Central Asia in a long-term perspective.

• Environmental Sciences Bulletin of The Korean Environmental Sciences Society
• /
• v.4 no.2
• /
• pp.111-116
• /
• 2000

Transboundary air pollution has recently become an area of increasing scientific interest and political concern as countries are receiving air pollutants from their neighbors. In order to gain a better understanding of the long-range transport processes of air pollutants and the source-receptor relationships among neighboring countries, an atmospheric transport model coupled with a RAMS(Regional Atmospheric Modeling System) model was applied to the East Asia region during the entire month of January 1993. The scalar transport option of the RAMS model was used to calculate special atmospheric constituents such as trace gases or aerosols. The sulfate production in clouds and rainwater and its removal processes by dry and wet deposition were considered. The sulfate budget from source regions to receptor regions was estimated by analysing the source-receptor relationships. When a specific receptor site revealed a sulfate value higher than the sulfate concentration based on its own source origin, this was taken to indicate long-range transport from another source region. The contribution ratio from various source region was calculated. The contribution ratio of dry and wet deposition was higher on the main continent of the East region. Furthermore, the high deposition amounts were identified on the west coast of Korea and the East China Sea.