• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.503-510
• /
• 2018

Restoring of damaged images is a fundamental problem that was attempted before digital image processing technology appeared. Various algorithms for reconstructing damaged images have been introduced. However, the results show inferior restoration results compared with manual restoration. Recent developments of DNN (Deep Neural Network) have introduced various studies that apply it to image restoration. However, if the wide area is damaged, it can not be solved by a general interpolation method. In this case, it is necessary to reconstruct the damaged area through contextual information of surrounding images. In this paper, we propose an image restoration network using a generative adversarial network (GAN). The proposed system consists of image generation network and discriminator network. The proposed network is verified through experiments that it is possible to recover not only the natural image but also the texture of the original image through the inference of the damaged area in restoring various types of images.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.953-964
• /
• 2020

Ever since media contents took over the world, the importance of typography has increased, and the influence of fonts has be n recognized. Nevertheless, the current Hangul font system is very poor and is provided passively, so it is practically impossible to understand and utilize all the shape characteristics of more than six thousand Hangul fonts. In this paper, the characteristics of Hangul font shapes were selected based on the Hangul structure of similar fonts. The stroke element detection training was performed by fine tuning Faster R-CNN Inception v2, one of the deep learning object detection models. We also propose a system that automatically extracts the stroke element characteristics from characters by introducing an automatic extraction algorithm. In comparison to the previous research which showed poor accuracy while using SVM(Support Vector Machine) and Sliding Window Algorithm, the proposed system in this paper has shown the result of 10 % accuracy to properly detect and extract stroke elements from various fonts. In conclusion, if the stroke element characteristics based on the Hangul structural information extracted through the system are used for similar classification, problems such as copyright will be solved in an era when typography's competitiveness becomes stronger, and an automated process will be provided to users for more convenience.

• Proceedings of the Korea Contents Association Conference
• /
• 2006.11a
• /
• pp.292-295
• /
• 2006

As Chinese characters occupies more than 70% of words we currently use, the education of Chinese characters is becoming important day by day to accurately deliver the meaning of words in our language life. In recent, there are increasing concerns on writing Chinese characters correctly as well as reciting, books and Internet contents on Chinese character writing is emerging. However, currently available Internet media on the Chinese characters education only illuminates recitation and interpretation. Moreover, the writing part is merely provided in the form of paper by printing the characters, thus, writing materials are insufficient. In this paper, we propose a design and implementation of Web based Chinese characters writing system. Using the system, a user can write Chinese characters with mouse device. The learning progress is accordingly managed for the user. In addition, the proposed system can be used any place in where Internet is connected.

• Archives of design research
• /
• v.13 no.3
• /
• pp.69-80
• /
• 2000

Body has been high-lightened as one of the most important theme since the philosophy and the arts are focused on it in the late 20 century. Resurgence of interests in human body has been based on the skepticism on rapid digitalization and do-materialization currently undergoing in electronic media environments. Artists have been endeavoring more and more to find a synthesis which links the conceptual and the sensuous in their works as digitalization gets faster and faster. The Bodily-oriented art uses its visceral qualities, either literally or metaphorically, to engage our total being, not just our mental consciousness, in building a sensuous, evocative statement. Its transcendent ideas are inter- mixed with the fabric of the world. We are touched by this art not only because we understand it cognitively, but because we "feel"it. These characteristics of textile arts caused gradual increase of soft-sculpture works using textiles and implies possibilities of inter-grade of physical and mental world. Ann Hamilton, Magdalena Abakanowiz, Folly Apfelbaum and Pallid Dougherty are, for example, related to the fiber arts. It would be of worth to study the characteristics of contemporary faber-art works, especially done by Abakanowiz who has been regarded as a dominant pioneer in the contemporary fiber arts from the viewpoint of inter-grade of the physicals and the mental. This paper, therefore, deals with the Abaknowiz′works in the context of human body and body-signs. Life and works might be classified into 5 stages; first, learning period since her birth in 1930, second, creation period of Abakan, third, remodelling period of Abakan, fourth, composition and dissolution period of Abakan and the last and fifth, new transformation period of Abakan. ′Abakan′through her whole life as an artist has been a plastic language and based ultimately on external human body but in various materials and forms.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.83-86
• /
• 2019

도시화 과정에서 도시의 생활폐기물 문제가 빠르게 증가되고 있고, 효과적이지 못한 생활폐기물 관리는 도시의 오염을 악화시키고 물리적인 환경오염과 경제적인 부분에서 극심한 문제들을 야기시킬 수 있다. 게다가 부피가 커서 관리하기 힘든 대형 생활폐기물들이 증가하여 도시 발전에도 방해가 된다. 생활폐기물을 처리하는데 있어 대형 생활폐기물 품목에 대해서는 요금을 청구하여 처리한다. 다양한 유형의 대형 생활폐기물을 수동으로 분류하는 것은 시간과 비용이 많이 든다. 그 결과 대형 생활폐기물을 자동으로 분류하는 시스템을 도입하는 것이 중요하다. 본 논문에서는 대형 생활폐기물 분류를 위한 시스템을 제안하며, 이 논문의 4 가지로 분류된다. 1) 높은 정확도와 강 분류(roust classification) 수행에 적합한 Convolution Neural Network(CNN) 모델 중 VGG-19, Inception-V3, ResNet50 의 정확도와 속도를 비교한다. 제안된 20 개의 클래스의 대형 생활폐기물의 데이터 셋(data set)에 대해 가장 높은 분류의 정확도는 86.19%이다. 2) 불균형 데이터 문제를 처리하기 Class Weight VGG-19(CW-VGG-19)와 Extreme Gradient Boosting VGG-19 두 가지 방법을 사용하였다. 3) 20 개의 클래스를 포함하는 데이터 셋을 수동으로 수집 및 검증하였으며 각 클래스의 컬러 이미지 수는 500 개 이상이다. 4) 딥 러닝(Deep Learning) 기반 모바일 애플리케이션을 개발하였다.

• The Journal of Korean Medicine Ophthalmology and Otolaryngology and Dermatology
• /
• v.18 no.2
• /
• pp.70-79
• /
• 2005

Background: Otitis media with effusion(OME) is one of the most common disease in childhood. Patient suffers from OME in many quarters. For example hearing loss, effects on speech, language, learning, behaviouralchanges etc. But the diagnosis of OME is difficult using only medical history and otoscopy. So, many other diagnostic tools are developed and tympanometry is one of them. When OME is treated by oriental medical Tx, tympanometry would be useful instrument. Objectives: To gain insight into the usability of tympanometry in F/U of OME treated by oriental medial Tx. Methods: Data was collected from 123 ears of 74 children who was treated by oriental medical Tx. Data includes sex, age, period of Tx, elapsed time to be improved, tympanograms and accompanied symptoms. The relationship between items was analysed by statistical methods. Results: There is no relationship between age, sex and period of Tx/elapsed time to be improved. When cough and phlegm is accompanied, the period of treatment and elapsed time to be improved are expanded. When improvement was seen on tympanogram, the period of treatment is expanded but the improvement was seen within 30days, the period of treatment is reduced. Conclusion: The application of tympanometry in oriental medical treatment of OME would provide us many informations about the status of patient so it will be helpful to predict the history of a case and to make a decision whether keep up treatment or not.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.1
• /
• pp.7-15
• /
• 2009

In this paper, a novel framework that synthesizes and clones facial expression in parameter spaces is presented. To overcome the difficulties in manipulating face geometry models with high degrees of freedom, many parameterization methods have been introduced. In this paper, a data-driven parameterization method is proposed that represents a variety of expressions with a small set of fundamental independent movements based on the ICA technique. The face deformation due to the parameters is also learned from the data to capture the nonlinearity of facial movements. With this parameterization, one can control the expression of an animated character's face by the parameters. By separating the parameterization and the deformation learning process, we believe that we can adopt this framework for a variety applications including expression synthesis and cloning. The experimental result demonstrates the efficient production of realistic expressions using the proposed method.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.2
• /
• pp.103-121
• /
• 2013

This study is to examine the basic structure of the professional development of school librarians and to analyze the national evaluation standards, and the states' evaluation tools and self-assessment tool currently used in the United States. The result is as follows: the structure of the school librarians' professional development processes, such as curriculum, certificate, and evaluation, have been affected by the national school library standards published by AASL. NBPTS's Library Media Standards and AASL's Learning4Life evaluation system are proposed as the representative national standards. Many states have developed their standards and tools to evaluate school librarians' performance, these standards are related to the national standards. AASL published A 21st-Century Approach to School Librarian Evaluation for school librarians' self-assessment in 2012, this workbook shows a specific way of developing their expertise.

• Communications of Mathematical Education
• /
• v.28 no.2
• /
• pp.179-193
• /
• 2014

After National Mathematics Education Advanced Plan represented in 2012, mathematics education fields began to attention to 'Storytelling'. Because the plan contains important topics, reinforcing mathematics education, improving understanding about mathematics, and enhancing self-guided learning. As one of the methods for improving understanding about mathematics, Storytelling in mathematics is emphasizing recently. The purpose of this study is to analyse the articles about 'Storytelling Mathematics' to find how the media report it. Also, we discuss the direction of Storytelling in mathematics education. The conclusion of this study is that most of the privately-owned company is using the Storytelling as a tool for advertising commercially. Readers have to make a decision which articles are true or useful. A policy makers must ponder how the 'Storytelling Mathematics' policy affect the demands and suppliers in education.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.176-184
• /
• 2020

Due to constant development and decline on Seoul areas the Seoul government is pushing various policies to regenerate declined Seoul areas. Theses various policies lead to land-use changes around numerous Seoul districts. This study aims to create prediction model which can foresee future land-use changes and while doing so, tried to derive various influential factors which leads to land-use changes. To do so, various open-data from national departments and Seoul government have been collected and implemented into random forest algorithm. The results showed promising accuracy and derived multiple influential factors which causes land-use changes around Seoul districts. The result of this study could further be implemented in policy makings for the public sectors, or could also be used as basis for studying gentrification problems happening in Seoul Area.