http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
최흥국(Choi Heung Kook) 한국정보처리학회 1999 정보처리학회논문지 Vol.6 No.1
In this paper, we suggest a new direct method for image segmentation using texture and color information combined through a mutivariate linear discriminant algorithm. The color texture is computed in nine 3?3 masks obtained from each 3?3?3 spatio-spectral neighborhood in the image using the classical Haralick and pressman texture features. Among these 9?28 texture features the best set was extracted from a training set. The resulting set of 10 features were used to segment an image into four different regions. The resulting segmentation was compared to classical color and texture segmentation methods using both box classifiers and maximum likelihood classification. It compared favourably on the test image from a Fastred-Lightgreen stained prostatic histological tissue section based on visual inspection. The classification accuracy of 97.5% for the new method obtained on the training data was also among the best of the tested methods. If these results hold for a larger set of images, this method should be a useful tool for segmenting images where both color and texture are relevant for the segmentation process.
Enhancement of Histogram Equalization with Neighborhood Metrics
Nayamlhagva Sengee,Choi Heung Kook(최흥국) 한국멀티미디어학회 2007 한국멀티미디어학회 학술발표논문집 Vol.2007 No.1
We present a refinement of histogram equalization using neighborhood metrics with general framework which orders pixels based on a sequence of sorting functions which uses both global and local information to remap the image graylevels. We designed a novel sorting key with the suggestion of using the original image greylevel as the primary key and a neighborhood voting metric as the secondary key and the novel contrast difference metrics as the third key. We find that our method can provide an improvement in contrast enhancement versus global Histogram Equalization (HE) and Histogram equalization with neighborhood metrics (HENM), while avoiding undesirable over-enhancement that can occur with local histogram equalization (LHE) and other methods.
Cyber-Lecture Management System based on XML
김혜영,김화선,김흥식,김상균,최흥국,Kim, Hye-Young,Kim, Hwa-Sun,Kim, Heung-Sik,Kim, Sang-Gyun,Choi, Heung-Kook Korea Information Processing Society 2003 정보처리학회논문지 A Vol.10 No.5
웹의 빠른 발전은 인터넷 기반의 원격 교육 도구들을 급속히 성장시키고 있다. 웹에서는 상호간의 정보를 서로 교환하고 표현할 때 사용자의 브라우저에서 볼 수 있는 HTML(Hyper Text Markup Language)로 제작된다. 하지만, HTML 의 구조적 단점은 모든 분야의 데이터를 저장 하고 다른 형태의 데이터로 변화될 수 있는 강한 힘을 지닌 XML(eXtensible Markup Language)을 필요로 하게 되었다. 그러나 강력한 XML 자체만으로 장점을 활용하여 어렵기 때문에 관련 XML 표준의 적절한 응용이 필요하다. 현재 사이버 교육 사이트들의 강좌 데이터는 서로 공유될 수 없으므로 사용자들은 사이버스쿨이 제공하는 기능만을 수동적으로 사용하기만 해야 한다. 이 한계를 해결할 수 있는 방법으로서, 본 연구에서는 사이버 강좌관리 시스템을 위해 통일된 XML데이터 구조를 정의하고 서버와 클라이언트의 처리되는 모델을 제시하였다. 웹에서의 가상 교육에 대한 데이터를 XML 로 저장함으로서 한번 저장된 데이터를 어떤 사이트에서든 조금의 수정없이 재 사용할 수 있게 되었다. 사용자적인 측면에서, 교수자와 학습자를 두어 어떤 종류의 사이버강좌라도 쉽게 관리할 수 있고 다양한 멀티미디어 자료와 쉬운 사용자 인터페이스를 제공하여 많은 학습자료들을 두어 어떤 종류의 사이버강좌라도 쉽게 관리할 수 있고 다양한 멀티미디어 자료와 쉬운 사용자 인터페이스를 제통해 XML 형태로 저장하고 추출하므로써 가능하게 되었고 정보활용에 극대화를 가져올 것이다. The speedy development of the world-wide web is rapidly growing the internet-based tools for the remote instruction. In interchanging and expressing the information of one another on the web, it is produced through the form of HTML(Hyoertext Text Markup Language). However, the structural disadvantage of the HTML is becoming to require a powerful XML(eXtensible Markup Language) which can store all the sphere of data, and transform them into another form. Nevertheless, because the powerful XML(eXtensible Markup Language). However necessary that XML standard should be applied appropriately. Because existing lecture data of cyber education sites cannot be shared, the users should passively use only the functions offered by cyber school. To solve the problem of this limit, in this study, the standardized data structure for XML is defined, and system model for processing between the server and the client is provided. By storing the lecture data of cyber education sites as XML on the web, stored data came to be reused without changing on any site. In the view of Users, they could used the Internet service with equipment that they want at any place and any time. To control any kinds of CK\LMS(Cyber Lecture Management System) for Administrator and Users, we offered a variety of Multimedia applications and an easy interface and built a new style of CLMS. Therefore, by strong and extracting the data related with the virtual education of the secondary school through the form of XML, for the effective interchange and sharing of the information, maximum utilization of the information can be achieved.