• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.7
• /
• pp.1585-1600
• /
• 2009

The goal of Semantic Web is to provide efficient and effective semantic search and web services based on the machine-processable semantic information of web resources. Therefore, the process of creating and adding computer-understandable metadata for a variety of web contents, namely, semantic annotation is one of the fundamental technologies for the semantic web. Recently, in order to manage annotation metadata, direct approach for embedding metadata into the document is mainly used in semantic annotation. However, many semantic annotation tools for web documents have been mainly worked with HTML documents, and most of these tools do not support semantic search functionalities using the metadata. In this paper, based on these problems and previous works, we propose the Ontology-based Semantic Annotation tool(OSA) to efficiently support semantic annotation for web documents(such as HTML, PDF). We define a semantic annotation model that represents ontological-semantic information by using RDFS(RDF Schema). Based on XMP(eXtensible Metadata Platform) standard, the model is encoded directly into the document. By using OSA with XMP, user can perform semantic annotation on web documents which are able to keep compatibility for managing annotation metadata. Eventually, the integrated semantic annotation metadata can be used effectively in semantic search for a variety of web contents.

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.269-282
• /
• 2023

The purpose of this study was to construct land cover maps using a deep learning model and to select the optimal deep learning model for land cover classification by adjusting the dataset such as input image size and Stride application. Two types of deep learning models, the U-net model and the DeeplabV3+ model with an Encoder-Decoder network, were utilized. Also, the combination of the two deep learning models, which is an Ensemble model, was used in this study. The dataset utilized RapidEye satellite images as input images and the label images used Raster images based on the six categories of the land use of Intergovernmental Panel on Climate Change as true value. This study focused on the problem of the quality improvement of the dataset to enhance the accuracy of deep learning model and constructed twelve land cover maps using the combination of three deep learning models (U-net, DeeplabV3+, and Ensemble), two input image sizes (64 × 64 pixel and 256 × 256 pixel), and two Stride application rates (50% and 100%). The evaluation of the accuracy of the label images and the deep learning-based land cover maps showed that the U-net and DeeplabV3+ models had high accuracy, with overall accuracy values of approximately 87.9% and 89.8%, and kappa coefficients of over 72%. In addition, applying the Ensemble and Stride to the deep learning models resulted in a maximum increase of approximately 3% in accuracy and an improvement in the issue of boundary inconsistency, which is a problem associated with Semantic Segmentation based deep learning models.

• Journal of Broadcast Engineering
• /
• v.26 no.3
• /
• pp.296-307
• /
• 2021

A digital hologram (DH) is an ultra-high value-added video content that includes 3D information in 2D data. Therefore, its intellectual property rights must be protected for its distribution. For this, this paper proposes a watermarking method of DH using a deep neural network. This method is a watermark (WM) invisibility, attack robustness, and blind watermarking method that does not use host information in WM extraction. The proposed network consists of four sub-networks: pre-processing for each of the host and WM, WM embedding watermark, and WM extracting watermark. This network expand the WM data to the host instead of shrinking host data to WM and concatenate it to the host to insert the WM by considering the characteristics of a DH having a strong high frequency component. In addition, in the training of this network, the difference in performance according to the data distribution property of DH is identified, and a method of selecting a training data set with the best performance in all types of DH is presented. The proposed method is tested for various types and strengths of attacks to show its performance. It also shows that this method has high practicality as it operates independently of the resolution of the host DH and WM data.

• Journal of IKEEE
• /
• v.7 no.1 s.12
• /
• pp.119-126
• /
• 2003

This paper presents a methodology for constructing a surgical simulation environment for the replacement of artificial knee join using CT image data. We provide a user interface of preoperative planning system for performing complex 3-D spatial manipulation and reasoning tasks. Simple manipulation of joystick and mouse has been proved to be both intuitive and accurate for the fitness and the wear expect of joint. The proposed methodology are useful for future virtual medical system where all the components of visualization, automated model generation, and surgical simulation are integrated.

• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.393-396
• /
• 2004

본 논문에서는 선박의 소음을 이용한 선박의 위치추적 및 지음향학적 인자의 역산 기법을 제안하였다. 예인 수평선배열에 의해 계측된 선박의 소음을 시간역전시켜(time reversed) 역전파(back propagation)시킨 음파는 해당 해양환경과 동일한 경우 원래의 음원 즉 선박의 위치에 가장 큰 에너지가 집중된다. 이러한 역전파된 신호의 집중 정도를 이용하여 음원의 위치 및 해양환경(특히 지음향학적 환경) 정보를 추정하였다. 본 역산에서 사용된 목적함수는 정합임펄스응답필터를 사용하여 음원의 위치에 집중된 정규화된 파워로 정의되었다. 최적화 알고리즘으로 유전알고리즘과 Powell 방법이 함께 사용되었다. 제안된 기법을 Elba섬 근해에서 실시된 MAPEX 2000 실험 데이터에 적용한 후 그 결과를 본 논문에서 제시하였으며 그 효용성을 확인하였다.

• The Journal of the Korea Contents Association
• /
• v.3 no.3
• /
• pp.47-54
• /
• 2003

In this paper, we implemented embedded LNUX-based UI(User Interface) board which can be applied to Human Iris recognition product. for this purpose, we also analyzed and designed LNUX operating system and adapted boot loader, kernel, control program modules according to the developed H/W architectures. As the experimental results shows that Iris recognition system is operable and embedded LNUX-based UI board which is connected to heterogeneous system by TCP/IP protocol can both successfully send and receive data this UI board has been able to obtain high performance.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10a
• /
• pp.695-698
• /
• 2000

본 논문에서는 이미지 데이터 컬러 속성을 기반으로 한 영상 검색 방법을 제안한다. 두 이미지 사이의 유사성을 측정하기 위하여 컬러 히스토그램의 분포 특성을 이미지 데이터베이스 영상과질의 영상에서 계산하여 유사도를 결정하도록 설계하였다. 두 영상의 유사도를 측정하기 위해 두영상의 R, G, B 히스토그램에 대해서 같은 값에 대한 빈도 수의 차를 거리로 측정한 후, 구해진 거리의 차를 비교한 방법과 히스토그램의 분포 곡선을 이루는 방정식을 구한 수 있도록 곡선 정합을 한 후에 두 영상의 컬러 특징 속성에 관한 특징 값의 추출을 위해서 다항식 보간법에 의한 방정식을 이용한 방법을 소개한다. 공간 데이터베이스 시스템에서 질의에 대한 효율적인 처리를 위해 R-Tree와 최대 점을 이용하여 영상을 검색한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.07a
• /
• pp.105-106
• /
• 2012

일반적으로 CG 합성이라 하면 '자연스러운' 것을 잘된 CG영상이라고 한다. 이 때 촬영된 영상이 정지화면 일 수 만은 없다. 카메라가 움직이는 영상에서는 CG합성도 실사카메라 무빙에 맞게 정확한 정합이 되어야 자연스러운 영상이 된다. 이를 위해 합성단계에서 작업할 때 3D 카메라 트래킹 기술이 필요하다. 카메라트래킹은 촬영된 실사영상만으로 카메라의 3차원 이동정보와 광학적 파라미터 등 촬영시의 3차원 공간을 복원하는 과정을 포함하고 있다. 이 과정에서 카메라 트래킹에 대한 오류의 발생으로 실사와 CG의 합성에 대한 생산성에 많은 문제점을 가지고 있다. 본 논문에서는 이러한 문제를 해결하기 위하여 소프트웨어에서 트래킹데이터를 보정하는 방법을 제안한다.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.298-303
• /
• 2008

User adaptive services have been important features in many applications. To provide such services, various techniques with various kinds of data are being used. In this paper, we propose a method to analyze user's past moving paths for predicting the goal position and the path to the goal by observing the user's current moving path. We develop a spatio-temporal similarity measure between paths. We choose a past path which is the most similar to the current path using the similarity. Based on the chosen path, user's spatio-temporal position is estimated. Through experiments we confirm this method is useful and effective.

• The Journal of the Korea Contents Association
• /
• v.17 no.4
• /
• pp.478-487
• /
• 2017

In recent years, developed countries have begun to pay attention to female workers through work-family balance in order to solve the problem of low fertility and aging. Korea has been building and running a women leaders database (hereafter, women leaders DB) centered on the female professionals since 2011. In particular, the Incheon women leader DB, which was built by Incheon city in 2009, is a classic example. As of 2015, about 2,735 people are registered in Incheon Women Leaders DB and it is systematically creating the database such as age, education, career years, major, occupation, and certification. However, there are administrative problems such as unspecified definition on professionalism and data trust issues including data entry, and DB personnels are concentrated in specific fields. Also, in the case of certification proving expertise, the utilization problem has been revealed including inclusion of private certification not yet verified. In order to solve these problems, we first need to clarify the concept of women leaders and establish the standard. The second is the improvement of data consistency through DB reorganization, and third is to build a system through continuous and active public relations that is used by both job seekers and recruiters.