• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.681-686
• /
• 2003

In recent years automatic image indexing and retrieval have been increasingly studied. However, content-based retrieval techniques for general images are still inadequate for many purposes. The novelty and originality of this thesis are the definition and use of a spatial information model as a contribution to the accuracy and efficiency of image search. In addition, the model is applied to represent color and shape image contents as a vector using the method of image features extraction, which was inspired by the previous work on the study of human visual perception. The indexing scheme using the color, shape and spatial model shows the potential of being applied with the well-developed algorithms of features extraction and image search, like ranking operations. To conclude, user can retrieved more similar images with high precision and fast speed using the proposed system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.5
• /
• pp.458-466
• /
• 2001

This paper is addressed to a design and implementation of Korean voice web browser using voice technologies for controling web browser and selecting contents in the web document, and converting them to voice after HTML analysis. Main feature of this web browser is universal design which considers both of normal person and visual disabled, allows multi-modal interface. As voice interface for visual disabled, it supports tree structure which allows to recognize web document structure easily by only voice guidance regardless of frame usage, can handle all elements described as tag in the web document, identify them as predefined different voice property according to element property. This method gets rid of additional guidance voice for element property without audio style sheet or additional programming effort.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.1015-1019
• /
• 2009

With the rapid development of game industry, game has become an important leisure style in people's life. The character is the spirit of a game, and a good character design can make game more attractive. Nowadays, most characters design only can grasp the general image of the character well without depicting or outlining the detail characteristic and features. Because these characters are designed only by designers' own wills. This paper will choose Three Kingdoms as an example, and analyze the status, social positions and characteristics of the character comprehensively by researching on physiognomy. This study will be a good reference for the designers.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.519-522
• /
• 2002

일반적으로 PubMed와 같은 인터넷을 이용한 대규모 의료 문헌정보 검색시스템에서 포괄적인 주제어나 간결한 주제어를 이용한 검색을 시도할 경우, 종종 매우 다양한 세부주제의 문헌리스트들이 다량으로 검색된다. 이러한 경우 이용자는 실제로 본인이 원했던 세부주제에 부합되는 문헌들을 찾기 위해서는 검색결과로 주어진 긴 문헌리스트상의 문헌 하나하나에 대해 다시 문헌제목이나 혹은 요약 등의 내용을 직접 읽어보고 내용을 확인하여야 한다. 이러한 작업은 매우 번거럽고 시간과 노력을 많이 필요로 한다. 따라서 본 논문에서는 이러한 노력을 줄이기 위한 한 가지 방안으로, PubMed 시스템의 주제어 검색결과로 주어진 문헌들에 대해 내용의 유사성과 차별성에 따라 자동으로 몇 개의 그룹으로 나누어주는 군집화시스템 MedCluster의 설계와 구현에 대해 소개한다. MedCluster의 큰 특징은 기존의 문서 군집화 방법과는 다른 신경망 GHSOM을 이용한 군집화 방법을 사용하는 점이다. GHSOM은 미리 문서 그룹의 개수를 정해줄 필요가 없고 다양한 레벨의 문서 그룹들을 얻을 수 있는 계층적 군집화를 이루어낸다는 장점을 가지고 있다. 본 논문에서는 신경망 GHSOM의 구조와 특성에 대해 간략히 살펴보고, GHSOM을 채용한 의료문헌 군집화시스템 MedCluster의 설계와 구현에 대해 설명한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.07a
• /
• pp.13-16
• /
• 2015

본 논문에서는 어휘의 동시 발생 (co-occurrence) 빈도와 분포를 이용한 회의록 요약방법을 제안한다. 회의록은 일반 문서와 달리 문서에 여러 세부적인 주제들이 나타나며, 잘못된 형식의 문장, 불필요한 잡담들을 포함하고 있기 때문에 이러한 특징들이 문서요약 과정에서 고려되어야 한다. 기존의 일반적인 문서요약 방법은 하나의 주제를 기반으로 문서 전체에서 가장 중요한 문장으로 요약하기 때문에 다중 주제 회의록 요약에는 적합하지 않다. 제안한 방법은 먼저 어휘의 동시 발생 (co-occurrence) 빈도를 이용하여 회의록 분할 (segmentation) 과정을 수행한다. 다음으로 주제의 구분에 따라 분할된 각 영역 (block)의 중요 단어 집합 생성, 중요 문장 추출 과정을 통해 회의록의 중요 문장들을 선별한다. 마지막으로 추출된 중요 문장들의 위치, 종속 관계를 고려하여 최종적으로 회의록을 요약한다. AMI meeting corpus를 대상으로 실험한 결과, 제안한 방법이 baseline 요약 방법들보다 요약 비율에 따른 평가 및 요약문의 세부 주제별 평가에서 우수한 요약 성능을 보임을 확인하였다.

• KNOM Review
• /
• v.22 no.3
• /
• pp.13-19
• /
• 2019

Network anomaly detection is a technology that collects information about flows on a network and detects malicious attacks occurring in a network in real time. In-band Network Telemetry (INT) technology provides more detailed information in real time, that is not provided by existing networks, such as hop latency and queue occupancy. In this paper, we propose the method to implement an anomaly detection system with higher performance by using INT as an input feature of machine learning and verify it through experiments.

• Journal of Digital Convergence
• /
• v.19 no.5
• /
• pp.307-313
• /
• 2021

In this paper, a lightweight network with fewer parameters compared to the existing object detection method is proposed. In the case of the currently used detection model, the network complexity has been greatly increased to improve accuracy. Therefore, the proposed network uses EfficientNet as a feature extraction network, and the subsequent layers are formed in a pyramid structure to utilize low-level detailed features and high-level semantic features. An attention process was applied between pyramid structures to suppress unnecessary noise for prediction. All computational processes of the network are replaced by depth-wise and point-wise convolutions to minimize the amount of computation. The proposed network was trained and evaluated using the PASCAL VOC dataset. The features fused through the experiment showed robust properties for various objects through a refinement process. Compared with the CNN-based detection model, detection accuracy is improved with a small amount of computation. It is considered necessary to adjust the anchor ratio according to the size of the object as a future study.

• Korean Journal of Heritage: History & Science
• /
• v.47 no.1
• /
• pp.46-65
• /
• 2014

This study, under the title of Daeungbojeon Hall of Bulyeongsa Temple, Uljin and the architectural technique of the architect, aimed to make a comprehensive speculation on Daeungbojeon Hall of Bulyeongsa Temple whose accurate construction year was confirmed in 1725. While existing studies dealt with it separately between construction and Buddhist art history this study attempted to sort out it in one perspective by means of comparison with compatible objects in the area. The results are as follows. 1st, by means of comparison of wall painting of Daeungbojeon Hall of Bulyeongsa Temple and other wall paintings of Gyeongsang-do Province, it was estimated to be created before and after 1725, the founding year of the building. 2nd, the stylobate of Daeungbojeon Hall is the only and unique case that Guibu was supported by the bottom. Such stylobate was estimated to be built in the early period of Goryeo stylobate of PostLintel Construction which was more simplified than that of the traditional unified Silla period considering specific techniques. Lastly, by means of comparison of the architectural technique of Daeungbojeon Hall of Bulyeongsa Temple with other temples in Gyeongsang-do Province, the characteristics of the building were found. In particular, the same architectural technique was confirmed by direct comparison of style with Yeongsanjeon Hall of Tongdosa Temple in 1714 which was constructed by the same architect.

• Journal of KIISE:Software and Applications
• /
• v.35 no.12
• /
• pp.789-799
• /
• 2008

For the communication between human and computer in an interactive computing environment, the gesture recognition has been studied vigorously. The algorithms which use the 2D features for the feature extraction and the feature comparison are faster, but there are some environmental limitations for the accurate recognition. The algorithms which use the 2.5D features provide higher accuracy than 2D features, but these are influenced by rotation of objects. And the algorithms which use the 3D features are slow for the recognition, because these algorithms need the 3d object reconstruction as the preprocessing for the feature extraction. In this paper, we propose a method to extract the 3D features combined with the 3D object reconstruction in real-time. This method generates three kinds of 3D projection maps using the modified GPU-based visual hull generation algorithm. This process only executes data generation parts only for the gesture recognition and calculates the Hu-moment which is corresponding to each projection map. In the section of experimental results, we compare the computational time of the proposed method with the previous methods. And the result shows that the proposed method can apply to real time gesture recognition environment.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.990-999
• /
• 2007

In this paper, we propose the region-based image retrieval method using JSEG which is a method for unsupervised segmentation of color-texture regions. JSEG is an algorithm that discretizes an image by color classification, makes the J-image by applying a region to window mask, and then segments the image by using a region growing and merging. The segmented image from JSEG is given to a user as the query image, and a user can select a few segmented regions as the query region. After finding the MBR of regions selected by user query and generating the multiple window masks based on the center point of MBR, we extract the feature vectors from selected regions. We use the accumulated histogram as the global descriptor for performance comparison of extracted feature vectors in each method. Our approach fast and accurately supplies the relevant images for the given query, as the feature vectors extracted from specific regions and global regions are simultaneously applied to image retrieval. Experimental evidence suggests that our algorithm outperforms the recent image-based methods for image indexing and retrieval.