• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.11A
• /
• pp.1889-1896
• /
• 2001

This paper proposes the hierachically regularized motion estimation technique for the efficient and accurate motion estimation. To use hierachical technique increases the reliability of motion vectors. And the regularization of neighbor vectors decreases bit rate of motion vectors. Also, using fast motion estimation algorithm with a few candidate vectors, the processing time added by regularization can be decreased. In the result of the experiment, the fast motion estimation with hierachical regularization technique achieves less computations and decreases estimation and distribution of false vectors.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.810-813
• /
• 2004

Indexing and Retrieving images from large and varied collections using image content as a key is a challenging and important problem in computer vision application. In this paper, a color Content-based Image Retrieval (CBIR) system using hierarchical Region of Interest (ROI) query and indexing is presented. During indexing process, First, The ROIs on every image in the image database are extracted using a region-based image segmentation technique, The JSEG approach is selected to handle this problem in order to create color-texture regions. Then, Color features in form of histogram and correlogram are then extracted from each segmented regions. Finally, The features are stored in the database as the key to retrieve the relevant images. As in the retrieval system, users are allowed to select ROI directly over the sample or user's submission image and the query process then focuses on the content of the selected ROI in order to find those images containing similar regions from the database. The hierarchical region-of-interest query is performed to retrieve the similar images. Two-level search is exploited in this paper. In the first level, the most important regions, usually the large regions at the center of user's query, are used to retrieve images having similar regions using static search. This ensures that we can retrieve all the images having the most important regions. In the second level, all the remaining regions in user's query are used to search from all the retrieved images obtained from the first level. The experimental results using the indexing technique show good retrieval performance over a variety of image collections, also great reduction in the amount of searching time.

• Asia pacific journal of information systems
• /
• v.1 no.1
• /
• pp.87-101
• /
• 1991

The primary purpose of this study was to investigate a robust search methodology that could be used in full-text information retrieval systems. A robust search methodology is one that can be easily used by a variety of users (particularly naive users) and it will give them comparable search performance regardless of their different expertise or interests In order to develop a possibly robust search methodology, a fully functional prototype of a fuzzy knowledge based information retrieval system was developed. Also, an experiment that used this prototype information retreival system was designed to investigate the performance of that search methodology over a small exploratory sample of user queries To probe the relatonships between the possibly robust search performance and the query organization using fuzzy inference logic, the search performance of a shallow query structure was analyzes. Consequently the following several noteworthy findings were obtained: 1) the hierachical(tree type) query structure might be a better query organization than the linear type query structure 2) comparing with the complex tree query structure, the simple tree query structure that has at most three levels of query might provide better search performance 3) the fuzzy search methodology that employs a proper levels of cut-off value might provide more efficient search performance than the boolean search methodology. Even though findings could not be statistically verified because the experiments were done using a single replication, it is worth noting however, that the research findings provided valuable information for developing a possibly robust search methodology in full-text information retrieval.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.861-864
• /
• 2009

Recently, the biometric recognition technology of veins in different parts of hand is very active. In this paper the image hierarchical slicing provides a way to detect vein patterns. The scanned vein image will be sliced into various thicknesses. We first get the average brightness values of the sliced image and then convert them into curvature where we can detect candidates of the vein. The candidates of the vein are used to do a further analysis. We search all of the vein candidates and analyze them to get the real vein pattern in the overlapping extraction. We propose this novel algorithm to detect the vein pattern from the original image.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.7 no.1
• /
• pp.147-169
• /
• 1994

The study is to assist system developers or designers who are participated in the design of the user-computer interface on online services such as Online Public Access Catalogue and Online Search-ins. To design the optimal user interface, system developers and designers should try to complete the following process orderly: 1) they should know and understand the active and potential user's information seeking behaviors concerning online services in details as possible. 2) they should design the conceptional user model on basis of that knowledge. 3）They should design the logical and hierachical computer model adaptable to the current environment. 4) they should design the display of the computer terminal which is ease to learn and use by the users. 5) finally, they should design the optimal and practical user inter-face on basis of the above 2, 3, and 4.

• Journal of the Korean Society for information Management
• /
• v.6 no.2
• /
• pp.87-103
• /
• 1989

In this study, A DDC online system was developed which provides subject access and browsing function for class numbers or subject terms. A knowledgebase of the DDC Schedules and Relative Index was designed for this purpose using IBM-PC. From the DDC 20th edition, subjects from 004 to 006, covering‘data processing’,‘computer science’‘programming and progrms’, and etc., were selected for this experiment. DDC schedules are represented as a frame structure which is apt to describe hierachical structures. This experiment, joining the DDC to the information retrieval environment of an online catalog, will contribute to the future of the online DDC system by providing possiblities for search strategies not feasible through the alphabetical approach of subject headings and keywords presently supported by online catalogs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.04a
• /
• pp.94-99
• /
• 2000

컴퓨터의 보급과 함께 인터넷의 대중화로 많은 정보가 인터넷을 통해 제공되면서 많은 사람들이 정보통신 기반 서비스를 이용하게 되었다. 하지만 이런 서비스에 익숙하지 않은 사용자가 자신이 원하는 정보를 찾는 것은 그리 쉬운 일이 아니다. 그래서 ISP나 PC통신 업체들은 사용자들이 겪는 어려움을 해결해 주기 위한 서비스를 제공하고 있다. 그러나 사용자들의 엄청난 증가로 인해 이런 서비스를 유지하는데 많은 인력과 시간이 필요하게 되면서 질의 응답 자동화에 대한 필요성이 대두되었다. 본 논문에서는 ISP 업체 중 하나인 한메일넷의 자동 응답 시스템을 위한 FAQ 브라우징 시스템을 개발하였다. 기존의 많은 검색 서비스가 키워드들을 단순히 나열하고 이 키워드의 링크를 따라가면서 검색을 하게 하였으나 이 방식은 검색 대상에 대한 키워드 정보만을 제공하기 때문에, 문제에 대한 배경 지식이 적거나 검색 서비스 사용에 익숙치 않은 사용자가 이용하기에는 쉽지 않다. 본 시스템에서는 사용자에게 이차원상에 표현된 문서 지도를 제공해서 사용자가 쉽게 전체 검색 자료의 분포를 파악하고 검색하도록 하였다. 또한 단계별 검색이 가능하도록 해서 사용자가 효율적으로 검색할 수 있다.

• The KIPS Transactions:PartD
• /
• v.8D no.4
• /
• pp.361-366
• /
• 2001

As growing the number of Webs, the total amount of accessible information has been greater than ever. To storage and retrieve the vast information on the Webs effectively, many researchers have been made utilizing XML (extensible Markup Language). In this paper, we propose an effective method of representation and retrieval mechanism for the structured retrieval of the XML documents : (1) the fixed sized LETID (Leveled Element Type ID) that contains the information of elements such as parent node, sibling nodes, and identical sibling nodes, and the hierachical information of current node, and (2) content index, structure index, attribute index model, and the information retrieval algorithm for the structured information retrieval. With our methods, we can effectively represent the structured information of XML documents, and can directly access the specific elements by simple operations to process various queries.

• Proceedings of the KOSOMBE Conference
• /
• v.1995 no.05
• /
• pp.235-238
• /
• 1995

In this paper, we propose an effective coding method of the angiography by using the scalable structure in the frequency domain for MPACS(Medical Picture Archiving and Communication System). We employed the subband decomposition method and MPEG-2 system which is the international standard coding method of the general moving picture. After the subband decomposition is applied to split an input image into 4 bands in the spatial frequency domain, the motion compensated DPCM coding method of MPEG-2 is carried out for each subband. As a result, an easily controllable coding Structure is accomplished by composing the compound hit stream for each subband group. Follows are the simulation results of the proposed sheme for the angiography. A scalable structure which can be easily controlled for a loss of transmission or the band limit can be accomplisbed in the MPEG-2 stucture by the subband decomposition minimizing the side information. And by reducing the search area of the motion vector between -4 and 3, the processing speed of a codec is enhanced by more than two times without a loss of the picture quality compare with the conventional DCT coefficients decompositon method. And the processing speed is considerably improved in the case of the parallel construction of each subband in the hardware.