• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.1330-1336
• /
• 2012

The Image retrieval has been study different approaches which are text-based, contents-based, area-based method and sub-image finding. The sub-image retrieval is to find a query image in the target one. In this paper, we propose a novel sub-image retrieval algorithm by Dot-Matrix method to be used in the bioinformatics. Dot-Matrix is a method to evaluate similarity between two sequences and we redefine the problem for retrieval of sub-image to the finding similarity of two images. For the approach, the 2 dimensional array of image converts a the vector which has gray-scale value. The 2 converted images align by dot-matrix and the result shows candidate sub-images. We used 10 images as target and 5 queries: duplicated, small scaled, and large scaled images included x-axes and y-axes scaled one for experiment.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.113-118
• /
• 2002

This paper presents a cluster-based image retrieval method. It retrieves images from a related cluster after classifying images into clusters using RAGMD, a clustering technique. When images are retrieved, first they are retrieved not from the whole image database one by one but from the similar cluster, a similar small image group with a query image. So it gives us retrieval-time reduction, keeping almost the same precision with the exhaustive retrieval. In the experiment using an image database consisting of about 2,400 real images, it shows that the proposed method is about 18 times faster than 7he exhaustive method with almost same precision and it can retrieve more similar images which belong to the same class with a query image.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.92-103
• /
• 2010

In this paper, a method for the recognition of dynamic hand gestures in various backgrounds using Dynamic Space Time Warping(DSTW) algorithm is proposed. The existing method using DSTW algorithm compares multiple candidate hand regions detected from every frame of the query sequence with the model sequences in terms of the time. However the existing method can not exactly recognize the models because a false path can be generated from the candidates including not-hand regions such as background, elbow, and so on. In order to solve this problem, in this paper, we use the invariant moments extracted from the candidate regions of hand and compare the similarity of invariant moments among candidate regions. The similarity is utilized as a weight and the corresponding value is applied to the matching cost between the model sequence and the query sequence. Experimental results have shown that the proposed method can recognize the dynamic hand gestures in the various backgrounds. Moreover, the recognition rate has been improved by 13%, compared with the existing method.

• The KIPS Transactions:PartD
• /
• v.13D no.3 s.106
• /
• pp.347-356
• /
• 2006

A video stream can be represented by a sequence of data points in a multidimensional space. In this paper, we introduce a trend vector that approximates values of data points in a sequence and represents the moving trend of points in the sequence, and present a pattern similarity matching method for data sequences using the trend vector. A sequence is partitioned into multiple segments, each of which is represented by a trend vector. The query processing is based on the comparison of these vectors instead of scanning data elements of entire sequences. Using the trend vector, our method is designed to filter out irrelevant sequences from a database and to find similar sequences with respect to a query. We have performed an extensive experiment on synthetic sequences as well as video streams. Experimental results show that the precision of our method is up to 2.1 times higher and the processing time is up to 45% reduced, compared with an existing method.

• Journal of Digital Contents Society
• /
• v.10 no.2
• /
• pp.239-247
• /
• 2009

In simple topology in network system, query should be delivered to all linked peers for query processing. This causes waste of transmission band width and throughput of each peer. To overcome this, as well as query processing strategy, efficient routing technique to deliver query to proper peer is needed. For efficient routing, clustering of peers in P2P networks is important. Clustering of P2P network bases on that combines peers that have similar characteristics in same cluster reduces quantity of message in network than assign peer for cluster randomly. In this paper, we propose clustering techniques for ontology based P2P query processing. Similarity measure point, cluster index structure, and query processing steps in ontology based P2P cluster environment are proposed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1517-1524
• /
• 2011

In this paper, a new document summarization method, which uses the semantic features and the pseudo relevance feedback (PRF) by using WordNet, is introduced to extract meaningful sentences relevant to a user query. The proposed method can improve the quality of document summaries because the inherent semantic of the documents are well reflected by the semantic feature from NMF. In addition, it uses the PRF by the semantic features and WordNet to reduce the semantic gap between the high level user's requirement and the low level vector representation. The experimental results demonstrate that the proposed method achieves better performance that the other methods.

• Proceedings of the KAIS Fall Conference
• /
• 2010.05a
• /
• pp.299-301
• /
• 2010

본 논문에서는 사용자의 키워드 학습과 비교 영역 학습을 이용하여 대용량의 비디오 데이터에 대한 사용자의 다양한 의미검색을 지원하는 에이전트 기반에서의 자동화된 비디오 검색 시스템을 제안한다. 사용자의 기본적인 질의와 질의에 의해 추출된 키 프레임의 이미지를 선택함으로써 에이전트는 추출된 키 프레임의 주석에 대한 의미를 더욱 구체화시킨다. 또한, 사용자에 의해 선택된 키 프레임은 질의 이미지가 되어 색상 히스토그램 비교기법과 제안하는 비교 영역 학습 기법을 통해 가장 유사한 키 프레임을 검색한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.10b
• /
• pp.7-9
• /
• 2004

센서 네트워크의 급속한 성장에 따라 센서 네트워크의 효율적 관리를 위한 다양한 연구가 진행 중이다. 특히, 센서의 저 전력을 위한 다양한 기술들이 개발되고 있다. 본 논문은 센서에 전해지는 다중 연속 질의의 중복 성을 제거함으로써, 센서 네트워크의 효율적 관리를 제공할 수 있는 방법을 제안한다. 다중 연속 질의는 두 가지 단계로 최적화가 이루어진다. 먼저, 다중 연속 질의의 시간 속성 중복을 제거하기 위해 B+tree를 이용해 그룹 핑된다. 그룹 핑된 다중 연속 질의들은 연관 속성의 중복 여부 판단을 통해, 중복 성을 제거하여 재구성 된다. 그러므로 재구성된 다중 연속 질의가 센서 노드에 전해지게 되면, 센서는 중복된 결과를 전송하지 않기 때문에 센서 노드의 불필요한 전력을 낭비하지 않게 된다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10b
• /
• pp.191-193
• /
• 1998

지금까지 제시된 최근접 질의 알고리즘은다소간의 cklms 있으나 기본적으로 질의 점과 MBR간의 최소거리에 기반한 분기와 한정 기법을 이용하고 있다. 그러나 차원이 증가함에 따라 질의 구와 겹치는 노드가 급속히 증가하기 때문에 최근접 질의 알고리즘의 성능은 매우 비효율적이다. 이러한 문제를 해결하기 위해서 MBR 간의 중첩을 줄이고 MBR 내에 가급적 많은 점을 포함할 수 있는 다양한 다차원 색인 구조가 제시도 되었다. 그러나 우리의 실험에 의하면 이러한 방법이 근본적인 해결책이 되지 못함을 알 수 있다. 고차원 백터 공간 모델이 가지는 문제로써 임의의 질의 점으로부터 모든 데이터 점들까지의 거리가 차원이 올라감에 따라 유사해지는 현상 때문에 비효율적인 성능이 나옴을 본 논문에서 지적한다.

• Journal of Internet Computing and Services
• /
• v.6 no.2
• /
• pp.99-115
• /
• 2005

Extensible Markup Language (XML) is an Internet standard that is used to express and convert data, In order to find the necessary information out of XML documents, you need a search system for XML documents, In this research, we have developed a search system that can find documents that matches the structure and content of a given XML document, making the best use of XML structure, Search metrics take account of the similarity in tag names, tag values, and the structure of tags, After a search, the system displays the ranked results in the order of aggregate similarity, Three methods of query are provided: keyword search which is conventional; search with tag names and their values; and search with XML documents, These three methods enable users to choose the method that best suits their preference, resulting in the increase of the usefulness of the system.