• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.171-178
• /
• 2008

Foreign word transliterations are not consistently used in documents, which hinders retrieving some important relevant documents in exact term matching information retrieval systems. In this paper, a meta search method is proposed, which expands and refines relevant variant queries from an original input foreign word transliteration query to retrieve the more relevant documents. The method firstly expands a transliteration query to the variants using a statistical method. Secondly the method selects the valid variants: it queries each variant to the retrieval systems beforehand and checks the validity of each variant by counting the number of appearance of the variant in the retrieved document and calculating the similarity of the context of the variant. Experiment result showed that querying with the variants produced at the first step, which is a base method of the test, performed 38% in average F measure, and querying with the refined variants at the second step, which is a proposed method, significantly improved the performance to 81% in average F measure.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.1
• /
• pp.9-14
• /
• 2002

Boolean retrieval is simple and elegant. However, since there is no provision for term weighting, no ranking of the answer set is generated. As a result, the size of the output might be too large or too small. Relevance feedback is the most popular query reformulation strategy. in a relevance feedback cycle, the user is presented with a list of the retrieved documents and, after examining them, marks those which are relevant. In practice, only the top 10(or 20) ranked documents need to be examined. The main idea consists of selecting important terms, or expressions, attached to the documents that have been identified as relevant by the user, and of enhancing the importance of these terms in a new query formulation. The expected effect is that the new query will be moved towards the relevant documents and away from the non-relevant ones. Local analysis techniques are interesting because they take advantage of the local context provided with the query. In this regard, they seem more appropriate than global analysis techniques. In a local strategy, the documents retrieved for a given query q are examined at query time to determine terms for query expansion. This is similar to a relevance feedback cycle but might be done without assistance from the user.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.1
• /
• pp.249-268
• /
• 2014

Relevance feedback is an effective tool to bridge the gap between superficial image contents and medically-relevant sense in content-based medical image retrieval. In this paper, we propose an interactive medical image search framework based on pairwise constraint propagation. The basic idea is to obtain pairwise constraints from user feedback and propagate them to the entire image set to reconstruct the similarity matrix, and then rank medical images on this new manifold. In contrast to most of the algorithms that only concern manifold structure, the proposed method integrates pairwise constraint information in a feedback procedure and resolves the small sample size and the asymmetrical training typically in relevance feedback. We also introduce a long-term feedback strategy for our retrieval tasks. Experiments on two medical image datasets indicate the proposed approach can significantly improve the performance of medical image retrieval. The experiments also indicate that the proposed approach outperforms previous relevance feedback models.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.8B
• /
• pp.1413-1423
• /
• 2000

Color distribution is changed according to the variation of illumination position and illumination color. Therefore, even if images are relevant each other, retrieval accuracy is degraded. In this paper, we propose the image retrieval method using color information excluded illumination component. The proposed dynamic range control method removes the shadow region generated by change of illumination position to increase the color discrimination power. To exclude the illuminant color, we use the diffuse reflection component of object and gray world assumption. The experimental results show that the color histogram method using color information excluded illuminant has higher retrieval accuracy than conventional color histogram using the color information of input image.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.8
• /
• pp.1782-1789
• /
• 1997

Most systems that retrieve distributed information on the Internet have difficulties in retrieving relevant information for they are not able to reflect exact semantics on retrieval queries that usersrequest. In this paepr, we propose an automatic query expansion based on ter distribution which reflects semantics of retrieval term to emhance the performance of information retrieval. We computed weight, indicating its overal imoritance in the collection documents and user's query and we use LSI's SVD technique to measure the term distribution which appears similar to query. And also, we measure the similarity to compared numerical value with query terms. Also we researched the method to reduce additional terms automatically and evaluated the performance of the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.1
• /
• pp.15-19
• /
• 2012

A Domain Dictionary generation algorithm based on pseudo feedback model is presented in this paper. This algorithm can increase the precision of domain dictionary generation algorithm. The generation of Domain Dictionary is regarded as a domain term retrieval process: Assume that top N strings in the original retrieval result set are relevant to C, append these strings into the dictionary, retrieval again. Iterate the process until a predefined number of domain terms have been generated. Experiments upon corpus show that the precision of pseudo feedback model based algorithm is much higher than existing algorithms.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.1 s.45
• /
• pp.43-50
• /
• 2007

Delay in the process of Information Extraction, IE, is largely due to inability to correctly recognize the user's information requirement of particular search factors. Especially if the wrapper rules are used in a search engine, the search generally fails to classify internet documents properly and efficiently since the application of the same wrapper rules lacks extensibility throughout various types of existing internet document. In case of buying or selling a ship, if the price range, type. place of delivery, inspection site and other information relevant to the sales would be available through the internet for proper retrieval the sales could more readily succeed by using Ontology relating to sales or purchase information and by selectively searching for the desired information through the content based retrieval system. This system proposes to improve various wrapper systems existing throughout different internet sites and to eliminate unnecessary information tagged on the existing internet documents in order to create a more advanced information retrieval system.

• Journal of KIISE:Software and Applications
• /
• v.27 no.2
• /
• pp.168-179
• /
• 2000

In reusable component retrieval systems with facet-based schemes, facet queries are generally used for representing the characteristics of components relevant to users. This paper proposes an expanded facet query equipped with an object-based thesaurus to precisely formulate user's intents. To evaluate the query, a component retrieval system is also designed and implemented. For exactly retrieving the components, user's query should include relevant facet values capable of fully specifying their characteristics. However, simply listing a series of facet values directly inputted by users, conventional queries fails to precisely represent user's intents. Our query, called expanded facet query, employs fuzzy boolean operators and object-based thesaurus; the former logically expresses the fuzzy connectives between facet queries and required components, whereas the latter helps users appropriately select the specific facet values into the query. A thesaurus query is provided to recommend the relevant facet values with their fuzzy degrees from the thesaurus as well. Furthermore, our retrieval system can automatically formulate queries with the recommended facet values, if necessary.

• The KIPS Transactions:PartB
• /
• v.10B no.1
• /
• pp.57-66
• /
• 2003

We propose a technique to extract a relevant passage from text collection based on field-associated terms since they tries to concentrate relevant text to users query. Documents are supposed to be managed as a whole without any segmentation into small pieces, but the method presented is independent upon any text-embedded auxiliary information, and is based on topic continuity and transition. For users needs-relative sentences or passages, we present a passage retrieval techniques by using occurrence frequency of a field-associated term to delimit text, that is likely to be relevant to a particular topic, considering continuity and transition within topic flowing in text. We evaluate 50 Japanese documents and verify the usefulness with 82% for average precision and 63% for recall.

• Proceedings of the IEEK Conference
• /
• 1999.11a
• /
• pp.487-490
• /
• 1999

In this paper we propose an efficient content-based image retrieval method using the color and wavelet based features. The color features are extracted from color histograms of the global image and the wavelet based features are extracted from the invariant moments of the high-pass band image through the spatial-frequency analysis of the wavelet transform. The proposed algorithm, called color and wavelet features based query(CWBQ), is composed of two-step query operations for efficient image retrieval: the coarse level filtering operation and the fine level matching operation. In the first filtering operation, the color histogram feature is used to filter out the dissimilar images quickly from a large image database. The second matching operation applies the wavelet based feature to the retained set of images to retrieve all relevant images successfully. The experimental results show that the proposed algorithm yields more improved retrieval accuracy with computationally efficiency than the previous methods.