• Journal of the Korea Computer Industry Society
• /
• v.2 no.12
• /
• pp.1601-1608
• /
• 2001

Digital library is the most important database system that needs information retrieval engine for natural language documents and multimedia data. This paper describes the experimental results of information retrieval engine and browser based on natural language processing. It includes lexical analysis, syntax processing, stemming, and keyword indexing for the natural language text. With the experimental database ‘Earth and Space Science’ that has lots of images and titles and their descriptive text in natural language, text-based search engine was tested. Combined with content-based image search engine, it is expected to be a multimedia information retrieval system in digital library

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1999.04a
• /
• pp.516-518
• /
• 1999

• 한국ITS학회:학술대회논문집
• /
• 2005.11a
• /
• pp.62-66
• /
• 2005

• Journal of Korea Multimedia Society
• /
• v.8 no.7
• /
• pp.906-915
• /
• 2005

In this paper we propose content based image retrieval method using sequential clustering and projection information. Proposed method uses the mean of color in clustered color regions by sequential clustering and the projection information in each clustered color regions, which combines spatial information with color information in images efficiently. The experimental results showed that the proposed method retrieval efficiency improved 11.6 percent over conventional methods. In addition, the proposed method robustly tolerates large changes in appearance and shape caused by changes in viewing positions, camera zooms, etc.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.766-773
• /
• 2010

Support vector machine (SVM) active learning plays a key role in the interactive content-based image retrieval (CBIR) community. However, the regular SVM active learning is challenged by what we call "the small example problem" and "the asymmetric distribution problem." This paper attempts to integrate the merits of semi-supervised learning, ensemble learning, and active learning into the interactive CBIR. Concretely, unlabeled images are exploited to facilitate boosting by helping augment the diversity among base SVM classifiers, and then the learned ensemble model is used to identify the most informative images for active learning. In particular, a bias-weighting mechanism is developed to guide the ensemble model to pay more attention on positive images than negative images. Experiments on 5000 Corel images show that the proposed method yields better retrieval performance by an amount of 0.16 in mean average precision compared to regular SVM active learning, which is more effective than some existing improved variants of SVM active learning.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.51 no.7
• /
• pp.323-326
• /
• 2002

As multimedia database and digital image libraries are enlarged, CBIR(Content Based Image Retrieval) has been getting importance for the efficient search. Generally, CBIR uses primitive features such as color, shape, texture and so on. Among various methods of CBIR, Gabor wavelet has good image retrieval performance with texture features but it has a disadvantage which does not perform well for a rotated image because of its direction oriented filter. In this paper, we propose a new method to solve this problem by modifying Gabor filter for all directions. And then we will compare the searching performance of the proposed method with those of conventional image retrieval methods through experiments with trademarks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.993-1014
• /
• 2021

This paper proposes a new image retrieval method called the 3D integrated multi-index to fuse SIFT (Scale Invariant Feature Transform) visual words with other features at the indexing level. The advantage of the 3D integrated multi-index is that it can produce finer subdivisions in the search space. Compared with the inverted indices of medium-sized codebook, the proposed method increases time slightly in preprocessing and querying. Particularly, the SIFT, contour and colour features are fused into the integrated multi-index, and the joint cooperation of complementary features significantly reduces the impact of false positive matches, so that effective image retrieval can be achieved. Extensive experiments on five benchmark datasets show that the 3D integrated multi-index significantly improves the retrieval accuracy. While compared with other methods, it requires an acceptable memory usage and query time. Importantly, we show that the 3D integrated multi-index is well complementary to many prior techniques, which make our method compared favorably with the state-of-the-arts.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.25 no.4
• /
• pp.313-332
• /
• 2014

With the increased creation, distribution, and use of image in context of the development of digital technologies and internet, research endeavors have accumulated drastically. As two dominant aspects of image retrieval have been considered content-based and concept-based image retrieval, concept-based image retrieval has been focused in the field of Library and Information Science. This study aims to systematically review the accumulated research of image retrieval from the perspective of LIS field. In order to achieve the purpose of this study, two data sets were prepared: a total of 282 image retrieval research papers from Web of Science, and a total of 35 image retrieval research from DBpia in Kore for comparison. For data analysis, systematic review methodology was utilized with bibliographic analysis of individual research papers in the data sets. The findings of this study demonstrated that two sub-areas, image indexing and description and image needs and image behavior, were dominant. Among these sub-areas, the results indicated that there were emerging areas such as collective indexing, image retrieval in terms of multi-language and multi-culture environments, and affective indexing and use. For the user-centered image retrieval research, college and graduate students were found prominent user groups for research while specific user groups such as medical/health related users, artists, and museum users were found considerably. With the comparison with the distribution of sub-areas of image retrieval research in Korea, considerable similarities were found. The findings of this study expect to guide research directions and agenda for future.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.157-160
• /
• 2000

This paper proposes a color-based image retrieval method using color adjacency and gradient. In proposed method, both the adjacency of different colors and gradient of a color in homogeneous region are considered as features of an image. The gradient, defined as the maximum distance along the direction with largest change of color, is computed for each pixel to determine whether the center color is similar or different to the neighboring colors. Therefore the problems caused by uniform quantization, which is popularly used at most existing retrieval, can be avoided. And furthermore, the storage of the feature is reduced by the proposed binary representation.

• Asia pacific journal of information systems
• /
• v.16 no.4
• /
• pp.203-215
• /
• 2006

The advent of KM(knowledge management) concept have led many organizations to seek an effective way to make use of their knowledge. But the absence of right tools for systematic handling of unstructured information makes it difficult to automatically retrieve and share relevant information that exactly meet user's needs. we propose a systematic method to enable content-based information retrieval from corpus of unstructured documents. In our method, a document is represented by using several key terms which are automatically selected based on their quantitative relevancy to the document. Basically, the relevancy is calculated by using a traditional TFIDF measure that are widely accepted in the related research, but to improve effectiveness of the measure, we exploited 'concept network' that represents term-term relationships. In particular, in constructing the concept network, we have also considered relative position of terms occurring in a document. A prototype system for experiment has been implemented. The experiment result shows that our approach can have higher performance over the conventional TFIDF method.