• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.894-897
• /
• 2000

In this paper, we present a content-based image retrieval method that is less sensitive to some rotations and translations of an image by using the fuzzy region segmentation. The algorithm retrieves similar images from a database using the two features of color and color spatial information. To index images, we use the average coordinates of color distribution to obtain the spatial information of each segmented region. Furthermore, we also propose the alternative to the ripple phenomenon, which is occurred in the conventional fuzzy region segmentation algorithm.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.06a
• /
• pp.355-358
• /
• 2011

본 논문에서는 이미지에서 사용자가 관심을 갖는 영역(ROI)의 내용을 나타내는 특성값과 영역의 위치를 함께 고려하여 이미지를 검색하는 방법을 제안한다. 제안한 방법은 검색 대상 이미지를 일정 크기의 블록으로 구분한 후 사용자가 선택한 다중 ROI와 가장 근접하는 특성을 가진 블록을 선택한다. 블록의 특성값은 MPEG-7의 도미넌트 컬러 기술자를 사용한다. 사용자가 선택한 블록의 특성값과 함께 블록의 위치를 측정한 후, 검색 대상 이미지의 블록들의 특성값 및 위치와 비교하여 유사도를 측정한다. 본 논문에서는 실험결과 제안한 방법이 전역 이미지 검색이나 동일한 위치의 블록만 비교하는 경우보다 다중 ROI의 내용과 위치를 함께 고려하는 방법이 다른 방법에 비해 우수한 성능을 나타냈다.

• Journal of the Korean Society for information Management
• /
• v.21 no.4 s.54
• /
• pp.187-208
• /
• 2004

In this study, aesthetic impressions were used for a high-level feature of image retrieval. The term, 'aesthetic' has been studied in psychology, art, and literature. It means unconscious, instantaneous parts of visual perception and emotion. The literatures related to aesthetic impressions were reviewed and four kinds of aesthetic impressions were defined operationally : strong impression, soft impression, courteous impression, and refined impression. 66 image files of paintings were sampled randomly from 1100 paintings and low-level color features were extracted from them by a using perceptual color model(Lai, & Tait, 1998). The high-level features of an image, that is, four kinds of aesthetic impressions of each painting were measured by 4 subjects and averaged. In CBIR, 2 subjects performed image retrievals using example queries. They were asked to retrieve images by using the aesthetic impressions or the keywords. In evaluations, subjects showed that they were satisfied with the aesthetic impression-based image retrieval system on the average. And R-precision of the image retrieval with both color features and aesthetic impressions was higher than that of the image retrieval with color features only. But further studies with larger test collections and query sets should be followed for generalization of the result of this study.

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.515-522
• /
• 2001

Feature-based similarity retrieval become an important research issue in image database systems. The features of image data are useful to discrimination of images. In this paper, we propose the highspeed k-Nearest Neighbor search algorithm based on Self-Organizing Maps. Self-Organizing Map(SOM) provides a mapping from high dimensional feature vectors onto a two-dimensional space. A topological feature map preserves the mutual relations (similarity) in feature spaces of input data, and clusters mutually similar feature vectors in a neighboring nodes. Each node of the topological feature map holds a node vector and similar images that is closest to each node vector. We implemented about k-NN search for similar image classification as to (1) access to topological feature map, and (2) apply to pruning strategy of high speed search. We experiment on the performance of our algorithm using color feature vectors extracted from images. Promising results have been obtained in experiments.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.6
• /
• pp.692-704
• /
• 2002

In this paper, we present am image retrieval method based on color-spatial features using quadtree and texture information extracted from object MBRs in an image. Tile proposed method consists of creating a DC image from an original image, changing a color coordinate system, and decomposing regions using quadtree. As such, conditions are present to decompose the DC image, then the system extracts representative colors from each region. And, image segmentation is used to search for object MBRs, including object themselves, object included in the background, or certain background region, then the wavelet coefficients are calculated to provide texture information. Experiments were conducted using the proposed similarity method based on color-spatial and texture features. Our method was able to refute the amount of feature vector storage by about 53%, but was similar to the original image as regards precision and recall. Furthermore, to make up for the deficiency in using only color-spatial features, texture information was added and the results showed images that included objects from the query images.

• Journal of KIISE:Databases
• /
• v.33 no.4
• /
• pp.372-383
• /
• 2006

Among the approaches to image database management, content-based image retrieval (CBIR) is viewed as having the best support for effective searching and browsing of large digital image libraries. Typical CBIR systems allow a user to provide a query image, from which low-level features are extracted and used to find 'similar' images in a database. However, there exists the semantic gap between human visual perception and low-level representations. An effective methodology for overcoming this semantic gap involves relevance feedback to perform feature re-weighting. Current approaches to feature re-weighting require the number of components for a feature representation to be the same for every image in consideration. Following this assumption, they map each component to an axis in the n-dimensional space, which we call the metric space; likewise the feature representation is stored in a fixed-length vector. However, with the emergence of features that do not have a fixed number of components in their representation, existing feature re-weighting approaches are invalidated. In this paper we propose a feature re-weighting technique that supports features regardless of whether or not they can be mapped into a metric space. Our approach analyses the feature distances calculated between the query image and the images in the database. Two-sided confidence intervals are used with the distances to obtain the information for feature re-weighting. There is no restriction on how the distances are calculated for each feature. This provides freedom for how feature representations are structured, i.e. there is no requirement for features to be represented in fixed-length vectors or metric space. Our experimental results show the effectiveness of our approach and in a comparison with other work, we can see how it outperforms previous work.

• Journal of Korea Multimedia Society
• /
• v.13 no.12
• /
• pp.1786-1797
• /
• 2010

Automatic understanding of contents in document image is a very hard problem due to involvement with mathematically challenging problems originated mainly from the over-determined system induced by document segmentation process. In both academic and industrial areas, there have been incessant and various efforts to improve core parts of content retrieval technologies by the means of separating out segmentation related issues using semi-structured document, e.g., invoice,. In this paper we proposed classification models for text lines on invoice document in which text lines were clustered into the five categories in accordance with their contents: purchase order header, invoice header, summary header, surcharge header, purchase items. Our investigation was concentrated on the performance of machine learning based models in aspect of linear-discriminant-analysis (LDA) and non-LDA (logic based). In the group of LDA, na$\"{\i}$ve baysian, k-nearest neighbor, and SVM were used, in the group of non LDA, decision tree, random forest, and boost were used. We described the details of feature vector construction and the selection processes of the model and the parameter including training and validation. We also presented the experimental results of comparison on training/classification error levels for the models employed.

• Journal of IKEEE
• /
• v.14 no.4
• /
• pp.305-311
• /
• 2010

Most recent web search engines perform effective keyword-based multimedia contents retrieval by investigating keywords associated with multimedia contents on the Web and comparing them with query keywords. On the other hand, most music and compilation albums provide professional artwork as cover art that will be displayed when the music is played. If the cover art is not available, then the music player just displays some dummy or random images, but this has been a source of dissatisfaction. In this paper, in order to automatically create cover art that is matched with music contents, we propose a music album cover art creation scheme based on music contents analysis and result synthesis. We first (i) analyze music contents and their lyrics and extract representative keywords, (ii) expand the keywords using WordNet and generate various queries, (iii) retrieve related images from the Web using those queries, and finally (iv) synthesize them according to the user preference for album cover art. To show the effectiveness of our scheme, we developed a prototype system and reported some results.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.661-683
• /
• 2001

There is a rapid increase in the use of digital video information in recent years, it becomes more important to manage video databases efficiently. The development of high speed data network and digital techniques has emerged new multimedia applications such as internet broadcasting, Video On Demand(VOD) combined with video data processing and computer. Video database should be construct for searching fast, efficient video be extract the accurate feature information of video with more massive and more complex characteristics. Video database are essential differences between video databases and traditional databases. These differences lead to interesting new issues in searching of video, data modeling. So, cause us to consider new generation method of database, efficient retrieval method of video. In this paper, We propose the construction and generation method of the video database based on contents which is able to accumulate the meaningful structure of video and the prior production information. And by the proposed the construction and generation method of the video database implemented the video database which can produce the new contents for the internet broadcasting centralized on the video database. For this production, We proposed the video indexing method which integrates the annotation-based retrieval and the content-based retrieval in order to extract and retrieval the feature information of the video data using the relationship between the meaningful structure and the prior production information on the process of the video parsing and extracting the representative key frame. We can improve the performance of the video contents retrieval, because the integrated video indexing method is using the content-based metadata type represented in the low level of video and the annotation-based metadata type impressed in the high level which is difficult to extract the feature information of the video at he same time.

• 한국정보통신설비학회:학술대회논문집
• /
• 2004.08a
• /
• pp.81-85
• /
• 2004

내용기반 질의법 (Content-based Query Method)은 멀티미디어 데이터가 가지고 있는 고유의 특성을 검색의 단서로 하여 질의하는 방법이다. 따라서 이러한 내용 기반의 디지털 오디오 콘텐츠 시스템은 유저가 데이터베이스 내에서 찾고자 하는 오디오 관련 정보의 질의 방법으로써 그 노래의 멜로디 정보를 입력함으로써 이루어지게 된다. 본 논문에서는 가수명이나 노래 제목, 혹은 가사의 일부 등 기존의 음악 검색에 필수적인 텍스트 정보인 키워드를 전혀 모르는 상태에서, 휴대폰이나 컴퓨터의 마이크를 통해 자신이 기억하고 있는 노래의 일부분을 흥얼거리는 것만으로, 각종 오디오 정보를 손쉽게 찾아주는 내용기반 질의법을 이용한 디지털오디오 검색시스템 (MuseFinder)을 소개한다. 또한 실제 유저의 편이성을 고려한 GUI에 기초한 고성능의 검색시스템을 구현하는데 있어 주요 이슈와 고려사항에 대해서 살펴보고 그 해결 방법을 제안한다.