• Journal of the Korean Society for Library and Information Science
• /
• v.51 no.4
• /
• pp.121-138
• /
• 2017

As information users seek multimedia with a wide variety of information needs, information environments for multimedia have been developed drastically. More specifically, as seeking multimedia with emotional access points has been popular, the needs for indexing in terms of abstract concepts including emotions have grown. This study aims to analyze the index terms extracted from Getty Image Bank. Five basic emotion terms, which are sadness, love, horror, happiness, anger, were used when collected the indexing terms. A total 22,675 index terms were used for this study. The data are three sets; entire emotion, positive emotion, and negative emotion. For these three data sets, co-word occurrence matrices were created and visualized in weighted network with PNNC clusters. The entire emotion network demonstrates three clusters and 20 sub-clusters. On the other hand, positive emotion network and negative emotion network show 10 clusters, respectively. The results point out three elements for next generation of multimedia retrieval: (1) the analysis on index terms for emotions shown in people on image, (2) the relationship between connotative term and denotative term and possibility for inferring connotative terms from denotative terms using the relationship, and (3) the significance of thesaurus on connotative term in order to expand related terms or synonyms for better access points.

• Journal of KIISE:Databases
• /
• v.34 no.5
• /
• pp.420-436
• /
• 2007

The choice of an effective indexing method is crucial to guarantee the performance of the spatial join operator which is heavily used in geographical information systems. The $R^*$-tree based method is renowned as one of the most representative indexing methods. In this paper, we propose an efficient spatial join technique based on the DOT(Double Transformation) index, and compare it with the spatial Join technique based on the $R^*$-tree index. The DOT index transforms the MBR of an spatial object into a single numeric value using a space filling curve, and builds the $B^+$-tree from a set of numeric values transformed as such. The DOT index is possible to be employed as a primary index for spatial objects. The proposed spatial join technique exploits the regularities in the moving patterns of space filling curves to divide a query region into a set of maximal sub-regions within which space filling curves traverse without interruption. Such division reduces the number of spatial transformations required to perform the spatial join and thus improves the performance of join processing. The experiments with the data sets of various distributions and sizes revealed that the proposed join technique is up to three times faster than the spatial join method based on the $R^*$-tree index.

• Journal of the Korean Society for Library and Information Science
• /
• v.42 no.1
• /
• pp.253-272
• /
• 2008

While relevant studies emphasize the significance of user-oriented indexing associated with fulfilling both topical and non-topical needs of individual users, a great number of operational retrieval systems supports only those searches related to subject attributes of the users' needs. Retrieval systems for presidential image collections are not an exception for such a restriction. Upon this reality. this study seeks diversification of access points for presidential images based on descriptors directly presented by potential user groups. Improvements of subject-based descriptors are suggested based on those descriptors identified.

• Annual Conference on Human and Language Technology
• /
• 2001.10d
• /
• pp.57-62
• /
• 2001

인터넷의 급속한 양적 증가로 인해 색인어 기반의 검색 방식만으로는 원하는 정보를 찾아 내기가 쉽지 않다. 색인어 기반의 검색 방식에서는 색인어로 나타나지 않는 특징을 이용할 수 없으며, 질적으로 균등한 검색 결과를 제시하지 못하기 때문이다. 따라서 사이트의 여러 가지 특성에 따라 계층적으로 분류해놓은 웹 디렉토리를 이용하거나, 관련 전문가들의 추천 리스트를 이용하여 검객하기도 한다. 본 연구에서는 기존의 색인어 기반의 검색 모델에 웹 디렉토리와 추천 문서 같은 문서간의 링크 정보를 결합할 수 있는 정보 검색 모델을 제시한다. 특정 질의어의 검색 결과로 얻어낸 문서와 그 문서와 연결된 문서 집합을 이용하여 네트워크를 구성한다. 이 네트워크에 검색기가 제시하는 순위와 유사도, 그리고 문서간의 링크 정도를 이용해서 확률값을 정해준다. 그리고 Ergodic Markov Model의 특성을 이용하여 색인어 정보와 링크 정보를 결합한다. 본 연구에서는 특정 문서가 질의어에 부합되는 정도를 사용자가 그 문서로 이동할 확률값으로 계산하는 방식을 보인다.

• Journal of Information Management
• /
• v.29 no.1
• /
• pp.20-39
• /
• 1998

In order to index documents, a thesaurus which consists of terms and relationships between terms is used. When an index term is selected, retrieval performance in the information retrieval system could be improved by using the relationship between the terms in the thesaurus. Recently, the usage of a thesaurus are extended from information retrieval to language and knowledge engineering, but term relationships in a thesaurus are simply represented in equivalence, hierarchy, and association. Particularly the associative relationship is vague in its definition and range as compared with the other relationships, i.e. equivalence, hierarchy, therefore the terms that are selected through associative relationship aren't well controlled. This study examines the relationships of existing thesauri, especially the types and ranges of associative relationship, and suggests the adequate type of associative relationship.

• Proceedings of the Korea Society of Costume Conference
• /
• 2001.04a
• /
• pp.42-43
• /
• 2001

색상특성은 각 계열별로 차이가 있었으나 전반적 으로 고명도.저채도 중심으로 황색계열과 청색계열 은 고명도 위주의 분포특성을 보였다. 이어 반하여 적색계열은 비교적 색조의 영역이 넓었으며 고채도 의 분포특성이 두드러졌다. 자색계열은 저명도.중 채도, 녹색계열은 고명도.저채도 중심이었다. 남.녀복의 색조유형으로서 여복에서는 white보다는 tone 중심의 색조특성이 나타났으며. 남복에서는 white를 제외한 tint의 색조유형이 많았다. 이는 당시대인의 백색지향 의식을 대변하는 것으로 사료된다. 음양오행론의 배색원리에 의해 검토한 결과 여복 은 상생이 남복보다 낮게 집계되었으며, 반대로 파버 비렌의 색채조화의 배색원리에 의한 검토 철과는 남 복보다 여복의 적용수치가 높았다. 이것은 감각적인 색채조화 보다는 의례적인 성향이 좀 더 징한 남복이 서구의 색채조화의 척도에 적합하지 않은 결과로 추측된다. 전통복의 배색특성은 남녀가 매우 다른 양상을 보 이고 있었다. 여복의 기본 복식구조인 저고리/치마 는 백/청색계열, 백/황색계열과의 배색이 중심으로서 면적대비 및 명도대비에 의한 조화가 이루어지고 있었다. 반면에 저고리의 배색은 유채색과 백색계열 의 배색으로 채도대비의 성향이 강했다. 남복은 황/백색계열. 백/청색계열로 명도의 차가 크지 않았다. 포/띠의 의복 구성에 있어서는 흑색 또 는 적.자색 등의 세조대(細條帶)로 인해 채도대비, 면적대비, 명도대비의 배색효과를 찾아볼 수 있었다. 이상과 같은 분석결과를 통한 한국인의 색사용의 특정은 복식의 전면에 등장하는 백색지향과 음양오 행설을 그 배경으로 하고 있다. 백색위주의 색사용은 인공미가 배제된 자연미의 추구에 기인한 것으로 토착화된 한국의 색으로 볼 수 있다. 백색은 여러 색을 통합하고 배색된 색채착화된 한국의 색으로 볼 수 있다. 백색은 여러 색을 통합하고 배색된 색채들을 담하게 만드는 것이 특징 으로 한국전통 복식의 배색특성을 주도하고 있었다. 마지막으로 본 연구는 회화자료를 근거한 것으로 풍속화의 변색 및 탈색에 의해 당시대의 정확한 색채규명이 어려우며, 실물작품이 아닌 도판을 통한 측 색으로 색의 오차가 발생할 수 있음을 연구의 한계 점으로 언급하고자 한다.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.5 no.2
• /
• pp.54-68
• /
• 2002

In this paper, We propose a multi-dimensional index structure, called a VA (vector approximate) -tree that constructs a tree with vector approximates of multi-dimensional feature vectors. To save storage space for index structures, the VA-tree employs vector approximation concepts of VA-file that presents feature vectors with much smaller number of bits than original value. Since the VA-tree is a tree structure, it does not suffer from performance degradation owing to the increase of data. Also, even though the VA-tree is MBR Minimum Bounding Region) based tree structure like a R-tree, its split algorithm never allows overlap between MBRs. We show through various experiments that our proposed VA-tree is the efficient index structure for large amount of multi-dimensional data.

• Spatial Information Research
• /
• v.2 no.2
• /
• pp.189-196
• /
• 1994

Adaptive smoothing filter is a filter that averages out the intensities around the pixels of similar intensities while conserving the discontinuties. When human eyes rec-ognize a map, the brain can easily assign one color for each element such as road or building while computer distinguishes all the minute color differences even for one ele¬ment. We can approach to the solution by using the adaptive smoothing filter so that the machine can assign one color for each element as much as we want, and it is found to be a very essential tool foor map segmentation of urban areas. The filter is applied to a scanned map, and it is used to extract roads and residential areas.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.143-146
• /
• 2008

For tracing tag locations, a trajectories should be modeled and indexed in radio frequency identification (RFID) systems. The trajectory of a tag can be represented as a line that connects two spatiotemporal locations captured when the tag enters and leaves the vicinity of a reader. If a tag enters but does not leave a reader, its trajectory is represented only as a point captured at entry and we should extend the region of a query to find the tag that remains in a reader. In this paper, we propose an interval data model of tag's trajectory in order to solve the problem. For the interval data model. we propose a new index scheme called the IR-tree(Interval R-tree) and algorithms of insert and split for processing query efficiently. We also evaluate the performance of the proposed index scheme and compare it with the previous indexes.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.6
• /
• pp.1458-1467
• /
• 1999

Existing index structures such as extendable hashing and B+-tree do not support partial string searches perfectly. The inverted file method and the signature file method that are used in the web retrieval engine also have problems that they do not provide partial string searches and suffer from serious retrieval performance degradation respectively. In this paper, we propose an efficient index method that supports partial string searches and achieves good retrieval performance. The proposed index method is based on the Inverted file structure. It constructs the index file with patterns that result from dividing terms by two syllables to support partial string searches. We analyze the characteristics of our proposed method through simulation experiments using wide range of parameter values. We analyze the derive analytic performance evaluation models of the existing inverted file method, signature file method and the proposed index method in terms of retrieval time and storage overhead. We show through performance comparison based on analytic models that the proposed method significantly improves retrieval performance over the existing method.