• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06b
• /
• pp.88-91
• /
• 2010

정보통신망 및 멀티미디어 기술의 발전으로 인해 정보의 형태는 단순한 텍스트 데이터에서 멀티미디어 데이터로 전환되고 있다. 멀티미디어 기술은 저장, 재생, 압축 등 관련 기술의 빠른 발전과 미디어의 사회, 문화적 역할이 계속 증가함에 따라 우리 사회 전반에 걸쳐 매우 광범위하게 사용되고 있으며, 이로 인해 동영상 검색등의 많은 검색을 요구 하고 있으나, 동영상 검색의 문제점은 생산되는 컨텐츠에서 동영상이 가지고 있는 비중은 계속해서 높아지지만 쌓아진 데이터를 검색하기엔 몇 가지 문제점이 있다. 첫 번째는 데이터의 중복성이고 두 번째는 제목, 내용 그리고 Keyword가 일치하지 않으며, 세 번째는 저자권 침해 등이 있다. 본 연구에서는 본 논문에서는 빠르게 변화되고 있는 정보화 시대에 맞게 동영상에서 음성과 얼굴영역을 검출하여, 검색 시 효율적이고 정확한 데이터의 검색이 이루어 질 수 있도록 검색 알고리즘을 제안하고 소개하며, 이중 두 번째의 문제점인 제목, 내용 그리고 Keyword의 불일치한 점에 두어 검색 시 영상의 이미지 검색과 음성을 통하여 keyword를 찾아 효율적이고 검색율의 높일 방법을 연구한다.

• Journal of the Korean Society for information Management
• /
• v.25 no.2
• /
• pp.49-68
• /
• 2008

In many information retrieval experiments, the data fusion techniques have been used to achieve higher effectiveness in comparison to the single evidence-based retrieval. However, there had not been many image retrieval studies using the data fusion techniques especially in combining retrieval results based on multiple retrieval methods. In this paper, we describe how the image retrieval effectiveness can be improved by combining two sets of the retrieval results using the Sobel operator-based edge detection and the Self Organizing Map(SOM) algorithms. We used the clip art images from a commercial collection to develop a test data set. The main advantage of using this type of the data set was the clear cut relevance judgment, which did not require any human intervention.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.2
• /
• pp.152-157
• /
• 2010

The development of computer and internet has introduced various types of media - such as, image, audio, video, and voice - to the traditional text-based information. However, most of the information retrieval systems are based only on text, which results in the absence of ability to use available information. By utilizing the available media, one can improve the performance of search system, which is commonly called content-based retrieval and content-based image retrieval system specifically tries to incorporate the analysis of images into search systems. In this paper, a content-based image retrieval system using HSI color space, ART2 algorithm, and SOM algorithm is introduced. First, images are analyzed in the HSI color space to generate several sets of features describing the images and an SOM algorithm is used to provide candidates of training features to a user. The features that are selected by a user are fed to the training part of a search system, which uses an ART2 algorithm. The proposed system can handle the case in which an image belongs to several groups and showed better performance than other systems.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.113-120
• /
• 2004

In this paper, we propose an efficient feature extraction and image retrieval algorithm for content-based retrieval method. First, we extract the object using Gaussian edge detector for input image which is key frames of MPEG video and extract the object features that are location feature, distributed dimension feature and invariant moments feature. Next, we extract the characteristic color feature using the proposed HAQ(Histogram Analysis md Quantization) algorithm. Finally, we implement an retrieval of four features in sequence with the proposed matching method for query image which is a shot frame except the key frames of MPEG video. The purpose of this paper is to propose the novel content-based image retrieval algerian which retrieves the key frame in the shot boundary of MPEG video belonging to the scene requested by user. The experimental results show an efficient retrieval for 836 sample images in 10 music videos using the proposed algorithm.

• Journal of KIISE:Databases
• /
• v.28 no.3
• /
• pp.406-417
• /
• 2001

With the advances in multimedia databases on the World Wide Web, it becomes more important to provide users with the search capability of distributed multimedia data. While there have been many studies about the database selection and the collection fusion for text databases. The multimedia databases on the Web have autonomous and heterogeneous properties and they use mainly the content based retrieval. The collection fusion problem of multimedia databases is concerned with the merging of results retrieved by content based retrieval from heterogeneous multimedia databases on the Web. This problem is crucial for the search in distributed multimedia databases, however, it has not been studied yet. This paper provides novel algorithms for processing the collection fusion of heterogeneous multimedia databases on the Web. We propose two heuristic algorithms for estimating the number of objects to be retrieved from local databases and an algorithm using the linear regression. Extensive experiments show the effectiveness and efficiency of these algorithms. These algorithms can provide the basis for the distributed content based retrieval algorithms for multimedia databases on the Web.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.10
• /
• pp.109-117
• /
• 2014

In navigation route planning systems using A* algorithms, the cardinality of an Open list, which is a list of candidate nodes through which a terminal node can be accessed, increases as the path length increases. In this paper, a method of alternately utilizing the Dijkstra's algorithm and the A* algorithm to reduce the cardinality of the Open list is investigated. In particular, by employing a depth parameter, named Level, the two algorithms are alternately performed depending on the Level's value. Using the hybrid searching approach, the Open list constructed in the Dijkstra's algorithm is transferred into the Open list of the A* algorithm, and consequently, the unconstricted increase of the cardinality of the Open list of the former algorithm can be avoided and controlled appropriately. In addition, an optimal or nearly optimal path similar to the Dijkstra's route, but not available in the A* algorithm, can be found. The experimental results, obtained with synthetic and real-life benchmark data, demonstrate that the computational cost, measured with the number of nodes to be compared, was remarkably reduced compared to the traditional searching algorithms, while maintaining the similar distance to those of the latter algorithms. Here, the values of Level were empirically selected. Thus, a study on finding the optimal Level values, while taking into consideration the actual road conditions remains open.

• Journal of Broadcast Engineering
• /
• v.16 no.3
• /
• pp.427-438
• /
• 2011

In this paper, we propose a content retrieval system using pictures taken from a display for more intelligent mobile services. We focus on the search robustness by minimizing the influence of photographing conditions such as changes in the illumination intensity. For an efficient search and precise detection, as well as robustness, we use a two-step comparison method based on indexing features and a binary map based on luminance and chrominance difference with the adjacent blocks. We also evaluate the proposed algorithm by comparing with the existing algorithms, and we show the content retrieval system that we've implemented using the proposed algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.5C
• /
• pp.513-519
• /
• 2007

Color correlogram is widely used in content-based image retrieval (CBIR) because it extracts not only the color distribution of pixels in images like color histogram, but also extracts the spatial information of pixels in the images. The color correlogram uses single color space. Therefore, the color correlograms does not have robust discriminative features. In this paper, we use both RGB and HSV color spaces together for the color correlogram to achieve better discriminative features. The proposed algorithm is tested on a large database of images and the results are compared with the single color space color correlogram. In simulation results, the proposed algorithm 5.63 average retrieval rank less than single color space correlogram.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.6
• /
• pp.118-126
• /
• 2003

This paper presents a low-complexity algorithm lot browsing a HD bit stream in DTV PVR according to its characteristics and also presents its implementation results. We propose an efficient algorithm which detects shots using some information after decoding MPEG-2 data, clusters them into scene and episode, and intelligently browses them according to some criteria after calculating their complexity. Some simulation results are presented to show the performance feasibility of the proposed algorithm. To implement it in real time, we propose an efficient hybrid architecture which partitions the algorithm into two parts of hardware and software. The hardware covers decoding process and extraction of some basic information which take most complexity in implementing the algorithm. The software covers the heuristic part of tile algorithm which has low complexity and needs to be expandable.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1013-1020
• /
• 2005

This paper presents an effective and robust leaf image retrieval system based on shape feature. Specifically, we propose an improved MPP algorithm for more effective representation of leaf images and show a new dynamic matching algorithm that basically revises the Nearest Neighbor search to reduce the matching time. In particular, both leaf shape and leaf arrangement can be sketched in the query for better accuracy and efficiency. In the experiment, we compare our proposed method with other methods including Centroid Contour Distance(CCD), Fourier Descriptor, Curvature Scale Space Descriptor(CSSD), Moment Invariants, and MPP. Experimental results on one thousand leaf images show that our approach achieves a better performance than other methods.