• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.9C
• /
• pp.930-938
• /
• 2005

We propose a content-based image retrieval(CBIR) method based on an efncient combination of a color feature and multiresolution texture features. As a color feature, a HSV autocorrelograrn is chosen which is blown to measure spatial correlation of colors well. As texture features, BDIP and BVLC moments are chosen which is hewn to measure local intensity variations well and measure local texture smoothness well, respectively. The texture features are obtained in a wavelet pyramid of the luminance component of a color image. The extracted features are combined for efficient similarity computation by the normalization depending on their dimensions and standard deviation vectors. Experimental results show that the proposed method yielded average $8\%\;and\;11\%$ better performance in precision vs. recall than the method using BDIPBVLC moments and the method using color autocorrelograrn, respectively and yielded at least $10\%$ better performance than the methods using wavelet moments, CSD, color histogram. Specially, the proposed method shows an excellent performance over the other methods in image DBs contained images of various resolutions.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.1C
• /
• pp.45-52
• /
• 2008

In this paper, we describe the Perceptually Weighted Histogram(PWH) and the Gaussian Weighted Histogram Intersection(GWHI) algorithms. These algorithms are able to provide positive results in image retrieval. But these histogram methods alter the histogram of an image by using particular lighting conditions. Even two pictures with little differences in lighting are not easily matched. Therefore, we propose that the Histogram Matching Algorithm(HMA) is able to overcome the problem of an image being changed by the intensity or color in the image retrieval. The proposed algorithm is insensitive to changes in the lighting. From the experiment results, the proposed algorithm can achieve up to 32% and up to 30% more recall than the PWH and GWHI algorithms, respectively. Also, it can achieve up to 38% and up to 34% more precision than PWH and GWHI, respectively Therefore, with our experiments, we are able to show that the proposed algorithm shows limited variation to changes in lighting.

• Journal of Broadcast Engineering
• /
• v.3 no.2
• /
• pp.127-137
• /
• 1998

In this paper, we propose the method of extracting edge information from MPEG video sequences for the detection of scene changes. In a the proposed method, five significant AC coefficients of each MPEG block are utilized to obtain edge images from the MPEG video. AC edge images obtained by the proposed scheme not only produce better object boundary information than conventional methods using only DC coefficients, but also can reduce the boundary effects produced by DC-based. Since the AC edge image contains the content information of each frame, it can be effectively utilized for the detection of scene change as well as the content-based video query. Experimental results show that the proposed method can be effectively utilized for the detection of scene changes.

• Proceedings of the KSRS Conference
• /
• 2007.03a
• /
• pp.92-96
• /
• 2007

전라남도 국민참여형 위성영상 블로그 시스템은 2006년도 행정자치부 자치단체정보화지원사업의 일환으로 구축된 것으로서， 사용자가 고해상도 위성영상 위에 직접 자신의 글，사진， 동영상을 올리고，이를 다른 사용자나 시스템과 공유할 수 있도록 구축된 시스템이다. 본 시스템이 궁극적으로 구현하고자 했던 과제는 다음과 같다. (1)지리정보 혹은 기타 정보의 고정성을 탈피하고，(2)지리정보와 멀티미디어 자료의 효율적 통합을 통해 geoUCC를 구축하며，(3)사용자의 참여를 통한 지리정보 제공 방식의 쌍방향성을 구현하여，(4) 사용자를 일방적 자료 활용자에서 자료 생성자로 발전시키고 궁극적으로는 자치단체와 국민 간 새로운 방식의 소통 방식을 생성하는 것이다. 본 시스템 구축의 결과로서 본 시스템에서 일반 국민에게 서비스되는 내용은 다음과 같다. (1) 전라남도 전역의 1m급 고해상도 위성영상의 대국민 서비스，(2)전라남도 전역에 대한 지번 단위까지의 주소 검색 서비스，(3)웹 상에서의 실시간 3차원 GIS 서비스，(4)Web2.0의 철학을 반영한 RSS, Trackback 및 Tag 검색 기능，(5)사용자가 직접 고해상도 위성영상 위에 자신의 글， 사진，동영상，홈페이지 등을 올릴 수 있는 "위성영상 블로그 쓰기 기능"，(6)국내 거의 모든 포털 사이트의 블로그와 홈페이지를 지원하는 시스템 연계(퍼가기) 기능 등이다. 결론적으로 본 시스템의 사용자는 고해상도 위성영상 기반의 지도 위에 자신의 여행기，사진， 동영상을 올림으로써 자신만의 사용자제작콘텐츠(UCC)를 생성할 수 있을 뿐만 아니라， 이를 다른 사용자와 공유， 활용함으로써 실질적인 쌍방향，참여형 지리정보시스템을 이용하게 된 것이다.

• Journal of Korea Multimedia Society
• /
• v.5 no.6
• /
• pp.616-624
• /
• 2002

An extraction method of central objects in the color images is proposed, in this paper. A central object is defined as a comparatively consist of the central object in the image. First of all. an input image and its decreased resolution images are segmented. Segmented regions are classified as the outer or the inner region. The outer region is adjacent regions are included by a same region in the decreased resolution image. Then core object regions and core background regions are selected from the inner region and the outer region respectively. Core object regions are the representative regions for the object and are selected by using the information about the information about the region size and location. Each inner regions is classified into foreground or background regions by comparing values of a color histogram intersection of the inner region against the core object region and the core background regions. The core object region and foreground regions consist of the central object in the image.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2001.06a
• /
• pp.265-268
• /
• 2001

In content-based video data retrieval, the representative-frame is usually used. To do that, the skill of detection for scene change is needed. Generally the color histogram comparison is used, but sensitive to light variation and tends to miss the scene change of similar color histogram. This paper shows how to use both color histogram comparison and entropy to prevent the false-positive of scene change occurred by light variation. At the experiments, il is more powerful to light variation to use both color histogram comparison entropy than to use only color histogram comparison.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.10a
• /
• pp.809-812
• /
• 2001

내용에 기반한 동영상 검색에서, 하나의 장면을 나타내는 대표 프레임을 자주 이용한다. 이를 위해 동영상의 장면전환을 검출하는 기술이 필요하며, 일반적으로 칼라 히스토그램 비교방법이 많이 쓰인다. 그러나 이는 급격한 밝기변화에 민감하고 칼라 히스토그램 분포가 비슷한 부분의 장면전환을 놓칠 수 있다는 단점이 있다. 본 논문에서는 칼라 히스토그램 비교방법과 엔트로피를 복합적으로 이용하여 이러한 단점을 보완하고자 하였다. 실험을 통해 제안한 방법은 기존의 칼라 히스토그램을 이용한 방법보다 성능이 우수함을 알 수 있었다.

• Journal of Intelligence and Information Systems
• /
• v.12 no.1
• /
• pp.95-105
• /
• 2006

This paper proposes a novel approach to represent the image by using shape descriptor having an information of area. The proposed descriptor is a set of vectors, consists of radius, area and direction parameters in the concentrated center point. Due to the area parameter, we know our descriptor can obtain the information of area. Also, we give an extended shape descriptor to get more detailed representation. To do this, we move the center point of our vision to that point for region of interest. By doing so about all of region of interest, we can get our descriptor for detailed information of the image. From more detailed descriptor, it's natural that it's more efficient fur representation, retrievals and so on. We make it the normalized pattern and expand to improve its quality. The proposed method is invariant to scale, position and rotation. The results show that it can be used efficiently for image representation as we can see in retrievals of silhouette images.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.95-102
• /
• 2005

In this paper, we propose a user friendly object-based image retrieval system using the interaction between cortex and hippocampus. Most existing ways of queries in content-based image retrieval rely on query by example or query by sketch. But these methods of queries are not adequate to needs of people's various queries because they are not easy for people to use and restrict. We propose a method of automatic color object extraction using CSB tree map(Color and Spatial based Binary をn map). Extracted objects were transformed to bit stream representing information such as color, size and location by region labelling algorithm and they are learned by the hippocampal neural network using the interplay between cortex and hippocampus. The cells of exciting at peculiar features in brain generate the special sign when people recognize some patterns. The existing neural networks treat each attribute of features evenly. Proposed hippocampal neural network makes an adaptive fast content-based image retrieval system using excitatory learning method that forwards important features to long-term memories and inhibitory teaming method that forwards unimportant features to short-term memories controlled by impression.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.119-121
• /
• 2000

최근 급속히 발전하고 있는 컴퓨터 하드웨어 기술로 이미지, 오디오, 비디오 등의 방대한 멀티미디어 데이터가 비 선별적으로 일반 사용자에게 제공되어지고 있다. 하지만 상이한 해석이 가능한 멀티미디어 데이터의 특성상 정확한 데이터의 전달을 위해 각각의 사용자의 취향을 고려할 수 있는 지능 컴퓨팅 기술 즉, 개인화 모델의 이용이 필수적이다. 개인화 모델의 구축을 위해서는 사용자의 피드백 정보를 필요로 하게 되는데, 현재까지의 연구는 결과에 대한 만족정도를 사용자가 일일이 조사해야 하는 부담 때문에 사용자에게는 일반적인 환경에서 사용자의 묵시적인 피드백 정보를 이용하는 기술 개발의 필요성이 강조되고 있다. 본 논문에서는 묵시적으로 사용자의 시각 정보 및 행위 정보를 이용하여 사용자의 부담을 줄이는 동시에 적응 및 학습 능력을 갖는 지능 사용자 인터페이스를 적용한 내용기반 이미지 검색 시스템을 구현하였다.