• Journal of Korea Multimedia Society
• /
• v.7 no.9
• /
• pp.1312-1320
• /
• 2004

Recently, even if a lot of visual feature representations have been studied and systems have been built, there is a limit to existing content-based image retrieval mechanism in its availability. One of the limits is the gap between a user's high-level concepts and a system's low-level features. And human beings' subjectivity in perceiving similarity is excluded. Therefore, correct visual information delivery and a method that can retrieve the data efficiently are required. Relevance feedback can increase the efficiency of image retrieval because it responds of a user's information needs in multimedia retrieval. This paper proposes an efficient CBIR introducing positive and negative relevance feedback with threshold value and pre-fetching to improve the performance of conventional relevance feedback mechanisms. With this Proposed feedback strategy, we implement an image retrieval system that improves the conventional retrieval system.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.4
• /
• pp.933-943
• /
• 1997

In this paper, a conernt-based image retrival system with color assigments has been stueide and implment-ed. The color of images has been extracted after changing RGB color space to HSV(hue, saturation, value)that is the most compatible color for peop]e's feeling. In the color extracting, an image is divided into 9 different areasand 3 major colors for each area are selected by using color histograms. It is possible to chose the class of umages by keywords. We are evaluate four different types of queries such as an image input, keywords with color assignments, combining an image input and keywords with color assinments, and selecting specific part of an umage. Experimental rusults show that four different query types privide precision/recall 0.55/0.37, 0.57/0.43, 0.59/0.45 and 0.63/0.61, respectively. With color assignments, the retrieval system has been able to obtain high performance and validity.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.5
• /
• pp.1-11
• /
• 2007

As the availability of an image information has been significantly increasing, necessity of system that can manage an image information is increasing. Accordingly, we proposed the region-based content retrieval(CBIR) algorithm based on an efficient combination of an image segmentation, an image texture, a color feature and an image's shape and position information. As a color feature, a HSI color histogram is chosen which is known to measure spatial of colors well. We used active contour and CWT(complex wavelet transform) to perform an image segmentation and extracting an image texture. And shape and position information are obtained using Hu invariant moments in the luminance of HSI model. For efficient similarity computation, the extracted features(color histogram, Hu invariant moments, and complex wavelet transform) are combined and then precision and recall are measured. As a experimental result using DB that was supported by www.freefoto.com. the proposed image retrieval engine have 94.8% precision, 82.7% recall and can apply successfully image retrieval system.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.309-314
• /
• 2006

Recently, multimedia DBMS is appeared to be the core technology of the information society to store, manage and retrieve multimedia data efficiently. In this paper, we propose a new method for content based-retrieval system using wavelet transform, energy value to extract automatically feature vector from image data, and suggest an effective retrieval technique through this method. Wavelet transform is widely used in image compression and digital signal analysis, and its coefficient values reflect image feature very well. The correlation in wavelet domain between query image data and the stored data in database is used to calculate similarity. In order to assess the image retrieval performance, a set of hundreds images are run. The method using standard derivation and mean value used for feature vector extraction are compared with that of our method based on energy value. For the simulation results, our energy value method was more effective than the one using standard derivation and mean value.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.990-999
• /
• 2007

In this paper, we propose the region-based image retrieval method using JSEG which is a method for unsupervised segmentation of color-texture regions. JSEG is an algorithm that discretizes an image by color classification, makes the J-image by applying a region to window mask, and then segments the image by using a region growing and merging. The segmented image from JSEG is given to a user as the query image, and a user can select a few segmented regions as the query region. After finding the MBR of regions selected by user query and generating the multiple window masks based on the center point of MBR, we extract the feature vectors from selected regions. We use the accumulated histogram as the global descriptor for performance comparison of extracted feature vectors in each method. Our approach fast and accurately supplies the relevant images for the given query, as the feature vectors extracted from specific regions and global regions are simultaneously applied to image retrieval. Experimental evidence suggests that our algorithm outperforms the recent image-based methods for image indexing and retrieval.

• The Journal of the Korea Contents Association
• /
• v.8 no.3
• /
• pp.1-7
• /
• 2008

Due to the development of ubiquitous computing, a wide variety of information is being produced and distributed rapidly in digital form. In this excess of information, it is not easy for users to search and find their desired information in short time. In this paper, we propose the personalized item recommendation using the image based filtering. This research uses the image based filtering which is extracting the feature from the image data that a user is interested in, in order to improve the superficial problem of content analysis. We evaluate the performance of the proposed method and it is compared with the performance of previous studies of the content based filtering and the collaborative filtering in the MovieLens dataset. And the results have shown that the proposed method significantly outperforms the previous methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.462-467
• /
• 2008

최근 웹 2.0 시대 참여, 공유, 개방 정신이 확대 되고, 다양한 디지털 저작물들이 대량 제작되어 활용되고 있다. 그리고 디지털 저작물의 특징상 누구나 손쉽게 무제한으로 복제와 유통이 가능함으로 디지털 저작물이 양은 기하급수적으로 증가하고 있다. 증가하는 이미지를 효과적으로 관리하고 검색하기 위해 색상, 질감, 모양 등을 이용한 내용기반 이미지 검색에 대한 연구가 활발히 진행되고 있다. 색상을 이용한 이미지 검색방법의 하나로 색상 히스토그램을 이용한 검색 방법이 있다. 그러나 이는 공간적인 상호관계를 적절히 표현하지 못한다는 단점이 있다. 따라서 본 논문에서는 이미지에 나타나는 주요 색상 및 불변 모멘트 값과 이미지의 중앙을 중심으로 한 영역별 유사도 검사를 통한 내용기반 이미지 검색 시스템을 제안한다. 첫 번째 유사성 검사 단계에서는 이미지의 영역별로 가중치를 부여하여 추출한 대표색상 정보를 사용하여, 유사하지 않은 이미지를 제거하여 검색대상의 수를 줄인다. 두 번째 유사성 검사 단계에서는 이미지를 영역으로 나누고, 이미지의 중심 영역부터 영역을 확장하며 영역마다 구축된 인덱스 검색을 통해 영역기반 유사 이미지 검색을 수행 한다. 세 번 단계에서는 이미지의 변형에 불변한 값인 불변 모멘트를 사용하여, 영역별 검사에서 제외된 유사이미지를 재검사한다. 제안한 이미지 검색 방법은 10000개의 다양한 이미지로 구성된 이미지 데이터베이스에서 검색을 실험을 통해 검색의 정확도 및 회수율을 측정하였다.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.10
• /
• pp.113-122
• /
• 1999

When we want to retrieve the most similar image from the image database, the color histogram intersection, shape feature and texture feature comparing method are used as a metric to measure the similarity. In order to increase the accuracy of retrievals, we need to integrate two different features. In this paper, the histogram intersection and shape based block histogram intersection method are used. This method results in a high efficient algorithm that meets a similar accuracy and a relatively fast retrieval speed compared to the method of integration of two different features. The Proposed algorithm is tested on retrievals of image database consisting of various 600 images and we implemented that the proposed algorithm gives fast, high efficiency and reliability compared to others.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.503-505
• /
• 1998

효율적인 영상 검색 시스템을 구축하기 위하여 칼라, 형태, 질감등과 같은 특징을 추출하여 검색하는 방법들이 연구되어 지고 있다. 이 중 기존의 형태 정보를 이용한 방법은 적용 대상을 국한하여 연구되거나 특징 추출을 위한 계산의 복잡성에 비해 좋은 효과를 보이지 않고 있다. 본 논문에서는 이러한 문제점을 해결하고 다양한 영상에 적용할 수 있는 특징을 추출하고자 통계적인 방법중의 하나인 히스토그램을 이용하고자 한다. 히스토그램을 이용한 방법은 계산이 용이할 뿐 아니라 검색 결과면에서도 높은 효율을 보이고 있다. 영상으로부터 추출한 선분을 각도에 따라 18개의 빈으로 양자화 하여 각 빈에 속한 선분들의 길이의 합을 이용하여 비교하는 각도 히스토그램(angular histogram), 그리고 선분들이 공간 분포에 대한 정보를 얻기 위하여 각도 히스토그램에서 각 빈에 속한 선분들의 대표 좌표들의 1차, 2차, 3차 모멘트를 구하여 사용하는 방법과 특정 각도를 가진 선분들 사이의 거리를 이용한 각도 Correlogram을 제안한다.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.275-276
• /
• 2006

본 논문에서는 내용기반 영상검색을 보다 효과적인 알고리즘 설계를 위해 칼라 RGB 특징정보 추출에 median 필터링을 이용한 영상검색의 성능을 분석하였다. 칼라영상에서 각각의 R,G,B칼라영상으로 나눈 후 일정크기의 블록으로 분할하여 R,G,B 각각의 중간값을 추출하고 크기순과 레벨의 특징자를 이용한 영상검색 기법을 제안한다.