• Journal of Korea Multimedia Society
• /
• v.5 no.3
• /
• pp.281-289
• /
• 2002

Few studies have been systematically pursued on a multimedia data mining in despite of the over-whelming amounts of multimedia data by the development of computer capacity, storage technology and Internet. Based on the preliminary image processing and content-based image retrieval technology, this paper presents the methods for discovering association rules from recurrent items with spatial relationships in huge data repositories. Furthermore, multimedia mining algorithm is proposed to find implicit association rules among objects of which content-based descriptors such as color, texture, shape and etc. are recurrent and of which descriptors have spatial relationships. The algorithm with recurrent items in images shows high efficiency to find set of frequent items as compared to the Apriori algorithm. The multimedia association-rules algorithm is specially effective when the collection of images is homogeneous and it can be applied to many multimedia-related application fields.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.113-121
• /
• 2012

In this paper, we proposed fast and efficient algorithm for detecting near-duplication based on content based retrieval in large scale video database. For handling large amounts of video easily, we split the video into small segment using scene change detection. In case of video services and copyright related business models, it is need to technology that detect near-duplicates, that longer matched video than to search video containing short part or a frame of original. To detect near-duplicate video, we proposed motion distribution and frame descriptor in a video segment. The motion distribution descriptor is constructed by obtaining motion vector from macro blocks during the video decoding process. When matching between descriptors, we use the motion distribution descriptor as filtering to improving matching speed. However, motion distribution has low discriminability. To improve discrimination, we decide to identification using frame descriptor extracted from selected representative frames within a scene segmentation. The proposed algorithm shows high success rate and low false alarm rate. In addition, the matching speed of this descriptor is very fast, we confirm this algorithm can be useful to practical application.

• Journal of Korea Multimedia Society
• /
• v.14 no.10
• /
• pp.1252-1261
• /
• 2011

In this paper, we propose the comparison method of pattern similarity for video segmentation algorithm. The shot boundary type is categorized as 2 types, abrupt change and gradual change. The representative examples of gradual change are dissolve, fade-in, fade-out or wipe transition. The proposed method consider the problem to detect shot boundary as 2-class problem. We concentrated if the shot boundary event happens or not. It is essential to define similarity between frames for shot boundary detection. We proposed 2 similarity measures, within similarity and between similarity. The within similarity is defined by feature comparison between frames belong to same shot. The between similarity is defined by feature comparison between frames belong to different scene. Finally we calculated the statistical patterns comparison between the within similarity and between similarity. Because this measure is robust to flash light or object movement, our proposed algorithm make contribution towards reducing false positive rate. We employed color histogram and mean of sub-block on frame image as frame feature. We performed the experimental evaluation with video dataset including set of TREC-2001 and TREC-2002. The proposed algorithm shows the performance, 91.84% recall and 86.43% precision in experimental circumstance.

• Korean Journal of Environment and Ecology
• /
• v.22 no.3
• /
• pp.289-300
• /
• 2008

This study aims to discriminate differences in natural landscapes between the Cairngorms National Park in Scotland and the Jirisan National Park in Korea, using functions of content-based image retrieval such as texture, shape, and color. Digital photographs of each National Park were taken and selected. The low-level functions of photographic images were reduced to orthogonally rotated five factors. Based on the reduced factors, a linear decision boundary was obtained between Cairngorms landscapes and Jirisan landscapes. As a result, the discriminant function significantly delineated two groups, resulting in $x^2=63.40$ with df=5(p<0.001). Both the eigenvalue 2.417 and the value of wilks' lambda 0.29 supported that the most proportion of total variability came from the differences between the means of discriminant function of groups. It was estimated that four independent variables explained about 70.7% of total variance of dependent variable. The variable with the largest effect on landscapes was far region-related factor(r=1.07), followed by near region-related factor (r=0.90). A total of 90.7% of cross-validated grouped cases were correctly classified. It was interpreted that far distant regions, as well as near distant regions, had sufficient discrimination power for landscape classification between the Cairngorms National Park and the Jirisan National Park, so that landscape identity of the National Park over cultures was revealed by skylines in a most effective way. Relatively fewer factors making visual landscapes were effectively used to classify natural landscapes of the National Parks which had different semantics.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1999.06b
• /
• pp.103-108
• /
• 1999

방송 환경의 디지털화와 더불어 단순히 단방향 방송 정보만을 시청하던 기존의 방식을 넘어 사용자의 다양한 욕구를 수용할 수 있는 대화형 방송 서비스(interactive broadcasting service)가 시작되고 있다. 대화형 방송 환경에서는 특히 사용자 측에 제공된 방대한 양의 디지털 멀티미디어 자료에 대한 효과적인 접근이 요구되는데, 본 논문에서는 이를 위하여 방송 비디오를 효과적으로 브라우징(browsing) 및 검색하고 전체의 내용을 짧은 시간 내에 개관할 수 있도록 하는 동적 비디오 요약(dynamic video abstraction) 기법에 관하여 고찰한다. 동적 비디오 요약에 의한 요약 비디오(skim video)는 전체 비디오를 내용에 기반하여 효과적으로 표현할 수 있도록 동영상 내의 주요 구간만으로 구성된 것으로, 대화형 방송에서 새로운 형태의 프로그램 안내 및 사용자 저장 자료에 대한 브라우징 도구 등으로써 매우 유용하게 사용할 수 있다. 본 논문에서는 자동으로 비디오 요약을 구현하기 위한 접근 방법과 전체 기능 구성 및 각 기능들의 구현 방법에 대하여 기술한다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.1 s.33
• /
• pp.93-100
• /
• 2005

This study is to desist and implement an efficient microbial medical image retrieval system based on knowledge and content of them which can make use of more accurate decision on colony as doll as efficient education for new techicians. For this. re first address overall inference to set up flexible search path using rule-base in order U redure time required original microbial identification by searching the fastest path of microbial identification phase based on heuristics knowledge. Next, we propose a color ffature gfraction mtU, which is able to extract color feature vectors of visual contents from a inn microbial image based on especially bacteria image using HSV color model. In addition, for better retrieval performance based on large microbial databases, we present an integrated indexing technique that combines with B+-tree for indexing simple attributes, inverted file structure for text medical keywords list, and scan-based filtering method for high dimensional color feature vectors. Finally. the implemented system shows the possibility to manage and retrieve the complex microbial images using knowledge and visual contents itself effectively. We expect to decrease rapidly Loaming time for elementary technicians by tell organizing knowledge of clinical fields through proposed system.

• Journal of KIISE:Software and Applications
• /
• v.29 no.4
• /
• pp.235-247
• /
• 2002

For an efficient indexing and retrieval of digital video data, research on video caption extraction and recognition is required. This paper proposes methods for extracting artificial captions from video data and enhancing their image quality for an accurate Hangul and English character recognition. In the proposed methods, we first find locations of beginning and ending frames of the same caption contents and combine those multiple frames in each group by logical operation to remove background noises. During this process an evaluation is performed for detecting the integrated results with different caption images. After the multiple video frames are integrated, four different image enhancement techniques are applied to the image: resolution enhancement, contrast enhancement, stroke-based binarization, and morphological smoothing operations. By applying these operations to the video frames we can even improve the image quality of phonemes with complex strokes. Finding the beginning and ending locations of the frames with the same caption contents can be effectively used for the digital video indexing and browsing. We have tested the proposed methods with the video caption images containing both Hangul and English characters from cinema, and obtained the improved results of the character recognition.

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.18-29
• /
• 2007

In this paper we present a system that classifies brain MR images by using 2 level decision tree learning. There are two kinds of information that can be obtained from images. One is the low-level features such as size, color, texture, and contour that can be acquired directly from the raw images, and the other is the high-level features such as existence of certain object, spatial relations between different parts that must be obtained through the interpretation of segmented images. Learning and classification should be performed based on the high-level features to classify images according to their semantic meaning. The proposed system applies decision tree learning to each level separately, and the high-level features are synthesized from the results of low-level classification. The experimental results with a set of brain MR images with tumor are discussed. Several experimental results that show the effectiveness of the proposed system are also presented.

• Journal of Internet Computing and Services
• /
• v.1 no.2
• /
• pp.89-96
• /
• 2000

Relevance feedback is a technique to learn the user's subjective perception of similarity between images, and has recently gained attention in Content Based Image Retrieval. Most relevance feedback methods assume that the individual features that are used in similarity judgments do not interact with each other. However, this assumption severely limits the types of similarity judgments that can be modeled In this paper, we explore a more sophisticated model for similarity judgments based on fuzzy measures and the Choquet Integral, and propose a suitable algorithm for relevance feedback, Experimental results show that the proposed method is preferable to traditional weighted- average techniques.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.27 no.3
• /
• pp.59-65
• /
• 2004

This paper explores an image segmentation and representation method using Vector Quantization(VQ) on color and texture for content-based image retrieval system. The basic idea is a transformation from the raw pixel data to a small set of image regions which are coherent in color and texture space. These schemes are used for object-based image retrieval. Features for image retrieval are three color features from HSV color model and five texture features from Gray-level co-occurrence matrices. Once the feature extraction scheme is performed in the image, 8-dimensional feature vectors represent each pixel in the image. VQ algorithm is used to cluster each pixel data into groups. A representative feature table based on the dominant groups is obtained and used to retrieve similar images according to object within the image. The proposed method can retrieve similar images even in the case that the objects are translated, scaled, and rotated.