YoungSik Choi

Content-based image retrieval based on a fuzzy approach

A typical content-based image retrieval (CBIR) system would need to handle the vagueness in the user queries as well as the inherent uncertainty in image representation, similarity measure, and relevance feedback. We discuss how fuzzy set theory can be effectively used for this purpose and describe an image retrieval system called FIRST (fuzzy image retrieval system) which incorporates many of these ideas. FIRST can handle exemplar-based, graphical-sketch-based, as well as linguistic queries involving region labels, attributes, and spatial relations. FIRST uses fuzzy attributed relational graphs (FARGs) to represent images, where each node in the graph represents an image region and each edge represents a relation between two regions. The given query is converted to a FARG, and a low-complexity fuzzy graph matching algorithm is used to compare the query graph with the FARGs in the database. The use of an indexing scheme based on a leader clustering algorithm avoids an exhaustive search of the FARG database. We quantify the retrieval performance of the system in terms of several standard measures.

Graph matching by relaxation of fuzzy assignments

Graphs are very powerful and widely used representational tools in computer applications. We present a relaxation approach to (sub)graph matching based on a fuzzy assignment matrix. The algorithm has a computational complexity of O(n/sup 2/m/sup 2/) where n and m are the number of nodes in the two graphs being matched, and can perform both exact and inexact matching. To illustrate the performance of the algorithm, we summarize the results obtained for more than 12 000 pairs of graphs of varying types (weighted graphs, attributed graphs, and noisy graphs). We also compare our results with those obtained using the graduated assignment algorithm.

Relevance feedback for content-based image retrieval using the Choquet integral

Relevance feedback is a technique to learn the users subjective perception of similarity between images, and has recently gained attention in content based image retrieval (CBIR). 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. The authors 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. The proposed algorithm is being incorporated into a CBIR system developed at Korea Telecom.

An accurate COG Defuzzifier design using Lamarckian co-adaptation of learning and evolution

This paper proposes a design technique of optimal center of gravity (COG) defuzzifier using the Lamarckian coadaptation of learning and evolution. The proposed COG defuzzifier is specified by various design parameters such as the centers, widths, and modifiers of MFs. The design parameters are adjusted with the Lamarckian co-adaptation of learning and evolution, where the learning performs a local search of design parameters in an individual COG defuzzifier, but the evolution performs a global search of design parameters among a population of various COG defuzzifiers. This co-adaptation scheme allows to evolve much faster than the non-learning case and gives a higher possibility of finding an optimal solution due to its wider searching capability. An application to the truck backer-upper control problem of the proposed co-adaptive design method of COG defuzzifier is presented. The approximation ability and control performance are compared with those of the conventionally simplified COG defuzzifier in terms of the fuzzy logic controllers approximation error and the average tracing distance, respectively.

Hierarchical Shot Clustering for Video Summarization

Digital video is rapidly becoming a communication medium for education, entertainment, and a variety of multimedia applications. With the size of the video collections growing to thousnads of hours, efficient searching, browsing, and managing video information have become of increasing importance. In this paper, we propose a novel hierarchical shot clustering method for video summarization which can efficiently generate a set of representative shots and provide a quick and efficient access to a large volume of video content. The proposed method is based on the compatibility measure that can represent correlations among shots in a video sequence. Experimental results on real life video sequences show that the resulting summary can retain the essential content of the original video.

A focused crawling for the web resource discovery using a modified proximal support vector machines

With the rapid growth of the World Wide Web, a focused crawling has been increasingly of importance. The goal of the focused crawling is to seek out and collect the pages that are relevant to a predefined set of topics. The determination of the relevance of a page to a specific topic has been addressed as a classification problem. However, when training the classifiers, one can often encounter some difficulties in selecting negative samples. Such difficulties come from the fact that collecting a set of pages relevant to a specific topic is not a classification process by nature. In this paper, we propose a novel focused crawling method using only positive samples to represent a given topic as a form of hyperplane, where we can obtain such representation from a modified Proximal Support Vector Machines. The distance from a page to the hyperplane is used to prioritize the visit order of the page. We demonstrated the performance of the proposed method over the WebKB data set and the Web. The promising results suggest that our proposed method be more effective to the focused crawling problem than the traditional approaches.