Content-Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these research efforts establish the basis of CBIR, the usefulness of the proposed approaches is limited. Specifically, these efforts have relatively ignored two distinct characteristics of CBIR systems: (1) the gap between high level concepts and low level features; (2) subjectivity of human perception of visual content. This paper proposes a relevance feedback based interactive retrieval approach, which effectively takes into account the above two characteristics in CBIR. During the retrieval process, the user's high level query and perception subjectivity are captured by dynamically updated weights based on the user's feedback. The experimental results over more than 70,000 images show that the proposed approach greatly reduces the user's effort of composing a query and captures the user's i...

Content-Based Image Retrieval (CBIR) has become one of the most active research areas in the past few years. Many visual feature representations have been explored and many systems built. While these research efforts establish the basis of CBIR, the usefulness of the proposed approaches is limited. Specifically, these e#orts have relatively ignored two distinct characteristics of CBIR systems: (1) the gap between high level concepts and low level features; (2) subjectivity of human perception of visual content. This paper proposes a relevance feedback based interactive retrieval approach, which effectively takes into account the above two characteristics in CBIR. During the retrieval process, the user's high level query and perception subjectivity are captured by dynamically updated weights based on the user's relevance feedback. The experimental results show that the proposed approach greatly reduces the user's effort of composing a query and captures the user's information need more precise...

To address the emerging needs of applications that require access to and retrieval of multimedia objects, we are developing the Multimedia Analysis and Retrieval System (MARS) [29]. In this paper, we concentrate on the retrieval subsystem of MARS and its support for content-based queries over image databases. Content-based retrieval techniques have been extensively studied for textual documents in the area of automatic information retrieval [40, 4]. This paper describes how these techniques can be adapted for ranked retrieval over image databases. Specifically, we discuss the ranking and retrieval algorithms developed in MARS based on the Boolean retrieval model and describe the results of our experiments that demonstrate the effectiveness of the developed model for image retrieval.

The tremendous growth in digital imagery is driving the need for more sophisticated methods for automatic image analysis, cataloging, and searching. We present a method for classifying and querying images based on the spatial orderings of regions or objects using composite region templates (CRTs). The CRTs capture the spatial information statistically and provide a robust way to measure similarity in the presence of region insertions, deletions, substitutions, replications and relocations. The CRTs can be used for classifying and annotating images by assigning symbols to the regions or objects and by extracting symbol strings from spatial scans of the images. The symbol strings can be decoded using a library of annotated CRTs to automatically label and classify the images. The CRTs can also be used for searching bysketch or example by measuring image similarity based on relative counts of the CRTs.

We conjecture that texture can be characterized by the statistics of the wavelet detail coefficients and therefore introduce 2 feature sets: 1) the wavelet histogram signatures which capture all first order statistics using a model based approach; 2) the wavelet cooccurrence signatures, which reflect the coefficients' second order statistics. The introduced feature sets outperform the traditionally used energy. Best performance is achieved by combining histogram and cooccurrence signatures.

While there are many textual and image retrieval systems, few have explored the granularity of the retrieval unit and the use of all available information for retrieval. This paper presents our work on using textual and image retrieval, fusing the results and providing document retrieval that uses visual and textual information from documents. A query refinement technique is also shown that blurs the line between browsing and searching and integrates both into the same framework.

With the expansion of the Internet, searching for information goes beyond the boundary of physical libraries. Millions of documents of various media types, suchas text, image, video, audio, graphics, and animation, are available around the world and linked by the Internet. Unfortunately, the state of the art of search engines for media types other than text lags far behind their text counterparts. To address this situation, wehave developed the Multimedia Analysis and Retrieval System #MARS#. This paper reports some of the progress made over the years towards exploring information retrieval beyond the text domain. In particular, the following aspects of MARS are addressed in the paper: visual feature extraction, retrieval models, query reformulation techniques, e#cient execution speed performance and user interface considerations. Extensive experimental results are reported to validate the proposed approaches. 1 Introduction Huge amounts of digital data are being generated...

This document reports on an implementation of MARS towards the exploration of Information Retrieval (IR) beyond the text domain; an implementation of an extensible image and text retrieval system and its application to a World Wide Web based multimedia search engine called WebMARS. WebMARS augments MARS by exploiting the vast amounts of web pages on the World Wide Web to obtain documents containing both textual and visual objects. User access to WebMARS is also provided through the World Wide Web. The system is implemented following a client server...

With advances in the computer technologies and the advent of the World Wide Web, there has been an explosion in the amount and complexity of digital data being generated, stored, transmitted, analyzed, and accessed. Much of this information is multimedia in nature, including digital images, video, audio, graphics, and text data. In order to make use of this vast amount of data, efficient and effectivetechniques to analyze and retrievemultimedia information based on its content need to be developed.