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...

This paper provides a comprehensive survey of the technical achievements in the research area of image retrieval, especially content-based image retrieval, an area that has been so active and prosperous in the past few years. The survey includes 100+ papers covering the research aspects of image feature representation and extraction, multidimensional indexing, and system design, three of the fundamental bases of content-based image retrieval. Furthermore, based on the state-of-the-art technology available now and the demand from real-world applications, open research issues are identified and future promising research directions are suggested. C ○ 1999 Academic Press 1.

This paper provides a comprehensive survey of the technical achievements in the research area of Image Retrieval, especially Content-Based Image Retrieval, an area so active and prosperous in the past few years. The survey includes 100+ papers covering the research aspects of image feature representation and extraction, multi-dimensional indexing, and system design, three of the fundamental bases of Content-Based Image Retrieval. Furthermore, based on the state-of-the-art technology available now and the demand from real-world applications, open research issues are identified, and future promising research directions are suggested. 1. INTRODUCTION Recent years have seen a rapid increase of the size of digital image collections. Everyday, both military and civilian equipment generates giga-bytes of images. Huge amount of information is out there. However, we can not access to or make use of the information unless it is organized so as to allow efficient browsing, searching and retriev...

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...

Unlike traditional database management systems, in content-based multimedia retrieval databases, it is difficult for users to express their exact information need directly in a precise query. A typical interface allows users to express their information need using examples of objects similar to the ones they wish to retrieve. Such a user interface, however, requires mechanisms to learn the query representation from the examples. In this paper, we describe the query refinement framework implemented in the Multimedia Analysis and Retrieval System (MARS) for learning query representations using relevance feedback. The proposed framework uses a query expansion approach towards modifying the query representation in which relevant objects are added to the query. Furthermore, query reweighting techniques are used to adjust similarity functions. 1 Introduction Advances in image processing, database management, and information retrieval (IR) have resulted in content-based multimedia retrieva...

The aim of the thesis was to study the use of shape features in content-based image retrieval and to implement shape features to such a system called PicSOM. Because of the internal structure and principles of PicSOM the emphasis was put on such shape feature techniques which can be represented by constant-sized feature vectors and with which the Euclidean distance can be used as a similarity measure. The review covers the best-known shape description techniques which have been published in scientic journals and conference proceedings. Based on the review, some techniques were selected for the...

There is already a huge demand for efficient image indexing and content-based retrieval. With TV going digital, advances in real-time video decompression, easy access to the Internet and the availability of cheap mass storage and fast graphics adaptor cards, digital video will become the next "big " media. Unfortunately, automatic indexing and feature extraction from digital video is even harder than still-image analysis. Presently, automatic analysis of digital video is mostly restricted to automatic detection of scene changes. In this paper we present a framework suitable to immediately explore the consequences of content-based video retrieval with a high granularity of video content. The frameworks employs semantic networks to represent video contents on a high level of abstraction and uses time-varying sensitive regions to link objects in a video to the knowledge base. A prototype was implemented under NEXTSTEP, exploiting the rich user-interface capabilities of this platform to feature drag & drop queries and authoring of the video retrieval system.

Content-based retrieval of three-dimensional scalar data is increasingly necessary as on-line repositories of data volumes continue to grow. This paper describes preliminary work in retrieving and displaying scalar volumetric data via web-browser user interfaces. An HTML-based web-browser is used to construct queries based on user-specified textual keywords and a voxel value histogram. Shape-based query handling is in development. Pre-rendered images of volumes matching the user's query are displayed and the user picks one of these to select a volume for further study. The selected volume is isosurfaced "on-the-fly", according to the user-supplied threshold value, and the resulting geometry is loaded into a VRML-based web-browser for interactive exploration and analysis. The system described here is being used as a platform for further research in content-based retrieval algorithms for volumetric data. 1 Introduction 1.1 Information flood In the past, humans were the sole source of o...

In content-based image retrieval (CBIR), content of an image can be expressed in terms of different features such as color, texture, shape, or text annotations. Retrieval based on these features can be various by the way how to combine the feature values. Most of the existing approaches assume a linear relationship between different features, and the usefulness of such systems was limited due to the difficulty in representing high-level concepts using lowlevel features. In this paper, we introduce Neural Network-based Flexible Image Retrieval (NNFIR) system, a humancomputer interaction approach to CBIR using Radial Basis Function (RBF) network to combine the values of the heterogeneous features. By using the RBF network, this approach determines nonlinear relationship between features so that more accurate similarity comparison between images can be supported. The experimental results show that the proposed approach captures the user's perception subjectivity more precisely using the dynamically updated weights. 1.

We propose a system that employs low-level image segmentation followed by color and 2-D shape matching to automatically group those low-level segments into objects based on their similarity to a set of example object templates presented by the user. A hierarchical content tree data structure is used for each database image to store matching combinations of low-level regions as objects. The system automatically initializes the content tree with only "elementary nodes" representing homogeneous low-level regions. The "learning" phase refers to labeling of combinations of lowlevel regions that have resulted in successful color and/or 2-D shape matches with the example template(s). These combinations are labeled as "object nodes" in the hierarchical content tree. Once learning is performed, the speed of second-time retrieval of learned objects in the database increases significantly. The learning step can be performed off-line provided that example objects are given in the form of user interest profiles. Experimental results are presented to demonstrate the effectiveness of the proposed system with hierarchical content tree representation and learning by color and 2-D shape matching on collections of car and face images.