Showing papers on "Content-based image retrieval published in 1995"

Content based image retrieval systems

Abstract: Images are being generated at an ever-increasing rate by sources such as defence and civilian satellites, military reconnaissance and surveillance flights, fingerprinting and mug-shot-capturing devices, scientific experiments, biomedical imaging, and home entertainment systems. For example, NASA's Earth Observing System will generate about 1 terabyte of image data per day when fully operational. A content-based image retrieval (CBIR) system is required to effectively and efficiently use information from these image repositories. Such a system helps users (even those unfamiliar with the database) retrieve relevant images based on their contents. Application areas in which CBIR is a principal activity are numerous and diverse. With the recent interest in multimedia systems, CBIR has attracted the attention of researchers across several disciplines. >

An integrated color-spatial approach to content-based image retrieval

Abstract: The use of color information for image retrieval has been used widely in many content-based retrieval system with some success. However, histogram-based color retrieval techniques su er from a lack of important spatial knowledge. We discuss a technique of integrating color information with spatial knowledge to obtain an overall impression of the image. The technique involves three steps: the selection of a set of representative colors, the analysis of spatial information of the selected colors, and the retrieval process based on the integrated color-spatial information. Two color histograms are used to aid in the process of color selection. After deriving the set of representative colors, spatial knowledge of the selected colors is obtained using a maximum entropy discretization with event covering method. A retrieval process is formulated to make use of the spatial knowledge to retrieve relevant images. A prototype image retrieval system has been implemented on the Unix system. It is tested on an image database consisting of 260 images. The result shows substantial improvement over the histogram-based color retrieval methods.

Scheme for visual feature-based image indexing

Abstract: As digital images are progressing into the mainstream of information systems, managing and manipulating them as images becomes an important issue to be resolved before we can take full advantage of their information content. To achieve content-based image indexing and retrieval, there are active research efforts in developing techniques to utilize visual features. On the other hand, without an effective indexing scheme, any visual content based image retrieval approach will lose its effectiveness as the number of features increases. This paper presents our initial work in developing an efficient indexing scheme using artificial neural network, which focuses on eliminating unlikely candidates rather than pin-pointing the targets directly. Experiment results in retrieving images using this scheme from a prototype visual database system are given.

Color indexing for efficient image retrieval

Abstract: Content based image retrieval is an active area of research. Many approaches have been proposed to retrieve images based on matching of some features derived from the image content. Color is an important feature of image content. The problem with many traditional matching-based retrieval methods is that the search time for retrieving similar images for a given query image increases linearly with the size of the image database. We present an efficient color indexing scheme for similarity-based retrieval which has a search time that increases logarithmically with the database size.

Efficient content-based image retrieval using automatic feature selection

Abstract: We describe a self-organizing framework for content-based retrieval of images from large image databases at the object recognition level. The system uses the theories of optimal projection for optimal feature selection and a hierarchical image database for rapid retrieval rates. We demonstrate the query technique on a large database of widely varying real-world objects in natural settings, and show the applicability of the approach even for large variability within a particular object class.

Content-based image retrieval using multiresolution histogram representation

Abstract: We present two new approaches based on color histogram indexing for content-based retrieval of image databases. Since the high computational complexity has been one of the main barriers towards the use of similarity measures such as histogram intersection in large databases, we propose a hierarchical indexing scheme where computationally efficient features are used to subset the image before more sophisticated techniques are applied for precise retrieval. The use of histograms at different color resolutions as filtering and matching features in a hierarchical scheme is studied. In the second approach, a multiresolution representation of the histogram using the indices and signs of its largest wavelet coefficients is examined. Excellent results have been observed using the latter method.

Content-based image retrieval: color and edges

Abstract: One of the tools that will be essential for future electronic publishing is a powerful image retrieval system. The author should be able to search an image database for images that convey the desired information or mood; a reader should be able to search a corpus of published work for images that are relevant to his or her needs. Most commercial image retrieval systems associate keywords or text with each image and require the user to enter a keyword or textual description of the desired image. This text-based approach has numerous drawbacks -- associating keywords or text with each image is a tedious task; some image features may not be mentioned in the textual description; some features are ``nearly impossible to describe with text''''; and some features can be described in widely different ways [Niblack, 1993]. In an effort to overcome these problems and improve retrieval performance, researchers have focused more and more on content-based image retrieval in which retrieval is accomplished by comparing image features directly rather than textual descriptions of the image features. Features that are commonly used in content-based retrieval include color, shape, texture and edges. In this report we describe a simple content-based system that retrieves color images on the basis of their color distributions and edge characteristics. The system uses two retrieval techniques that have been described in the literature -- i.e. histogram intersection to compare color distributions and sketch comparison to compare edge characteristics. The performance of the system is evaluated and various extensions to the existing techniques are proposed.

Content-based image retrieval systems (panel)

Abstract: Image Retrieval (IR) problem is concerned with retrieving images that are relevant to users’ requests from a large collection of images, referred to as the image database. A software system that facilitates image retrieval is referred to as the Image Retrieval System (IRS). Previous approaches to the IR problem have been in one of the two directions. In the first direction, image contents are modeled as image attributes. Attributes are extracted manually from the images and are managed within the framework of conventional database systems. The second approach emphasizes the importance of an object recognition system as an integral part of the IRS to overcome the limitations of attribute based retrieval. However, object recognition is a computationally expensive task and renders the approach unsuitable for even the moderate size image databases. Furthermore, IR systems based on this approach tend to be domain-specific. The recent emergence of ubiquitous interest in Multimedia Information Systems has brought the IR problem to the attention of many researchers across several disciplines. Much of this recent research focuses on bridging the gap between the previous two approaches to the problem. The primary emphasis has been on developing domain-independent IRS that provide the ability to retrieve images based on their contents without the need for performing the object recognition task at the query processing time. These efforts have culminated in the introduction of novel image representations and image data models, query processing algorithms for content-based image retrieval, intelligent query languages/interfaces, tools for image database design, and domainindependent system architectures for the IRS. IR Systems that make use of these recent advances are just beginning to appear. Therefore, the theme of the proposed panel is to set up a forum to bring together researchers, developers, and practitioners to explore and discuss various issues concerning the evolving theory, design and development of Content-based Image Retrieval Systems.

Fixed-window image descriptors for image retrieval

Abstract: We work towards a content-based image retrieval system, where queries can be image-like objects. At entry time, each image is processed to yield a large number of indices into its windows. A window is a square in a fixed quad-tree decomposition of the image, and an index is a fixed-size vector, called a descriptor, similar to the periodograms used in spectral estimation. The fixed decomposition of images was prompted by the need for fast processing, but leads to windows that often straddle image regions with different textural contents, making indices less effective. In this paper, we investigate different definitions of spectral distance which we plan to use to classify windows according to their texture content.

Content-based image retrieval

Abstract: In order to retrieve images it is much more sophisticated and usual for human beings to use natural language concepts, e.g. mountainlake, than syntactical features, e.g. red region left up. This leads to a content-based image retrieval. Furthermore, it is unreasonable for any human being to make the content description for 1000 of images manually.From this point of view, the project IRIS1 (Image Retrieval for Information Systems) combines well-known methods and techniques in computer vision and AI in a new way to generate content descriptions of images in a textual form automatically. The text retrieval is done by IBM SearchManager for AIX.The system is implemented on IBM2 RISC Sytem/60003 using AIX4. It has already been tested with 1200 images.

Feature identification as an aid to content-based image retrieval

Abstract: In recent years, databases have evolved from storing pure textual information to storing multimedia information -- text, audio, video, and images. With such databases comes the need for a richer set of search keys that include keywords, shapes, sounds, examples, sketches, color, texture and motion. In this paper we address the problem of image retrieval where keys are object shapes or user sketches. In our scheme, shape features are extracted from each image as it is stored. The image is first segmented and points of high curvature are extracted. Regions surrounding the points of high curvature are used to compute feature values by comparing the regions with a number of references. The references themselves are picked out from the set of orthonormal wavelet basis vectors. An ordered set of distance measures between each local region and the wavelet references form a feature vector. When a user queries the database through a sketch, the feature vectors for high curvature points on the sketch are determined. An efficient nearest neighbor search then yields a set of images which contain objects that match the user's sketch closely. The process is completely automated. Initial experimental results are presented.

Modeling complex objects in content-based image retrieval

Abstract: This paper describes the extended model for information retrieval (EMIR) designed for complex information description and retrieval and particularly well suited for image modeling. A main object in the proposed model has a three parts specification: a description that is a list of attributes; a composition that is a list of component objects; and a topology that is a list of semantic relationships between component objects, expressing more semantic aspects of the main object structure. The model is well suited for image modeling for two complementary reasons. On one hand, it can distinguish between an object structure and its contents. This is achieved by relaxing the class-object classical instantiation link; thus allowing objects to have individual non categorized contents rather than those predicted in their classes. On the other hand, images have typically very different individual contents, and, therefore, cannot be easily modeled within a structured database model such as the relational model. The query language is organized according to the three-part organization of the model. A simple query has three parts: description, being some constraints on some attributes values; composition, being a set of sub-queries on the composition part of objects; topology, being the specification of special required links on the results of composition sub-queries.

Distributed adaptive attribute-based image retrieval

Abstract: In this paper, we describe a prototype system, named DAIRS, for distributed image retrieval. DAIRS features adaptive query reformulation mechanism for improving the retrieval effectiveness. The query reformulation mechanism is based on the calculation of the functional dependency between each image attribute and the user's relevance feedback. The importance (or weight) of each attribute is modified in the reformulated query based on the degree of such functional dependency. Since image servers are dynamically evolving in a distributed environment, DAIRS has been designed to deal with image databases in various domains distributed in the Internet. The DAIRS communication protocol is designed to cooperate with http and ftp, so that the client can easily access the distributed image repositories. Experimental results show that the query reformulation mechanism significantly improves the retrieval effectiveness.© (1995) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Content-Based Image Retrieval

Abstract: As more and more image data are acquired and assume the role of “first-class citizens” in information technology, managing and manipulating them as images becomes an important issue to be resolved before we can take full advantage of their information content [CH92]. Image database and visual information system technologies have become major efforts to address this issue, and a variety of commercial systems are now available to accommodate different sizes of image resources, different computational platforms, and different commitments to investment. These systems have been used in an equally wide variety of applications, including medical image management, multimedia libraries, document archives, museums, transaction systems, computer-aided design and manufacturing (CAD/CAM) systems, geographic information systems, and criminal identification.

Content-based image retrieval and its benefits for the stock photography market

Abstract: The development of powerful low-cost desktop computer systems has changed the pre-press business where tight deadlines must be met persistently. An increasing number of newspapers and magazines are acquiring, handling, and storing images digitally while the use of hardcopies and slides decreases. Today's computers and high capacity storage-media enable stock photography agencies to build digital image databases, giving users fast access to large numbers of images. However, the transition from analog to digital image archives imposes new problems: with thousands of images at hand, the search for a particular image may turn into the search for the needle in a haystack. The first image Database Management Systems (DBMSs) were extended text DBMSs, which stored the image data along with a set of manually entered descriptive keywords. The major problem with this approach is that there is no generally agreed-upon language to describe images. Even sophisticated DBMSs are unable to detect synonyms; hence, an image described with certain properties such as "curvy" may not be found if a user enters