Proceedings. IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173)

21-21 June 1998

Filter Results

Displaying Results 1 - 25 of 25
  • Proceedings. IEEE Workshop on Content-Based Access of Image and Video Libraries (Cat. No.98EX173)

    Publication Year: 1998
    Request permission for reuse | PDF file iconPDF (297 KB)
    Freely Available from IEEE
  • On image classification: city vs. landscape

    Publication Year: 1998, Page(s):3 - 8
    Cited by:  Papers (61)  |  Patents (12)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (240 KB)

    Grouping images into semantically meaningful categories using low-level visual features is a challenging and important problem in content-based image retrieval. Based on these groupings, effective indices can be built for an image database. The authors show how a specific high-level classification problem (city vs. landscape classification) can be solved from relatively simple low-level features s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Decoding image semantics using composite region templates

    Publication Year: 1998, Page(s):9 - 13
    Cited by:  Papers (26)  |  Patents (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (281 KB)

    The authors present a method for decoding image semantics using composite region templates (CRTs). The CRTs define prototypal spatial arrangements of regions and features in the images. The system classifies unknown images by matching the strings of regions extracted from the images to the templates in a CRT library. They describe the process for generating the CRTs from photographic images by aut... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning feature relevance and similarity metrics in image databases

    Publication Year: 1998, Page(s):14 - 18
    Cited by:  Papers (19)  |  Patents (21)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (238 KB)

    Most of the current image retrieval systems use "one-shot" queries to a database to retrieve similar images. Typically a K-NN (nearest neighbor) kind of algorithm is used where the weights of the features that are used to represent images remain fixed (or manually tweaked by the user) in the computation of a given similarity metric. However, neither all of the features are equally important for a ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semantic agents for content-based discovery in distributed image libraries

    Publication Year: 1998, Page(s):19 - 23
    Cited by:  Papers (1)  |  Patents (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (173 KB)

    The amount, size, and diversity of multimedia information libraries accessible over the Internet and intranets are continuously increasing. This explosion of information demands content-based network information discovery in order to avoid overloading users with irrelevant information during access. Distributed agent systems promise to be a platform to deliver the scalability and extensibility req... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Combining textual and visual cues for content-based image retrieval on the World Wide Web

    Publication Year: 1998, Page(s):24 - 28
    Cited by:  Papers (86)  |  Patents (39)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (67 KB)

    A system is proposed that combines textual and visual statistics in a single index vector for content-based search of a WWW image database. Textual statistics are captured in vector form using latent semantic indexing (LSI) based on text in the containing HTML document. Visual statistics are captured in vector form using color and orientation histograms. By using an integrated approach, it becomes... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local versus global features for content-based image retrieval

    Publication Year: 1998, Page(s):30 - 34
    Cited by:  Papers (29)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (526 KB)

    It is now recognized in many domains that content-based image retrieval (CBIR) from a database of images cannot be carried out by using completely automated approaches. One such domain is medical radiology for which the clinically useful information in an image typically consists of gray level variations in highly localized regions of the image. Currently, it is not possible to extract these regio... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using weighted spatial relationships in retrieval by visual contents

    Publication Year: 1998, Page(s):35 - 39
    Cited by:  Papers (21)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (176 KB)

    An original modeling technique is presented which enables quantitative representation and comparison of the mutual positioning of a pair of extended regions, and which is able to account for the overall distribution of relationships among the individual pixels belonging to the two regions. Properties of the representation are expounded to develop an efficient computation technique and to motivate ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image database retrieval of rotated objects by user sketch

    Publication Year: 1998, Page(s):40 - 44
    Cited by:  Papers (9)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (433 KB)

    The paper describes the authors' image retrieval system, which enables the user to search a grey-scale image database intuitively by presenting simple sketches. The database contains 120 different isolated objects (mostly hand tools) with arbitrary orientation. Each of these images is represented by a hidden Markov model (HMM) which has been modified in order to obtain rotation and scale invarianc... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Textural features for image database retrieval

    Publication Year: 1998, Page(s):45 - 49
    Cited by:  Papers (25)  |  Patents (20)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (95 KB)

    The paper presents two feature extraction methods and two decision methods to retrieve images having some section in them that is like the user input image. The features used are variances of gray level co-occurrences and line-angle-ratio statistics constituted by a 2D histogram of angles between two intersecting lines and ratio of mean gray levels inside and outside the regions spanned by those a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Categorization of image databases for efficient retrieval using robust mixture decomposition

    Publication Year: 1998, Page(s):50 - 54
    Cited by:  Papers (12)  |  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (575 KB)

    The authors present a robust mixture decomposition technique that automatically finds a compact representation of the data in terms of categories, and apply it to the problem of organizing databases for efficient retrieval. The time taken for retrieval is shown to be an order of magnitude smaller than that of exhaustive search methods. The proposed scheme is tested on images from the VisTex textur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Symmetry-based indexing of image databases

    Publication Year: 1998, Page(s):56 - 62
    Cited by:  Papers (52)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (168 KB)

    The use of shape as a cue for indexing in pictorial databases has been traditionally based on global invariant statistics and deformable templates, on the one hand, and local edge correlation on the other. This paper proposes an intermediate approach based on a characterization of the symmetry in edge maps. The use of symmetry matching as a joint correlation measure between pairs of edge elements ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient access to and retrieval from a shape image database

    Publication Year: 1998, Page(s):63 - 67
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (36 KB)

    Sequential comparison of image visual features, so as to perform similar shape retrieval, is time-consuming and impractical. Access methods that utilize image shape features from different perspectives to narrow down the search space are necessary and essential. We propose a two-stage matching scheme, combining global and local features, to enhance the efficiency of a search operation. In addition... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast wavelet histogram techniques for image indexing

    Publication Year: 1998, Page(s):68 - 72
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (58 KB)

    Image histograms have become very popular in image and video indexing applications because of their low complexity. However, histogram-based techniques are not efficient in retrieving texture images. A histogram technique that exploits the directional properties of a wavelet transform has been proposed in the literature. Although, this technique provides good retrieval performance for texture imag... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Parallel content-based image analysis on PIM processors

    Publication Year: 1998, Page(s):73 - 77
    Cited by:  Patents (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (67 KB)

    We study the problem of retrieving images from a large digital library, by searching the image contents with a specified pattern, using a low cost processing-in-memory (PIM) parallel processor architecture called Shamrock. We consider large databases with images that are rich in details, such as satellite and medical images. For the algorithmic part we focus on Fourier transforms and analyze the t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Percentile blobs for image similarity

    Publication Year: 1998, Page(s):78 - 83
    Cited by:  Papers (10)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (145 KB)

    We present a new algorithm called PBSIM for computing image similarity, based upon a novel method of extracting bloblike features from images. In tests on a classification task using a data set of over 1000 images, PBSIM shows significantly higher accuracy than algorithms based upon color histograms, as well as previously reported results for another approach based upon bloblike features. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling and querying video data: a hybrid approach

    Publication Year: 1998, Page(s):86 - 90
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (98 KB)

    This paper develops a video data model and a rule-based query language for video retrieval. A video sequence is split into a set of fragments. Each fragment can be analyzed to extract the information of interest that can be put into a database. This database can then be searched to find information of interest. Two types of information are considered: the entities (objects) of interest in a video ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient content representation in MPEG video databases

    Publication Year: 1998, Page(s):91 - 95
    Cited by:  Papers (13)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (705 KB)

    In this paper, an efficient video content representation system is presented which permits automatic extraction of a limited number of characteristic frames or scenes that provide sufficient information about the content of an MPEG video sequence. This can be used for reduction of the amount of stored information that is necessary in order to provide search capabilities in a multimedia database, r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ViBE: a new paradigm for video database browsing and search

    Publication Year: 1998, Page(s):96 - 100
    Cited by:  Papers (8)  |  Patents (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (219 KB)

    Video Browsing Environment (ViBE) is a unique browseable/searchable paradigm for organizing video databases containing a large number of sequences. The system first segments video sequences into shots by using the generalized trace obtained from the DC-sequence of the compressed data stream. Each video shot is then represented by a hierarchical tree structure of key frames, and the shots are autom... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiple object labeling in video sequences without skill

    Publication Year: 1998, Page(s):101 - 105
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (207 KB)

    The current trend for integrating media of various forms has treated video sequences as object components. Video processing algorithms which automatically extract objects from video sequences need to be fine-tuned to suit the different video contents. The algorithms themselves, however, tend to be too complicated for multimedia-content editors without skills in video processing. We present a frame... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A perspective view on visual information retrieval systems

    Publication Year: 1998, Page(s):108 - 109
    Cited by:  Papers (1)  |  Patents (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (14 KB)

    Visual information retrieval is a new subject of research in information technology. Its purpose is to retrieve, from a database, images or image sequences that are relevant to a query. It is an extension of traditional information retrieval so to include visual media. Interactivity with visual content is essential to visual information retrieval. Visual elements such as color, texture and object ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Challenges and opportunities in search and retrieval for media databases

    Publication Year: 1998, Page(s):110 - 111
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (255 KB)

    It is obvious that technological advances continue their rapid progress and are making media databases (databases containing not only text and numbers but maps, graphs, images, audio and video) quite feasible. We outline requirements for search and retrieval in media databases and address research challenges needed to solve this challenging problem. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image retrieval evaluation

    Publication Year: 1998, Page(s):112 - 113
    Cited by:  Papers (50)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (81 KB)

    One of the most significant problems in content-based image retrieval results from the lack of a common test-bed for researchers. Although many published articles report on content-based retrieval results using color photographs, there has been little effort in establishing a benchmark set of images and queries. Doing so would have many benefits in advancing the technology and utility of content-b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CBIR in medicine: still a long way to go

    Publication Year: 1998
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (3 KB)

    The application of content-based image retrieval technologies in medicine thus far has not been successful. Existing techniques deal with two-dimensional images and are concerned with searching through generic image features such as color, shape, texture, or a combination of these. For multimedia medical data, application-specific algorithms for feature extraction and better data models must be de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CBIR In Medicine: Still A Long Way To Go

    Publication Year: 1998, Page(s): 115
    Cited by:  Papers (2)
    Request permission for reuse | PDF file iconPDF (67 KB)
    Full text access may be available. Click article title to sign in or learn about subscription options.