Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348)

Volume 2 • 24-28 Oct. 1999

Go

Filter Results

Displaying Results 1 - 25 of 204
  • 1999 Intemational Conference on Image Processing [front matter]

    Publication Year: 1999, Page(s):iii - liv
    Request permission for reuse | PDF file iconPDF (2566 KB)
    Freely Available from IEEE
  • Author index

    Publication Year: 1999, Page(s):lxiii - lxxix
    Request permission for reuse | PDF file iconPDF (1198 KB)
    Freely Available from IEEE
  • Binary and ternary flows for image segmentation

    Publication Year: 1999, Page(s):1 - 5 vol.2
    Cited by:  Papers (12)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (910 KB)

    A novel region-based approach to snakes is introduced in this paper for the segmentation of images composed of two or three types of regions where each region may be distinguished by a given statistic. The basic idea behind this technique is to formulate curve evolutions which separate two or more values of a predetermined set of statistics computed over geometrically determined subsets of the ima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The shape of illusory figures

    Publication Year: 1999, Page(s):6 - 10 vol.2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    We have been developing a stochastic model for figure-ground separation. The model selects/constructs the foreground with preference for figures with “more convex” shapes. When these models are applied to illusory figures they yield perceptually accurate selection of figure and background. The approach is based on an “entropy” measure of a region diffusion Markov model from a set of local figure/g... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Locally homogeneous images as minimizers of objective functions

    Publication Year: 1999, Page(s):11 - 15 vol.2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (632 KB)

    We present a theoretical study of the reconstruction of locally homogeneous images from noisy data, by minimizing regularized objective functions. The latters are composed of a smooth data-fidelity term and a regularizer where a potential function (PF) is applied to each difference between neighbouring pixels. We confine our attention to the reconstruction of images which contain either weakly hom... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the problem of granulometry for a degraded Boolean image model

    Publication Year: 1999, Page(s):16 - 20 vol.2
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (434 KB)

    We consider a geometric coverage process consisting of a random number of disks, or grains, having random radii and positions in the plane. Our objective is granulometry: estimation of a parameter of the disk radius distribution, which is important in diverse applications such bio-assay, ballistics, and numerical taxonomy. These disks are only incompletely observed due to mutual occlusion, spatial... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonlinear diffusion: A probabilistic view

    Publication Year: 1999, Page(s):21 - 25 vol.2
    Cited by:  Papers (6)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (481 KB)

    A probabilistic view of diffusion is presented. A discrete symmetric random walk is shown to be equivalent to a heat equation evolution, and an extension to nonlinear evolutions including Perona-Malik equation is shown to be of utmost importance for analysis. Upon unraveling the limitations as well as the advantages of such an equation, we are able to propose a new approach which is demonstrated t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised progressive parsing of Poisson fields using minimum description length criteria

    Publication Year: 1999, Page(s):26 - 30 vol.2
    Cited by:  Papers (7)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (559 KB)

    This paper describes novel methods for estimating piecewise homogeneous Poisson fields based on minimum description length (MDL) criteria. By adopting a coding-theoretic approach, our methods are able to adapt to the the observed field in an unsupervised manner. We present a parsing scheme based on fixed multiscale trees (binary, for 1D, quad, for 2D) and an adaptive recursive partioning algorithm... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A frequency domain approach to lane detection in roadway images

    Publication Year: 1999, Page(s):31 - 35 vol.2
    Cited by:  Papers (5)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (737 KB)

    This paper introduces a new algorithm for detecting lane markers in images acquired from a forward-looking vehicle-mounted camera. The method is based on a novel set of frequency domain features that capture relevant information concerning the strength and orientation of spatial edges. The frequency domain features are combined with a deformable template prior, in order to detect the lane markers ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two Markov point processes for simulating line networks

    Publication Year: 1999, Page(s):36 - 40 vol.2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (391 KB)

    We investigate two Markov object processes to model line networks. The first one is based on region interactions whereas the interactions of the second one are defined w.r.t. the segment intersection points. We use a Metropolis-Hastings-Green scheme to simulate both models. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Uncertainties in Bayesian geometric models

    Publication Year: 1999, Page(s):41 - 45 vol.2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (779 KB)

    Deformable geometric models fit very naturally into the context of Bayesian analysis. The prior probability of boundary shapes as taken to proportional to the negative exponential of the deformation energy used to control the boundary. This probabilistic interpretation is demonstrated using a Markov-Chain Monte-Carlo (MCMC) technique, which permits one to generate configurations that populate the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rate-distortion motion compensated noise filtering for low bit rate video coding

    Publication Year: 1999, Page(s):46 - 50 vol.2
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (564 KB)

    Noise in video coding applications degrades the image quality and prevents effective compression. In this paper, we define a rate-distortion optimization framework to adapt the response of a motion compensated (MC) temporal noise filter for MC hybrid video coding schemes. We propose a solution based on the Lagrange multiplier method to determine the optimal control parameter set of the filter, and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Improved encoding of DCT coefficients for low bit-rate video coding using multiple VLC tables

    Publication Year: 1999, Page(s):51 - 55 vol.2
    Cited by:  Patents (68)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (410 KB)

    All current video compression standards employ motion compensated prediction and blockwise encoding of the prediction error using the discrete cosine transform (DCT). The DCT coefficients of each block are quantized, re-ordered into a vector, and each zero-run/coefficient pair is encoded as a single symbol, using a variable length code (VLC) table. In this paper, we show that the use of multiple i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using multiple global motion models for improved block-based video coding

    Publication Year: 1999, Page(s):56 - 60 vol.2
    Cited by:  Papers (16)  |  Patents (8)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (504 KB)

    A novel motion representation and estimation scheme is presented that leads to improved coding efficiency of block-based video coders like, e.g., H.263. The proposed scheme is based on motion-compensated prediction from more than one reference frame. The reference pictures are warped or globally motion-compensated versions of the previous frame. Affine motion models are used as warping parameters ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rate-distortion optimized region-based video coder

    Publication Year: 1999, Page(s):61 - 65 vol.2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (946 KB)

    In this paper, we present an efficient region-based video coding scheme. The region partioning is optimized according to a rate-distortion criterion in order to achieve constant bit-rate or constant quality. This optimization is led through a labeling for each image of an initial segmentation map using regions merging, regions' label relaxation and quantization variation. Results obtained show the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Content based very low bit rate video coding using wavelet transform

    Publication Year: 1999, Page(s):66 - 70 vol.2
    Cited by:  Papers (4)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    In this paper we present a new hybrid compression scheme for videoconferencing and videotelephony applications at very low bit rates (i.e., 32 kbits/s). In these applications, human face is the most important region within a frame and should be coded with high fidelity. To preserve perceptually important information at low bit rates, such as face regions, skin-tone is used to detect and adaptively... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Low cost video compression using fast, modified Z-coding of wavelet pyramids

    Publication Year: 1999, Page(s):71 - 75 vol.2
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (461 KB)

    This paper describes a fast, low-complexity, entropy efficient video coder for wavelet pyramids. This coder approaches the entropy-limited coding rate of video wavelet pyramids, is fast in both hardware and software implementations, and has low complexity (no multiplies) for use in ASICs. It consists of a modified Z-coder used to code the zero/non-zero significance function and Huffman coding for ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Very low-bit video coding based on gain-shape VQ and matching pursuits

    Publication Year: 1999, Page(s):76 - 80 vol.2
    Cited by:  Papers (4)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (298 KB)

    We show that the techniques of gain-shape VQ can be used in optimizing the dictionary of the matching pursuit codec. Various performance of our method were evaluated. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive modulus quantizer design for matching pursuit video coding

    Publication Year: 1999, Page(s):81 - 85 vol.2
    Cited by:  Papers (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (532 KB)

    Overcomplete signal decomposition using matching pursuits has been shown to be an efficient technique for coding motion residual images in a hybrid video coder. Unlike orthogonal decomposition where computation of the transform coefficients is decoupled from quantization, matching pursuit uses an in-loop quantizer which must be specified before coding begins. Optimal quantizer design thus depends ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Representation and retrieval of video scene by using object actions and their spatio-temporal relationships

    Publication Year: 1999, Page(s):86 - 90 vol.2
    Cited by:  Papers (2)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (573 KB)

    In this paper we present a method for representing and retrieving video sequences based on the domain-specific behavior of objects present in the scenes. The representation includes three parts: (a) Action description, representing the action performed by a single object. (b) Interaction description, which describes interactions between multiple objects and is mapped directly to the event semantic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Probabilistic analysis and extraction of video content

    Publication Year: 1999, Page(s):91 - 95 vol.2
    Cited by:  Papers (10)  |  Patents (2)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (501 KB)

    In this paper we present a probabilistic framework for mapping low-level visual features into a specific set of semantic descriptors. Specifically, we employ hidden Markov models (HMMs) and Bayesian belief networks (BBNs) at various stages to characterize content domains and extract the relevant semantic information. HMMs are utilized at the shot and sequence levels to model the sequentially-varyi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic caption localization in compressed video

    Publication Year: 1999, Page(s):96 - 100 vol.2
    Cited by:  Papers (7)  |  Patents (3)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (466 KB)

    We present a method to automatically locate captions in MPEG video. Caption text regions are segmented from the background using their distinguishing texture characteristics. This method first locates candidate text regions directly in the DCT compressed domain, and then reconstructs the candidate regions for further refinement in the spatial domain. Therefore, only a small amount of decoding is r... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object-based motion classification

    Publication Year: 1999, Page(s):101 - 105 vol.2
    Cited by:  Papers (1)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (427 KB)

    With the development of object-based video representations such as MPEG-4, object based video manipulations applications become more and more important, such as 2D video scene composition. Semi-automatic algorithms designed to perform that task use meaningful informations about the behavior of the video object in the original sequence. This article proposes a method to split the sequence in tempor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A framework for measuring video similarity and its application to video query by example

    Publication Year: 1999, Page(s):106 - 110 vol.2
    Cited by:  Papers (11)  |  Patents (9)
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (666 KB)

    The usefulness of a video database relies on whether the video of interest can be easily located. To allow exploring, browsing, and retrieving videos according to their visual content, efficient techniques for evaluating the visual similarity between different video clips are necessary. We present a framework for measuring video similarity across different resolutions-both spatial and temporal. In... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Region feature based similarity searching of semantic video objects

    Publication Year: 1999, Page(s):111 - 115 vol.2
    Request permission for reuse | Click to expandAbstract | PDF file iconPDF (469 KB)

    New video representations based on semantic objects (e.g., MPEG-4) provide great potential for content-based video searching. In this paper we present an efficient query model for similarity searching of video objects based on localized region features and spatial-temporal structures. The query model is barred on an existing framework on region-level video query, but addresses several new issues l... View full abstract»

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