By Topic

IEE Proceedings - Vision, Image and Signal Processing

Issue 3 • 20 June 2003

Filter Results

Displaying Results 1 - 9 of 9
  • Combining static and dynamic features using neural networks and edge fusion for video object extraction

    Publication Year: 2003, Page(s):160 - 167
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (911 KB)

    Semantic object representation is an important step for digital multimedia applications such as object-based coding, content-based access and manipulations. The authors propose an image sequence segmentation scheme which provides region information for the semantic object representation of those applications. The objective is to develop a hardware-friendly segmentation algorithm by combining stati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Continuous restricted Boltzmann machine with an implementable training algorithm

    Publication Year: 2003, Page(s):153 - 158
    Cited by:  Papers (33)  |  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (649 KB)

    The authors introduce a continuous stochastic generative model that can model continuous data, with a simple and reliable training algorithm. The architecture is a continuous restricted Boltzmann machine, with one step of Gibbs sampling, to minimise contrastive divergence, replacing a time-consuming relaxation search. With a small approximation, the training algorithm requires only addition and mu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture-based image indexing in the process of lossless data compression

    Publication Year: 2003, Page(s):198 - 204
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (786 KB)

    The authors describe a new approach for content-based image indexing and retrieval by extracting texture features from the process of image compression via JPEG-LS. Since the compression technique adopted incorporates local edge detection to formulate predictive values for pixels being encoded, the texture features extracted by the proposed algorithms are also capable of describing image content i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Inertia-based video cut detection and its integration with video coder

    Publication Year: 2003, Page(s):186 - 192
    Cited by:  Patents (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (733 KB)

    An encoder-dependent video cut detection algorithm is proposed. Based on the inertia property of natural videos, the proposed algorithm detects video cuts in the video-coding loop by making use of the intermediate results of video compression. Experiments show that the detection performance of the proposed algorithm is quite good as compared to previous works, and when it is integrated with the co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unified approach for constructing multiwavelets with approximation order using refinable super-functions

    Publication Year: 2003, Page(s):143 - 152
    Cited by:  Papers (2)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (738 KB)

    A unified approach for constructing a large class of multiwavelets is presented. This class includes Geronimo-Hardin-Massopust (1994), Alpert (1993), finite element and Daubechies-like multiwavelets. The approach is based on the characterisation of approximation order of r multiscaling functions using a known compactly supported refinable super-function. The characterisation is formulated as a gen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive filtering approaches for colour image and video restoration

    Publication Year: 2003, Page(s):168 - 177
    Cited by:  Papers (3)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (973 KB)

    An adaptive simplified model Kalman filter (ASMKF) is developed for image and video impulsive noise suppression. The ASMKF is more effective than the median filter (MF) and the robust reduced update Kalman filter (RRUKF) in suppressing the impulsive noise, especially when the signal-to-noise ratio is low. Further, a hybrid filter is presented for colour image and video restoration in a mixed noise... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum likelihood based framework for second-level adaptive prediction

    Publication Year: 2003, Page(s):193 - 197
    Cited by:  Papers (1)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (565 KB)

    A study is presented of a maximum likelihood based framework for second-level adaptive prediction which is formed from a group of predictors. It is a natural extension to first-level prediction which is formed directly from a group of pixels. The proposed framework offers a greater degree of freedom for adaptation and tackles the problem of model uncertainty that is inherent in first-level predict... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image detail-preserving filter for impulsive noise attenuation

    Publication Year: 2003, Page(s):179 - 185
    Cited by:  Papers (12)
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (1982 KB)

    A new nonlinear filter is proposed for attenuating impulsive noise while preserving image details. The filter truncates the grey value of a pixel to the maximal or minimal value of its enclosed surrounding band. Impulsive noise inside the band is thus attenuated while image details are preserved as long as they stretch to the band. The recursive form of the proposed filter leads to a simple archit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Relationship between an LPTV system and the equivalent LTI MIMO structure

    Publication Year: 2003, Page(s):133 - 141
    IEEE is not the copyright holder of this material | Click to expandAbstract | PDF file iconPDF (739 KB)

    It is understood how to transform a linear periodically time-varying (LPTV) filter/ difference equation into an equivalent multiple-input/multiple-output (MIMO) structure, or transfer matrix, with linear time-invariant (LTI) elements, but no published method exists for the reverse operation. The paper presents a technique to transform from the LTI MIMO structure to the original single-input/single... View full abstract»

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