By Topic

Proceedings of 3rd IEEE International Conference on Image Processing

19-19 Sept. 1996

Go

Filter Results

Displaying Results 1 - 25 of 263
  • International Conference on Image Processing

    Publication Year: 1996, Page(s):iii - xlv
    Request permission for commercial reuse | PDF file iconPDF (2536 KB)
    Freely Available from IEEE
  • New subband geometries for image texture segmentation

    Publication Year: 1996, Page(s):971 - 974 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (626 KB)

    The usefulness of multichannel filtering for image texture segmentation has been demonstrated in the literature. Based on psychophysical studies, it has been largely believed that Gabor filters are optimal for segmentation. In this paper, the application of maximally decimated, non-separable, perfect reconstruction filter banks (subband systems) are investigated for texture segmentation. The subba... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Symmetry and locality: uncertainty revisited

    Publication Year: 1996, Page(s):207 - 210 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (344 KB)

    The purpose of this paper is to explore the relationship between symmetry and locality-properties which are regarded as desirable in any image representation and which are frequently mentioned in connection with wavelet transforms. It is shown how the two conspire to cause uncertainty; a new form of the uncertainty principle is introduced and a novel window design technique presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rotational symmetry: the Lie group SO(3) and its representations

    Publication Year: 1996, Page(s):203 - 206 vol.3
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    The paper describes iterative algorithms to normalize coefficient vectors computed by expanding functions on the unit sphere into a series of surface harmonics. Typical applications of the normalization procedure are the matching of different three-dimensional images, orientation estimations in low-level image processing or robotics. The method uses general methods from the theory of Lie-groups an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-step motion estimation algorithm using low-resolution quantization

    Publication Year: 1996, Page(s):795 - 798 vol.3
    Cited by:  Papers (1)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    We propose a new motion estimation algorithm using low-resolution quantization. The proposed algorithm reduces both performance degradation and computational cost by matching at every search position with a low bit resolution image. It consists of two steps: the low resolution search that generates the candidate motion vectors and the full-resolution search that finds the best motion vector in the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coordinate transformations, symmetries, and GHT

    Publication Year: 1996, Page(s):197 - 201 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1024 KB)

    A conjugate harmonic function pair is a suitable curvi-linear coordinate pair with which image iso-gray curves can be described. In this representation, images or parts of images which are symmetric with respect to such a function pair, have iso-gray curves which are lines or parallel line patterns. Detecting these lines, or generalized linear symmetry fitting as it will be called, corresponds to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • `Pencigraphy' with AGC: joint parameter estimation in both domain and range of functions in same orbit of the projective-Wyckoff group

    Publication Year: 1996, Page(s):193 - 196 vol.3
    Cited by:  Papers (20)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (668 KB)

    Consider a static scene and fixed center of projection, about which a camera is free to zoom, pan, tilt, and rotate about its optical axis. With an ideal camera, the resulting images are in the same orbit of the projective group-action, and each pixel of each image provides a measurement of a ray of light passing through a common point-in space. Unfortunately, most modern cameras have a built in a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Compression of vector quantization code sequences based on code frequencies and spatial redundancies

    Publication Year: 1996, Page(s):463 - 466 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (404 KB)

    Vector quantization (VQ) can be used to compress images with high compression ratios. The VQ methods produce a sequence of code values which identifies the codebook model vectors to be used as blocks of pixels in the decoded image. In this paper we define a novel non-lossy and computationally efficient method to further compress the code sequence based on the relative frequencies of the code value... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local color and texture extraction and spatial query

    Publication Year: 1996, Page(s):1011 - 1014 vol.3
    Cited by:  Papers (17)  |  Patents (12)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (424 KB)

    In this paper we present a unified system for the extraction, representation and query of spatially localized color and texture regions. The system utilizes a back-projection of binary feature sets to identify and extract prominent regions. The binary feature sets provide an effective and easily indexable representation of color and texture. We also provide a mechanism for integrating features by ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optical flow recognition from the power spectrum of a single blurred image

    Publication Year: 1996, Page(s):791 - 794 vol.3
    Cited by:  Papers (18)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB)

    In this paper a new technique for calculation of the optical flow is presented. When there is motion in the observed scene, an image taken will be motion blurred (to a degree depending on the exposure time). Up to now most of the algorithms for estimating the motion in a scene ignored motion blur and treated it as noise. On the contrary, motion blur is structured information and in certain cases c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion characterization of unrigid objects by detecting and tracking feature points

    Publication Year: 1996, Page(s):803 - 806 vol.3
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (532 KB)

    A new algorithm to determine the motion of unnrigid objects like smoke clouds is presented. It consists of two parts. The first one is the localisation of edges and feature points along them. The wavelet transform is used for each of these localisations. The determination of feature points is done through the characterisation of a quantity related to Lipschitz exponents. The second part is the tra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Template-based image retrieval

    Publication Year: 1996, Page(s):871 - 874 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (568 KB)

    A classified hierarchical template matching algorithm is presented in this work. In our system, a template is first classified into one of three classes: texture, edge and low-activity. Then different features are used for each class, thereby achieving a better recognition rate than with the commonly used l2 metric. Furthermore, a two-level hierarchical searching algorithm is designed t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic flow control planning for real-time image processing devices

    Publication Year: 1996, Page(s):643 - 646 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    High performance vision systems have a complex architecture which makes them difficult to program. The objective of the ARVISA (Advanced Real-time VIsion System Architecture) project was to facilitate the programming of such systems by providing an integrated application development environment. Its central component is the automatic flow control planner (FCP). Using the FCP, image processing algo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image representation based on the affine symmetry group

    Publication Year: 1996, Page(s):189 - 192 vol.3
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB)

    The representation of 2-D signals which are symmetric under the affine group of transformations is considered. An extension of the multiresolution Fourier transform (MFT) is presented and shown to have a predictable redistribution of energy as a result of affine transformations of the input signal. An approximation based on the discrete MFT then forms the basis of a computationally efficient algor... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion-based segmentation and tracking of dynamic radar clutters

    Publication Year: 1996, Page(s):923 - 926 vol.3
    Cited by:  Papers (4)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    The aim of this study is to perform a classification and a short term spatial estimation of radar clutter. Motion-based segmentation allows one to part clutter into two sets: the static ones and the dynamic ones. A spatial segmentation can then be processed, using Doppler data, in order to obtain homogeneous clutter. The dynamic clutter can be tracked by means of adaptive algorithms based on new t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3-D analysis of textures using structural information

    Publication Year: 1996, Page(s):161 - 164 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (420 KB)

    This paper presents a new algorithm that obtains the surface orientation of the texture image using structural approaches. The proposed method showed that structural approaches can be effectively used in 3-D analysis of textures as well as description and segmentation. By examining the Fourier power spectrum of the texture image, we determine the tilt of the textured surface. Then, 1-D projection ... View full abstract»

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

    Publication Year: 1996, Page(s):699 - 702 vol.3
    Cited by:  Papers (23)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (616 KB)

    A digital image processing system has been developed to quantify and monitor the presence of microaneurysms in retinal fluorescein angiograms. The system is fully automated (except for the initial digitisation), and includes stages for preprocessing, registration of same-eye images obtained at different visits, fovea detection for placement of regions-of-interest, and detection of microaneurysms a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A modular neural network vector predictor for predictive VQ

    Publication Year: 1996, Page(s):431 - 434 vol.3
    Cited by:  Papers (4)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1320 KB)

    In this paper, we present a modular neural network vector predictor in order to improve the predictive component of a predictive vector quantization (PVQ) scheme. The proposed vector prediction technique consists of five dedicated predictors (experts), where each expert predictor is optimized for a particular class of input vectors. An input vector is classified into one of five classes based on i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Extraction of TV news articles based on scene cut detection using DCT clustering

    Publication Year: 1996, Page(s):847 - 850 vol.3
    Cited by:  Papers (9)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (396 KB)

    This paper describes a system which can automatically separate and extract articles included in TV news program. At first, the system detects scene cut points based on clustering of video frames compressed by discrete cosine transformation (DCT). This clustering technique is robust for abrupt changes caused by camera flushing. Then, on the detected scene cut points, the main studio frame is estima... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Development of motion analysis system for quantitative evaluation of teamwork in soccer games

    Publication Year: 1996, Page(s):815 - 818 vol.3
    Cited by:  Papers (23)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (948 KB)

    We present a motion analysis system of soccer games. The purpose of this system is to evaluate the teamwork quantitatively based on the movement of all the players in a game. Space management and cooperative movement by the players are two major factors for teamwork evaluation. To quantify them from motion images, we propose two new features; “minimum moving time pattern” and “do... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient spatio-temporal decomposition for perceptual processing of video sequences

    Publication Year: 1996, Page(s):331 - 334 vol.3
    Cited by:  Papers (16)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (400 KB)

    This paper presents a vision model for moving pictures. The model is an extension of a normalization model by Teo and Heeger (1994). It accounts for normalization of the cortical receptive field responses and inter-channel masking. The model is compared with a simpler vision model for video by presenting results on quality assessment of MPEG compressed video View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contour segmentation using Hough transform

    Publication Year: 1996, Page(s):583 - 586 vol.3
    Cited by:  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (384 KB)

    In many 2D situations, contours can be efficiently represented as line segments or short circle arcs sequences. Therefore, we propose an original use of the Hough transform for detecting such primitives. Rather than searching directly for circle arcs, we have chosen to use the Hough transform for evaluating the relevance of each edge point and the curvature center associated with it. A specific pa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive learning vector quantizers for image compression

    Publication Year: 1996, Page(s):459 - 462 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (316 KB)

    We investigate adaptive vector quantization for image compression based the idea of gold-washing. The technique is a mechanism for testing the usefulness of a code vector in a codebook. It thus provides a tool for developing new ways of creating code vectors dynamically based on the input data. In this paper, we propose a new algorithm to quantize an input for which a close enough code vector can ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Static tomographic reconstruction of the time varying ionosphere

    Publication Year: 1996, Page(s):523 - 526 vol.3
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (412 KB)

    An image of electron density in a vertical slice through the ionosphere can be created using tomographic techniques. An ionospheric tomography system consists of a satellite and several ground stations. Ionospheric electron density can change significantly during the time it takes to collect enough data for one image. In many other applications of tomography, motion of an object in the source imag... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A watermark for digital images

    Publication Year: 1996, Page(s):219 - 222 vol.3
    Cited by:  Papers (154)  |  Patents (59)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    The growth of networked multimedia systems has magnified the need for image copyright protection. One approach used to address this problem is to add an invisible structure to an image that can be used to seal or mark it. These structures are known as digital watermarks. We describe two techniques for the invisible marking of images. We analyze the robustness of the watermarks with respect to line... View full abstract»

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