Proceedings 10th International Conference on Image Analysis and Processing

27-29 Sept. 1999

Filter Results

Displaying Results 1 - 25 of 210
  • Proceedings 10th International Conference on Image Analysis and Processing

    Publication Year: 1999
    Request permission for commercial reuse | PDF file iconPDF (680 KB)
    Freely Available from IEEE
  • The laminar architecture of visual cortex and image processing technology

    Publication Year: 1999, Page(s):2 - 9
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (101 KB)

    The mammalian neocortex is organized into layers which include circuits that form functional columns in cortical maps. A major unsolved problem concerns how bottom-up, top-down, and horizontal interactions are organized within cortical layers to generate adaptive behaviors. This article summarizes a model, called the LAMINART model, of how these interactions help the visual cortex to realize: (1) ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A figure extraction method based on the color and texture contrasts of regions

    Publication Year: 1999, Page(s):12 - 17
    Cited by:  Papers (5)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (516 KB)

    Detecting interesting regions from pictures has become important in order to reduce the computational complexity associated with such time-consuming processes as object recognition. In this paper we assume that figure-ground segmentation of a picture is necessary as the first step towards evaluating the attractiveness of regions. In vision research, it has been found that the V4 cortex in the visu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Representing and recognizing visual dynamic events with support vector machines

    Publication Year: 1999, Page(s):18 - 23
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (167 KB)

    Support vector machines (SVM) have been recently introduced as techniques for solving pattern recognition and regression estimation problems. SVM are derived within the framework of statistical learning theory and combine a solid theoretical foundation with very good performances in several applications. In this paper we describe a system able to detect, represent, and recognize visual dynamic eve... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Distinctiveness maps for image matching

    Publication Year: 1999, Page(s):26 - 31
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (265 KB)

    Stereo correspondence is hard because different image features can look alike. We propose a measure for the ambiguity of image points that allows matching of distinctive points first and breaks down the matching task into smaller and separate subproblems. Experiments with an algorithm based on this measure demonstrate the ensuing efficiency and low likelihood of incorrect matches. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiresolution object-of-interest detection for images with low depth of field

    Publication Year: 1999, Page(s):32 - 37
    Cited by:  Papers (4)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (203 KB)

    This paper describes a novel multiresolution image segmentation algorithm for separating sharply focused objects-of-interest from other foreground or background objects in low depth-of-field (DOF) images, such as sports, telephoto, macro, and microscopic images. The algorithm takes a multiscale context-dependent approach to segment images based on features extracted from wavelet coefficients in hi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Permanence-based shape decomposition in binary pyramids

    Publication Year: 1999, Page(s):38 - 43
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (76 KB)

    An algorithm to decompose hierarchically bidimensional patterns is introduced. The single-scale input pattern is first transformed into a multi-scale data set. The multi-resolution skeleton is then computed and its hierarchical decomposition is obtained by using the notion of permanence. A constrained reverse distance transformation is applied to the skeleton components to reconstruct the regions ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image enhancement using pattern-selective color image fusion

    Publication Year: 1999, Page(s):44 - 49
    Cited by:  Papers (14)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (114 KB)

    This paper introduces a method for extending the effective dynamic range and depth of focus of a sensor through pattern-selective color image fusion. Pattern-selective fusion methods provide a mechanism for combining multiple monochromatic source images through identifying salient features in the source images at multiple scales and orientations, and combining those features into a single fused im... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Morphological interpolation and color images

    Publication Year: 1999, Page(s):50 - 55
    Cited by:  Papers (8)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (228 KB)

    This paper regards the application of interpolation tools offered by mathematical morphology to color images. The approach presented here uses the lexicographic ordering to compare values of the pixels. These comparisons are performed in a new, transformed color space-the comparative color space, which is essential with respect to the visual importance of color channels for the human perception. B... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning visual operators from examples: a new paradigm in image processing

    Publication Year: 1999, Page(s):58 - 62
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (212 KB)

    This paper presents a general strategy for designing efficient visual operators. The approach is highly task-oriented and what constitutes the relevant information is defined by a set of examples. The examples are pairs of images displaying a strong dependence in the chosen feature but are otherwise independent. Particularly important concepts in the work are mutual information and canonical corre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Texture segmentation by frequency-sensitive elliptical competitive learning

    Publication Year: 1999, Page(s):64 - 69
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (200 KB)

    In this paper a new learning algorithm is proposed with the purpose of texture segmentation. The algorithm is a competitive clustering scheme with two specific features: elliptical clustering is accomplished by incorporating the Mahalanobis distance measure into the learning rules, and underutilization of smaller clusters is avoided by incorporating a frequency-sensitive term. In the paper an effi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface approximation of 3D objects from irregularly sampled clouds of 3D points using spherical wavelets

    Publication Year: 1999, Page(s):70 - 75
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (264 KB)

    This paper presents a technique for computing multiresolution shape models of 3D objects acquired as clouds of 3D points. The procedure is fully automated and is able to process data from any object with a genus equivalent to that of a sphere. An important feature of this method is that it does not impose any restrictions on the input data, which can be provided by any kind of 3D sensor. The metho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Shape reconstruction of 3D bilaterally symmetric surfaces

    Publication Year: 1999, Page(s):76 - 81
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (148 KB)

    The paper presents a new approach for shape recovery based on integrating geometric and photometric information. We consider 3D objects which are symmetric with respect to a plane (e.g., faces) and their reconstruction from a single image. Both the viewpoint and the illumination are not necessarily frontal. In principle, no correspondence between symmetric points is required, but knowledge about a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning vector quantization with alternative distance criteria

    Publication Year: 1999, Page(s):84 - 89
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (73 KB)

    An adaptive algorithm for training of a nearest neighbour (NN) classifier is developed in this paper. This learning rule has some similarity to the well-known LVQ method, but uses the nearest centroid neighbourhood concept to estimate optimal locations of the codebook vectors. The aim of this approach is to improve the performance of the standard LVQ algorithms when using a very small codebook. Th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation-based lossless compression for color images

    Publication Year: 1999, Page(s):90 - 94
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (108 KB)

    It is generally accepted that a color image may be encoded by using a gray-scale compression technique on each of the three-color planes. Such an approach, however, does not take advantage of the correlation existing between the color planes. In this paper, a new segmentation-based lossless compression method is proposed for color images. The method exploits the correlation existing among the thre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sprite generation and coding of multiview image sequences

    Publication Year: 1999, Page(s):95 - 100
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (134 KB)

    An algorithm to generate background sprite images from multiview image sequences is presented. A dynamic programming algorithm, using a multiview matching cost as well as pure geometrical constraints, is used to provide an estimate of the disparity field and to identify occluded areas. By combining motion, disparity and occlusion information, a sprite image corresponding to the first (main) view a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An anisotropic diffusion PDE for noise reduction and thin edge preservation

    Publication Year: 1999, Page(s):102 - 107
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (221 KB)

    In this paper, an image denoising operator defined by a nonlinear partial differential equation (PDE) is presented. Similar to the operators proposed by Perona, Malik and Catte et al., it can remove noise, enhance step-like edges and keep the locality of the edges. Its extra ability is to keep thin edges. The criterion for stopping time is also investigated. The new operator is capable of removing... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ICM method for multi-level thresholding using maximum entropy criterion

    Publication Year: 1999, Page(s):108 - 113
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (85 KB)

    The maximum entropy approach is one of the most important threshold selection methods. Many authors avoid the computationally prohibitive problem when the maximum entropy criterion is applied to multi-level threshold selection. This paper deals with this problem using the iterated conditional modes (ICM) method. Experiments show ICM can get satisfactory if not optimal results using our initializat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The distance transform algorithm on a two-processor computer

    Publication Year: 1999, Page(s):114 - 118
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (42 KB)

    This paper contains the description of the implementation of the weighted distance transform for digital image analysis on a two-processor shared memory computer. The computer is a SMP (symmetric multiprocessing) computer and the algorithm is implemented using POSIX threads. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An extension to a filter implementation of a local quadratic surface for image noise estimation

    Publication Year: 1999, Page(s):119 - 124
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (115 KB)

    An important task in image analysis is the estimation of noise content. Based on regression analysis this paper gives a description for simple image filter design. Specifically 3/spl times/3 filter implementations of a quadratic surface, residuals from this surface, gradients and the Laplacian are given. For the residual a 5/spl times/5 filter is given also. It is shown that the 3/spl times/3 filt... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computation of two texture features in hardware

    Publication Year: 1999, Page(s):125 - 129
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (32 KB)

    This paper presents the hardware architectures of two texture features: mean and contrast. These features are based on the co-occurrence matrix method. However the features can be calculated without the co-occurrence matrix, too. The formalism behind the features without the co-occurrence matrix is shown, and the corresponding hardware architectures are depicted with data flow graphs (DFG). The ar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image restoration using quantum fluctuation

    Publication Year: 1999, Page(s):130 - 135
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (304 KB)

    Quantum fluctuation is introduced into the Markov random field (MRF) model for image restoration in the context of a Bayesian approach. We investigate the dependence of the quantum fluctuation on the quality of BW image restoration by making use of statistical mechanics. We find that the maximum posterior marginal (MPM) estimate based on the quantum fluctuation gives a fine restoration in comparis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic construction of tree-structural image transformations using genetic programming

    Publication Year: 1999, Page(s):136 - 141
    Cited by:  Papers (9)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (235 KB)

    We previously proposed an automatic construction method of image transformations. In this method, we approximate an unknown image transformation by a series of several known image filters, and a genetic algorithm optimizes their combination to meet the processing purpose presented by sets of original and target images. In this paper, we propose an extended method named "automatic construction of t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Comparison of texture features based on Gabor filters

    Publication Year: 1999, Page(s):142 - 147
    Cited by:  Papers (38)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (273 KB)

    The performance of a number of texture feature operators is evaluated. The features are all based on the local spectrum which is obtained by a bank of Gabor filters. The comparison is made using a quantitative method which is based on Fisher's criterion. It is shown that, in general, the discrimination effectiveness of the features increases with the amount of post-Gabor processing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two dimensional generalized edge detector

    Publication Year: 1999, Page(s):148 - 153
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (162 KB)

    Detecting edges in images is one of the most challenging issues in computer vision and image processing due to lack of a robust detector. Gokmen and Jain (1997) have obtained an edge detector called the generalized edge detector (GED), capable of producing most of the existing edge detectors. The original problem was formulated on a two-dimensional hybrid model comprised of the linear combination ... View full abstract»

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