Proceedings of 13th International Conference on Pattern Recognition

25-29 Aug. 1996

Go

Filter Results

Displaying Results 1 - 25 of 149
  • Proceedings of the 13th International Conference on Pattern Recognition Volume IV, Track D: Parallel and Connectionist Systems

    Publication Year: 1996
    Request permission for commercial reuse | PDF file iconPDF (485 KB)
    Freely Available from IEEE
  • Source position estimation using radial basis functions

    Publication Year: 1996, Page(s):3 - 7 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (399 KB)

    The problem of bearing estimation using radar focal plane arrays is addressed. Motivated by a requirement for a compact integrated solution in the sensor focal plane, a basis function approach is adopted. The development of a solution that is robust to sensor noise leads to a ridge regression-type estimate for the model parameters. The approach is assessed using radially symmetric kernel functions... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Curve and surface interpolation using rational radial basis functions

    Publication Year: 1996, Page(s):8 - 13 vol.4
    Cited by:  Papers (1)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (483 KB)

    This paper addresses the problem of reconstructing two-dimensional curves and three-dimensional surfaces from scattered, sparse measurements. We extend the rational Gaussian (RaG) functions introduced by Goshtasby (1993) to general rational radial basis functions and develop a method to compute the smoothness parameters for the shape model by considering the adjacency relation of the control point... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Single view recognition and pose estimation of 3D objects using sets of prototypical views and spatially tolerant contour representations

    Publication Year: 1996, Page(s):14 - 18 vol.4
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB)

    We show that a multiple-view approach to 3D recognition basing upon spatially tolerant contour representations is both straight and tractable. The approach is straight with respect to the ease in extending an existing distance- and orientation-invariant 2D robot-vision-system to a 3D recognition system. It is tractable with respect to the number of required views of an object to enable fast and re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Attention and pattern detection using sensory and reactive control mechanisms

    Publication Year: 1996, Page(s):19 - 23 vol.4
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (506 KB)

    We introduce a biologically motivated low level model of visual attention and saccade generation based on data-driven dynamic processes governing foveation and recognition of object primitives. The approach consists of two major processing pathways, magno- (M) and parvocellular (P), and it employs: 1) retinal sampling, 2) active foveation, and 3) low-level ("coarse") recognition mechanisms. The M ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Knowledge-based view control of a neural 3-D object recognition system

    Publication Year: 1996, Page(s):24 - 29 vol.4
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (667 KB)

    The recognition of 3D objects is one of the most challenging goals in computer vision. In this paper we present a robot vision system that analyzes its environment by active vision techniques. Therefore, the system is gathering information about an object in the scene by taking multiple views. It is designed as a hybrid system that brings together the advantages of neural networks and knowledge ba... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Surface modeling and robot path generation using self-organization

    Publication Year: 1996, Page(s):30 - 34 vol.4
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (506 KB)

    A tree-structured variant of the self-organizing map provides an elegant solution for automated surface processing with a robot, e.g. for painting, coating or sandblasting. Given a set of data points in arbitrary order from the object surface, the self-organizing map can be used to generate a tool path that is both smooth and covers the object with equal areas. Input data may come from a laser mea... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Performing temporal action with a hand-eye system using the SHOSLIF approach

    Publication Year: 1996, Page(s):35 - 39 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    In this paper we present a general framework by which a robotic system can be trained to perform some tasks. In the training phase, the system learns the relationship between the sensors and the actuators from a series of training examples supplied interactively by a system trainer. The system automatically builds a recursive partition tree (RPT) which approximates the mapping from the input to th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mutual learning or unsupervised interactions between mobile robots

    Publication Year: 1996, Page(s):40 - 44 vol.4
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (601 KB)

    This paper presents an overview of an ongoing project about the study of vision-based interactions between mobile robots. We first introduce the concept of dynamic map, which is a unified representation of the dynamic capabilities of a robot along with its interactions with its environment. An overview of the experimental setup is given, presenting the robot architecture, including the vision-base... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Incremental learning for vision-based navigation

    Publication Year: 1996, Page(s):45 - 49 vol.4
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (481 KB)

    In this paper, we explore the issue of incremental learning for autonomous navigation of a mobile robot. The autonomous navigation problem is regarded as a content-based retrieval problem where the robot learns the navigation experience using a hierarchical recursive partition tree (RPT). During real navigation, each time a new image is grabbed to retrieve the learned tree. The associated control ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Face recognition using ensembles of networks

    Publication Year: 1996, Page(s):50 - 54 vol.4
    Cited by:  Papers (8)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (574 KB)

    We describe a novel approach for fully automated face recognition and show its feasibility on a large database of facial images (FERET). Our approach, based on a hybrid architecture consisting of an ensemble of radial basis function (RBF) neural networks and inductive decision trees, combines the merits of "abstractive" features with those of "holistic" template matching. The benefits of our archi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning to recognise talking faces

    Publication Year: 1996, Page(s):55 - 59 vol.4
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (524 KB)

    An approach for person identification is described based on spatio-temporal analysis of the talking face. A person is represented by a parametric model of the visible speech articulators and their temporal characteristics during speech production. The model consists of shape parameters, representing the lip contour and intensity parameters representing the grey level distribution in the mouth regi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning affine transformations of the plane for model-based object recognition

    Publication Year: 1996, Page(s):60 - 64 vol.4
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (557 KB)

    We consider the problem of learning the mapping between the image coordinates of unknown affine views of an object and the parameters of the affine transformation that can align a known view of the same object with them. A single layer neural network (SL-NN) is used to learn the mapping. Although the proposed approach is conceptually similar to other approaches in the literature, its practical adv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic link matching for multiple object recognition

    Publication Year: 1996, Page(s):65 - 69 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (455 KB)

    We present an extended version of dynamic link matching for the recognition of all objects similar to a stored model. With a given complex image containing multiple objects, our system can detect all of those matched with a model regardless of their type of geometric transformation and distortion. This is achieved by allowing simultaneous strengthening of multiple bundles of interlayer links (dyna... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A neural 3-D object recognition architecture using optimized Gabor filters

    Publication Year: 1996, Page(s):70 - 74 vol.4
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (530 KB)

    We present an object recognition architecture based on feature extraction by Gabor filter kernels and feature classification by an artificial neural network. The parameters of the Gabor filters are optimized to the specific problem by minimizing an energy function. Such Gabor filters extract features that can be more easily classified by the neural network. Moreover, the feature space is low-dimen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Triplet-based object recognition using synthetic and real probability models

    Publication Year: 1996, Page(s):75 - 79 vol.4
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (514 KB)

    We describe a model-based object recognition system that uses a probabilistic model for recognizing and locating objects. For each major view class of each 3D object, a probability model consisting of triplets of visible features, their parametrization, and their frequency of detection is constructed from a set of synthetic training images. These synthetic probability models are used to recognize ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Skeletal shape extraction from dot patterns by self-organization

    Publication Year: 1996, Page(s):80 - 84 vol.4
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (399 KB)

    Extraction of skeletal shape from a 2D dot pattern is discussed. We use a self-organizing neural network model to get a piecewise linear approximation of a skeleton of the pattern. It is found that even without a proper definition of a skeleton, the proposed algorithm is able to produce skeletons that are quite close to what we intuitively feel it should be. In Kohonen's self-organizing model, the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum-likelihood design of layered neural networks

    Publication Year: 1996, Page(s):85 - 89 vol.4
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (397 KB)

    The design of layered neural networks is posed as a problem of estimating finite mixtures of normal densities in the framework of statistical decision-making. The output units of the network (third layer) correspond to class-conditional mixtures defined as weighted sums of a given set of normal densities which can be viewed as radial basis functions. It is shown that the resulting classification p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Unsupervised segmentation of gray level Markov model textures with hierarchical self organizing maps

    Publication Year: 1996, Page(s):90 - 94 vol.4
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (544 KB)

    Segmentation of gray level images into regions of uniform texture is investigated. An unsupervised approach through the use of Kohonen's self organizing map (SOM) and a multilayer version of it, the hierarchical self organizing map (HSOM), is employed to find the regions in an image composed of textures from different classes. For testing, gray level artificial textured images modeled as Markov ra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling object recognition as a Markov decision process

    Publication Year: 1996, Page(s):95 - 99 vol.4
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (508 KB)

    The field of computer vision has made significant advances over the past twenty years, yet we still have not developed a theoretical or practical understanding of how the many components of vision are combined into coherent, functioning systems. As a result, there are few applications of computer vision technology in the real world, even though the library of available computer vision techniques k... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Markov random field model of subjective contour perception

    Publication Year: 1996, Page(s):100 - 104 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (469 KB)

    We describe a model of subjective contour perception that sees the triangle: top-down feedback from the perception of an occluding object causes the perception of illusory contrast along the object's boundary. Unlike other approaches, the model explicitly incorporates a representational hierarchy of visual elements at multiple levels of abstraction, for example, both local contrast edges and trian... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autoassociative learning in relaxation labeling networks

    Publication Year: 1996, Page(s):105 - 110 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (628 KB)

    We address the problem of training relaxation labeling processes, a popular class of parallel iterative procedures widely employed in pattern recognition and computer vision. The approach discussed here is based on a theory of consistency developed by Hummel and Zucker (1983) and contrasts with a previously introduced learning strategy which can be regarded as heteroassociative, i.e. what is actua... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3-D object recognition from range images by using a model-based Hopfield-style matching algorithm

    Publication Year: 1996, Page(s):111 - 116 vol.4
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (567 KB)

    A new method is proposed for recognizing 3-D objects by using a Hopfield-style optimization algorithm based on matching between patch-based image and model descriptions. To obtain the image descriptions, range images are employed to extract reliable high-level patch features. In the optimization process the objective function is a Liapunov function that is minimized in a Hopfield net with its inte... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3-D object recognition using adaptive scale MEGI

    Publication Year: 1996, Page(s):117 - 122 vol.4
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (542 KB)

    We propose a method for recognition of a 3-D object using a multi scale description of the object and adaptive matching. MEGI model is a description model to represent arbitrary shapes. However, many MEGI elements are necessary to represent uneven or carved surfaces with accuracy, so it is difficult to use them for recognition. As a solution, we make a tree which corresponds to the multi scale des... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Matchability-oriented feature selection for recognition structure learning

    Publication Year: 1996, Page(s):123 - 127 vol.4
    Cited by:  Papers (1)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (539 KB)

    For effective recognition, a recognition structure that controls the information flow among the specialized processing modules should reflect the implicit correlation structure of the environmental input. Autonomous construction of a recognition structure will lead to extensive improvement in the flexibility of the adaptive recognition system. For this purpose we propose a matchability-oriented fe... View full abstract»

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