Proceedings of 12th International Conference on Pattern Recognition

9-13 Oct. 1994

Filter Results

Displaying Results 1 - 25 of 200
  • Proceedings of 12th International Conference on Pattern Recognition

    Publication Year: 1994
    Request permission for commercial reuse | PDF file iconPDF (887 KB)
    Freely Available from IEEE
  • Guaranteed geometric hashing

    Publication Year: 1994, Page(s):465 - 469 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (471 KB)

    Geometric hashing is an invariant feature-driven approach to model-based object recognition. Previous interest has focused on its ability to accommodate sensor error. This paper presents an enhancement of the geometric hashing technique which guarantees, under only a few constraints, that models will not be missed due to sensor noise. The authors' geometric hashing algorithm enters model affine in... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generic recognition of articulated objects by reasoning about functionality

    Publication Year: 1994, Page(s):847 - 849 vol.1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (265 KB)

    Previous work on the recognition of objects by reasoning about their functionality has not dealt with objects that have moving parts. In this paper we introduce a scenario in which object recognition is accomplished by first deriving an articulated shape model from an observed sequence of 3-D shapes and by then reasoning about the possible functionality of the articulated shape model. View full abstract»

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

    Publication Year: 1994, Page(s):865 - 875
    Request permission for commercial reuse | PDF file iconPDF (614 KB)
    Freely Available from IEEE
  • Geometric invariant of noncoplanar lines in a single view

    Publication Year: 1994, Page(s):190 - 195 vol.1
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (476 KB)

    The importance of geometric invariants to many machine vision tasks, such as model-based recognition, has been recognized. A number of studies on geometric invariants in a single view concentrate on coplanar objects: coplanar points, coplanar lines, coplanar conics, etc. Therefore, it is essentially only to 2-D objects that we can apply methods using geometric invariants. This paper presents a stu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Determining local natural scales of curves

    Publication Year: 1994, Page(s):185 - 189 vol.1
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (452 KB)

    An alternative to representing curves at a single scale or a fixed number of multiple scales is to represent them only at their natural (i.e. most significant) scales. This allows all the important information concerning the different sized structures contained in the curve to be explicitly represented without the overhead of redundant representations of the curve. This paper describes several app... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of the second order spatio-temporal derivatives of deforming image curves

    Publication Year: 1994, Page(s):179 - 184 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (588 KB)

    This paper intends to show that the second order spatio-temporal derivatives of de-forming image curves can be computed quite accurately from image sequences. These quantities, related to the second order optical flow parameters, are useful in the computation of the motion and the structure of a 3-D rigid curve from monocular image sequences. We show that they can be estimated directly from the po... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Camera calibration without feature extraction

    Publication Year: 1994, Page(s):704 - 706 vol.1
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (292 KB)

    We present an original approach to the problem of camera calibration. Contrary to classical techniques, which first extract the image features and then compute the camera parameters, we directly search for the camera parameters that best map three-dimensional points onto the image edges, characterized as maxims of the intensity gradient or zero-crossings of the Laplacian. Expressed as a one-stage ... View full abstract»

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

    Publication Year: 1994, Page(s):174 - 178 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB)

    In this contribution we consider in all detail the effect of digitization on circular arcs. Given a specific discrete circular arc we find the set of all continuous arcs which by digitization would result in this pattern. From this characterization we provide optimal estimates of the radius (or curvature) of the original arc. This estimator achieves the ultimate precision one can reach in estimati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Part decomposition and description of 3D shapes

    Publication Year: 1994, Page(s):629 - 632 vol.1
    Cited by:  Papers (12)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (480 KB)

    Addresses the problem of obtaining natural descriptions of 3D shapes. The authors present one of the first attempts to address the description of 3D compound objects, where the parts are connected smoothly. The input the authors consider is either complete 3D data or range data from a single view. The authors suggest a volumetric graph representation of the object, where the nodes represent indivi... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A generalized motion model for estimating optical flow using 3-D Hermite polynomials

    Publication Year: 1994, Page(s):361 - 366 vol.1
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (540 KB)

    Classic optical flow algorithms assume local image translational motion and apply some primitive image smoothing. Recent studies have taken two separate approaches toward improving accuracy: the application of spatio-temporal filtering schemes and the use of generalized motion models such as the affine model. Each has achieved improvement in its specialized situations. We analyze the interdependen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Camera parameter determination from a single view of a general planar calibration object

    Publication Year: 1994, Page(s):238 - 242 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (344 KB)

    A new approach to camera parameter estimation based on a single perspective view of a general planar calibration object is proposed. For the first time, the authors present an analytical approximation model for the perspective projection under some mild conditions. With this approximation model, the authors can decouple and estimate the six camera parameters. The authors also derive some important... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scale-invariant polyhedral object recognition using fragmentary edge segments

    Publication Year: 1994, Page(s):850 - 853 vol.1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (400 KB)

    We propose a scale-invariant polyhedral object recognition algorithm that is based on the pose clustering paradigm using fragmentary edge segments. Two novel feature-focus techniques are introduced to reduce the computational complexity for matching a scene with n edge fragments and a model with m edges from Q(m2n2) to O(mn) without loss of matching quality. In addition, we s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An automatic jigsaw puzzle solver

    Publication Year: 1994, Page(s):616 - 618 vol.1
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (332 KB)

    A computer vision system to automatically analyze and assemble an image of the pieces of a jigsaw puzzle is presented. The system, called Automatic Puzzle Solver (APS), derives a new set of features based on the shape and color characteristics of the puzzle pieces. A combination of the shape dependent features and color cues is used to match the puzzle pieces. Matching is performed using a modifie... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A general parameter updating approach to image classification

    Publication Year: 1994, Page(s):720 - 722 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (576 KB)

    This paper presents an EM approach to parameter updating in supervised image classification based on the maximum aposteriori (MAP) estimation. By specifying suitable prior distribution in the form of constraint on the differences between class mean vectors, the new algorithm generally gives better estimates of the class means than the maximum likelihood-EM algorithm, as shown by results with MR im... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive window algorithm for aerial image stereo

    Publication Year: 1994, Page(s):701 - 703 vol.1
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (560 KB)

    Binocular stereo vision processes estimate 3D surfaces using a pair of images taken from different points of view. 3D surface characteristics are estimated by matching 3D image areas or features corresponding to the projections of same 3D points. The most classic area-based methods used cross correlation with a fixed window-size, but this technique presents a major draw-back: the computation of de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Moment difference method for the parameter estimation of a quadratic curve

    Publication Year: 1994, Page(s):169 - 173 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (372 KB)

    In this paper, we present a novel method to estimate the parameters of a quadratic curve. We show that by grouping the data points and by estimating the so-called moments difference (MD) which are unbiased and consistent, the parameters of a quadratic curve can be estimated with higher accuracy than the existing methods View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Interactive analysis of multi-spectral images using a Hilbert curve

    Publication Year: 1994, Page(s):93 - 97 vol.1
    Cited by:  Papers (6)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (440 KB)

    There have been many new developments in interactive analysis for multi-spectral images in the research of remote sensing. In general, the methods used are linear transformations such as principal component analysis. In this paper, the authors present a new interactive method for classifying multi-spectral images using a Hilbert curve which is a one-to-one mapping and preserves the neighborhood as... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive meshes and nonrigid motion computation

    Publication Year: 1994, Page(s):730 - 732 vol.1
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    We describe a new method for computing displacement field for sequences of temporal images. It involves minimizing the energy defined on the space of correspondence functions. This energy is divided in two terms: one which matches the contour points and particularly high curvature points, and one which regularizes the field. We introduce an adaptive mesh the resolution of which depends on the pres... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stereoscopic recovery of egomotion and structure: models, uniqueness and experimental results

    Publication Year: 1994, Page(s):645 - 648 vol.1
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    Algorithms for estimating the smooth egomotion of moving cameras and the structure of objects in a stationary environment using long, noisy stereo image sequences are presented. Conditions for the uniqueness of the motion and structure parameters also given View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Using polyballs to approximate shapes and skeletons

    Publication Year: 1994, Page(s):626 - 628 vol.1
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (340 KB)

    This paper presents an approach to approximate the skeleton of continuous shapes either in 2D or 3D space. The data required is a sampling of the boundary of the shape. The authors call polyball any finite union of balls. A preliminary work on polyballs shows that their skeletons consist of simple components (line segments in 2D and polygons in 3D). To construct these components, only the computat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ScilImage: an environment for collaborative use and development of image processing software

    Publication Year: 1994, Page(s):543 - 545 vol.1
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (244 KB)

    This paper presents a brief overview of a portable multi-layered interactive environment for software development and use, and a class based infrastucture for image processing. The environment consists of a library handler, a C interpreter, a command expander, a menu and dialog generator, and a visual programming interface. It forms a proper vehicle for development and exchange of (image processin... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Online color camera calibration

    Publication Year: 1994, Page(s):232 - 237 vol.1
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (656 KB)

    This paper presents a practical approach to online color camera calibration under changing illumination conditions. Calibration is based on a color camera model and color constancy. In the first stage of the calibration a reconstruction of the current illuminant is performed based on an image taken from a scene with a calibrated color set. Using the updated power spectrum distribution of the curre... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Making snakes converge from minimal initialization

    Publication Year: 1994, Page(s):613 - 615 vol.1
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (764 KB)

    In this paper, we present a new snake-based method to delineate contours where the user has to specify only the two distant end points without having to supply an almost complete polygonal approximation. We achieve much better convergence properties than those of traditional snakes by propagating the image information along the curve from both end points towards its center. We use our new method t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Global shape from shading

    Publication Year: 1994, Page(s):120 - 125 vol.1
    Cited by:  Papers (5)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (608 KB)

    A new approach for the reconstruction of a smooth three dimensional object from its two dimensional gray level image is presented. An algorithm based on topological properties of simple smooth surfaces is provided to solve the problem of global reconstruction. Classifying singular points in the shading image as maxima minima and two kinds of saddle points, serves as the key to the solution of the ... View full abstract»

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