By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 8 • Date Aug 1995

Filter Results

Displaying Results 1 - 11 of 11
  • Structural matching in computer vision using probabilistic relaxation

    Page(s): 749 - 764
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1440 KB)  

    In this paper, we develop the theory of probabilistic relaxation for matching features extracted from 2D images, derive as limiting cases the various heuristic formulae used by researchers in matching problems, and state the conditions under which they apply, We successfully apply our theory to the problem of matching and recognizing aerial road network images based on road network models and to the problem of edge matching in a stereo pair. For this purpose, each line network is represented by an attributed relational graph where each node is a straight line segment characterized by certain attributes and related with every other node via a set of binary relations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mean shift, mode seeking, and clustering

    Page(s): 790 - 799
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (752 KB)  

    Mean shift, a simple interactive procedure that shifts each data point to the average of data points in its neighborhood is generalized and analyzed in the paper. This generalization makes some k-means like clustering algorithms its special cases. It is shown that mean shift is a mode-seeking process on the surface constructed with a “shadow” kernal. For Gaussian kernels, mean shift is a gradient mapping. Convergence is studied for mean shift iterations. Cluster analysis if treated as a deterministic problem of finding a fixed point of mean shift that characterizes the data. Applications in clustering and Hough transform are demonstrated. Mean shift is also considered as an evolutionary strategy that performs multistart global optimization View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On critical point detection of digital shapes

    Page(s): 737 - 748
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (968 KB)  

    In this paper, we present a nonlinear algorithm for critical point detection (CPD) of 2D digital shapes. The algorithm eliminates the problems arising from curvature approximation and Gaussian filtering in the existing algorithms. Based on the definition of “critical level,” we establish a set of criteria for the design of an effective CPD algorithm for the first time. By quantifying the critical level to the modified area confined by three consecutive “pseudocritical points,” a simple but very effective algorithm is developed. The comparison of our experimental results with those of many other CPD algorithms shows that the proposed algorithm is superior in that it provides a sequence of figures at every detail level, and each has a smaller integral error than the others with the same number of critical points. The experimental results on shapes with various complexities also show the algorithm is reliable and robust with regard to noise View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Algebraic functions for recognition

    Page(s): 779 - 789
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1812 KB)  

    In the general case, a trilinear relationship between three perspective views is shown to exist. The trilinearity result is shown to be of much practical use in visual recognition by alignment-yielding a direct reprojection method that cuts through the computations of camera transformation, scene structure and epipolar geometry. Moreover, the direct method is linear and sets a new lower theoretical bound on the minimal number of points that are required for a linear solution for the task of reprojection. The proof of the central result may be of further interest as it demonstrates certain regularities across homographics of the plane and introduces new view invariants. Experiments on simulated and real image data were conducted, including a comparative analysis with epipolar intersection and the linear combination methods, with results indicating a greater degree of robustness in practice and a higher level of performance in reprojection tasks View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking of tubular molecules for scientific applications

    Page(s): 800 - 805
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (564 KB)  

    In this paper, we present a system for detection and tracking of tubular molecules in images. The automatic detection and characterization of the shape, location, and motion of these molecules can enable new laboratory protocols in several scientific disciplines. The uniqueness of the proposed system is twofold: At the macro level, the novelty of the system lies in the integration of object localization and tracking using geometric properties; at the micro level, in the use of high and low level constraints to model the detection and tracking subsystem. The underlying philosophy for object detection is to extract perceptually significant features from the pixel level image, and then use these high level cues to refine the precise boundaries. In the case of tubular molecules, the perceptually significant features are antiparallel line segments or, equivalently, their axis of symmetries. The axis of symmetry infers a coarse description of the object in terms of a bounding polygon. The polygon then provides the necessary boundary condition for the refinement process, which is based on dynamic programming. For tracking the object in a time sequence of images, the refined contour is then projected onto each consecutive frame View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of camera behavior during tracking

    Page(s): 765 - 778
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1084 KB)  

    A camera is mounted on a moving robot and can rotate, relative to the robot, about two axes. We show how the optical flow field can be used to control the camera's motion to keep a target at the center of the camera's field of view, but that this is not always possible when the target lies close to the plane defined by the camera's two axes of rotation. When the target is held at the center of the camera's field of view, then the magnitude of the camera's angular velocity about one axis never exceeds the magnitude of the flow vector associated with the target, but the angular velocity about the other axis is dependent on the inverse distance of the target from this axis, and hence can become large as this distance becomes small. Situations, where the magnitudes of the camera's angular velocity and acceleration become large, are considered in the special case where the relative motion between the robot and its environment is purely translational. The tracking strategy is experimentally evaluated using computer-generated optical flow fields View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • ASSET-2: real-time motion segmentation and shape tracking

    Page(s): 814 - 820
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (680 KB)  

    This paper describes a system for detecting and tracking moving objects in a moving world. The feature-based optic flow field is segmented into clusters with affine internal motion which are tracked over time. The system runs in real-time, and is accurate and reliable View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • CASM: a VLSI chip for approximate string matching

    Page(s): 824 - 830
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (624 KB)  

    The edit distance between two strings a1, ..., am and b 1, ..., bn is the minimum cost s of a sequence of editing operations (insertions, deletions and substitutions) that convert one string into the other. This paper describes the design and implementation of a linear systolic array chip for computing the edit distance between two strings over a given alphabet. An encoding scheme is proposed which reduces the number of bits required to represent a state in the computation. The architecture is a parallel realization of the standard dynamic programming algorithm proposed by Wagner and Fischer (1974), and can perform approximate string matching for variable edit costs. More importantly, the architecture does not place any constraint on the lengths of the strings that can be compared. It makes use of simple basic cells and requires regular nearest neighbor communication, which makes it suitable for VLSI implementation. A prototype of this array has been built at the University of South Florida View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Registering multiview range data to create 3D computer objects

    Page(s): 820 - 824
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (544 KB)  

    Concerns the problem of range image registration for the purpose of building surface models of 3D objects. The registration task involves finding the translation and rotation parameters which properly align overlapping views of the object so as to reconstruct from these partial surfaces, an integrated surface representation of the object. The registration task is expressed as an optimization problem. We define a function which measures the quality of the alignment between the partial surfaces contained in two range images as produced by a set of motion parameters. This function computes a sum of Euclidean distances from control points on one surfaces to corresponding points on the other. The strength of this approach is in the method used to determine point correspondences. It reverses the rangefinder calibration process, resulting in equations which can be used to directly compute the location of a point in a range image corresponding to an arbitrary point in 3D space. A stochastic optimization technique, very fast simulated reannealing (VFSR), is used to minimize the cost function. Dual-view registration experiments yielded excellent results in very reasonable time. A multiview registration experiment took a long time. A complete surface model was then constructed from the integration of multiple partial views. The effectiveness with which registration of range images can be accomplished makes this method attractive for many practical applications where surface models of 3D objects must be constructed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Similarity and affine invariant distances between 2D point sets

    Page(s): 810 - 814
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (544 KB)  

    We develop expressions for measuring the distance between 2D point sets, which are invariant to either 2D affine transformations or 2D similarity transformations of the sets, and assuming a known correspondence between the point sets. We discuss the image normalization to be applied to the images before their comparison so that the computed distance is symmetric with respect to the two images. We then give a general (metric) definition of the distance between images, which leads to the same expressions for the similarity and affine cases. This definition avoids ad hoc decisions about normalization. Moreover, it makes it possible to compute the distance between images under different conditions, including cases where the images are treated asymmetrically. We demonstrate these results with real and simulated images View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Finding Waldo, or focus of attention using local color information

    Page(s): 805 - 809
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (668 KB)  

    We present a method to locate an “object” in a color image, or more precisely, to select a set of likely locations for the object. The model is assumed to be of known color distribution, which permits the use color-space processing. A new method is presented, which exploits more information than the previous backprojection algorithm of Swain and Ballard (1990) at a competitive complexity. Precisely, the new algorithm is based on matching local histograms with the model, instead of directly replacing pixels with a confidence that they belong to the object. We prove that a simple version of this algorithm degenerates into backprojection in the worst case. In addition, we show how to estimate the scale of the model. Results are shown on pictures digitized from the famous “Where is Waldo” books. Issues concerning the optimal choice of a color space and its quantization are carefully considered and studied in this application. We also propose to use co-occurrence histograms to deal with cases where important color variations can be expected View full abstract»

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

Aims & Scope

The IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) is published monthly. Its editorial board strives to present most important research results in areas within TPAMI's scope.

Full Aims & Scope

Meet Our Editors

Editor-in-Chief
David A. Forsyth
University of Illinois