Notification:
We are currently experiencing intermittent issues impacting performance. We apologize for the inconvenience.
By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 8 • Date Aug 1993

Filter Results

Displaying Results 1 - 11 of 11
  • Shape from shading with a linear triangular element surface model

    Publication Year: 1993 , Page(s): 815 - 822
    Cited by:  Papers (28)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (764 KB)  

    The authors propose to combine a triangular element surface model with a linearized reflectance map to formulate the shape-from-shading problem. The main idea is to approximate a smooth surface by the union of triangular surface patches called triangular elements and express the approximating surface as a linear combination of a set of nodal basis functions. Since the surface normal of a triangular element is uniquely determined by the heights of its three vertices (or nodes), image brightness can be directly related to nodal heights using the linearized reflectance map. The surface height can then be determined by minimizing a quadratic cost functional corresponding to the squares of brightness errors and solved effectively with the multigrid computational technique. The proposed method does not require any integrability constraint or artificial assumptions on boundary conditions. Simulation results for synthetic and real images are presented to illustrate the performance and efficiency of the method View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Darboux frames, snakes, and super-quadrics: geometry from the bottom up

    Publication Year: 1993 , Page(s): 771 - 784
    Cited by:  Papers (42)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1196 KB)  

    A representational and a computational model for deriving 3-D articulated volumetric descriptions of objects from laser rangefinder data is described. This method is purely bottom up: it relies on general assumptions cast in terms of differential geometry. Darboux frames, snakes, and superquadrics form the basis of this representation, and curvature consistency provides the computational framework. The organization is hierarchical. Darboux frames are used to describe the local surface, whereas snakes are used to interpolate between features, particularly those that serve to partition a surface into its constituent parts. Superquadrics are used to characterize the 3-D shape of each surface partition. The result is a set of connected volumetric primitives that serve to describe the overall shape of an object. Examples that show how the approach performs on data acquired with a laser rangefinder are included View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Pattern recognition properties of various feature spaces for higher order neural networks

    Publication Year: 1993 , Page(s): 795 - 801
    Cited by:  Papers (12)  |  Patents (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (556 KB)  

    The authors explore alternatives that reduce the number of network weights while maintaining geometric invariant properties for recognizing patterns in real-time processing applications. This study is limited to translation and rotation invariance. The primary interest is in examining the properties of various feature spaces for higher-order neural networks (HONNs), in correlated and uncorrelated noise, such as the effect of various types of input features, feature size and number of feature pixels, and effect of scene size. The robustness of HONN training is considered in terms of target detectability. The experimental setup consists of a 15×20 pixel scene possibly containing a 3×10 target. Each trial used 500 training scenes plus 500 testing scenes. Results indicate that HONNs yield similar geometric invariant target recognition properties to classical template matching. However, the HONNs require an order of magnitude less computer processing time compared with template matching. Results also indicate that HONNs could be considered for real-time target recognition applications View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vehicle-type motion estimation from multi-frame images

    Publication Year: 1993 , Page(s): 802 - 808
    Cited by:  Papers (10)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (692 KB)  

    A model for vehicle-type motion, which assumes that the motion is a rotation around an axis through the vehicle center followed by a forward translation along the main axis of the vehicle, is proposed. When the rotation and the amplitude of translation are constant, this type of motion is shown to be equivalent to a constant camera-centered motion. This indicates that a constant motion in the conventional camera-centered model, which is commonly considered to be artificial, can in fact be a reasonable model in real life. It is shown that a constant vehicle-type motion can be interpreted as a constant screw motion. A linear algorithm for estimating constant vehicle-type motion is presented, and experiments using real scene images are included. As an extension, vehicle-type motion with constant rotation and constantly accelerated translation is discussed View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The intensity axis of symmetry and its application to image segmentation

    Publication Year: 1993 , Page(s): 753 - 770
    Cited by:  Papers (13)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1880 KB)  

    The authors present the intensity axis of symmetry (IAS) method for describing the shape of structures in grey-scale images. They describe the spatial and intensity variations of the image simultaneously rather than by the usual two-step process of using intensity properties of the image to segment an image into regions and describing the spatial shape of these regions. The result is an image shape description that is useful for a number of computer vision applications. The method relies on minimizing an active surface functional that provides coherence in both the spatial and intensity dimensions while deforming into an axis of symmetry. Shape-based image segmentation is possible by identifying image regions associated with individual components of the IAS. The resulting image regions have geometric coherence and correspond well to visually meaningful objects in medical images View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive split-and-merge segmentation based on piecewise least-square approximation

    Publication Year: 1993 , Page(s): 808 - 815
    Cited by:  Papers (17)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (792 KB)  

    The performance of the classic split-and-merge segmentation algorithm is severely hampered by its rigid split-and-merge processes, which are insensitive to the image semantics. The author proposes efficient algorithms and data structures to optimize the split-and-merge processes by piecewise least-square approximation of image intensity functions. This optimization aims at the unification of segment finding and edge detection. The optimized split-and-merge algorithm is shown to be adaptive to the image semantics and, hence, improves the segmentation validity of the previous algorithms. This algorithm also appears to work well on noisy sources. Since the optimization is done within the split-and-merge framework, the better segmentation performance is achieved at the same order of time complexity as the previous algorithms View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Constrained clustering as an optimization method

    Publication Year: 1993 , Page(s): 785 - 794
    Cited by:  Papers (60)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (832 KB)  

    A deterministic annealing approach to clustering is derived on the basis of the principle of maximum entropy. This approach is independent of the initial state and produces natural hierarchical clustering solutions by going through a sequence of phase transitions. It is modified for a larger class of optimization problems by adding constraints to the free energy. The concept of constrained clustering is explained, and three examples are are given in which it is used to introduce deterministic annealing. The previous clustering method is improved by adding cluster mass variables and a total mass constraint. The traveling salesman problem is reformulated as constrained clustering, yielding the elastic net (EN) approach to the problem. More insight is gained by identifying a second Lagrange multiplier that is related to the tour length and can also be used to control the annealing process. The open path constraint formulation is shown to relate to dimensionality reduction by self-organization in unsupervised learning. A similar annealing procedure is applicable in this case as well View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On learning to recognize 3-D objects from examples

    Publication Year: 1993 , Page(s): 833 - 837
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (580 KB)  

    Previous results on nonlearnability of visual concepts relied on the assumption that such concepts are represented as sets of pixels. The author uses an approach developed by Haussler (1989) to show that under an alternative, feature-based representation, recognition is probably approximately correct (PAC) learnable from a feasible number of examples in a distribution-free manner View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Early jump-out corner detectors

    Publication Year: 1993 , Page(s): 823 - 828
    Cited by:  Papers (14)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (592 KB)  

    The authors present two new corner detectors. One works by using dissimilarity, along the contour direction to detect curves in the image contour, and the other estimates image curvature along the contour direction. These operators are fast, robust to noise, and require no subjective thresholding View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A constrained approach to multifont Chinese character recognition

    Publication Year: 1993 , Page(s): 838 - 843
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (524 KB)  

    The constraint graph is introduced as a general character representation framework for recognizing multifont, multiple-size Chinese characters. Each character class is described by a constraint graph model. Sampling points on a character skeleton are taken as nodes in the graph. Connection constraints and position constraints are taken as arcs in the graph. For patterns of the same character class, the model captures both the topological invariance and the geometrical invariance in a general and uniform way. Character recognition is then formulated as a constraint-based optimization problem. A cooperative relaxation matching algorithm that solves this optimization problem is developed. A practical optical character recognition (OCR) system that is able to recognize multifont, multiple-size Chinese characters with a satisfactory performance was implemented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Optimally small operator supports for fully parallel thinning algorithms

    Publication Year: 1993 , Page(s): 828 - 833
    Cited by:  Papers (8)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (548 KB)  

    Requirements for the support size and shape are investigated for the class of all adequate fully parallel thinning operators. Eleven pixel supports are shown to be the smallest possible supports, and the possible positions of the support pixels are shown to be well constrained. Constraints on support positions are demonstrated for operators with supports that are larger than optimal, and a sufficient test for connectivity preservation is reviewed. These results allow algorithm designers looking for small support operators to focus on a relatively small set of acceptable supports 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