By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 8 • Date Aug. 2011

Filter Results

Displaying Results 1 - 21 of 21
  • [Front cover]

    Publication Year: 2011, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (149 KB)
    Freely Available from IEEE
  • [Inside front cover]

    Publication Year: 2011, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (162 KB)
    Freely Available from IEEE
  • CENTRIST: A Visual Descriptor for Scene Categorization

    Publication Year: 2011, Page(s):1489 - 1501
    Cited by:  Papers (62)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1570 KB) | HTML iconHTML

    CENsus TRansform hISTogram (CENTRIST), a new visual descriptor for recognizing topological places or scene categories, is introduced in this paper. We show that place and scene recognition, especially for indoor environments, require its visual descriptor to possess properties that are different from other vision domains (e.g., object recognition). CENTRIST satisfies these properties and suits the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Construction of Iso-Contours, Bisectors, and Voronoi Diagrams on Triangulated Surfaces

    Publication Year: 2011, Page(s):1502 - 1517
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3206 KB) | HTML iconHTML Multimedia Media

    In the research of computer vision and machine perception, 3D objects are usually represented by 2-manifold triangular meshes M. In this paper, we present practical and efficient algorithms to construct iso-contours, bisectors, and Voronoi diagrams of point sites on M, based on an exact geodesic metric. Compared to euclidean metric spaces, the Voronoi diagrams on M exhibit many special properties ... View full abstract»

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

    Publication Year: 2011, Page(s):1518 - 1531
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (8860 KB) | HTML iconHTML Multimedia Media

    In this paper we consider the problem of reconstructing the 3D position and surface normal of points on an unknown, arbitrarily-shaped refractive surface. We show that two viewpoints are sufficient to solve this problem in the general case, even if the refractive index is unknown. The key requirements are 1) knowledge of a function that maps each point on the two image planes to a known 3D point t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Feature Selection and Kernel Learning for Local Learning-Based Clustering

    Publication Year: 2011, Page(s):1532 - 1547
    Cited by:  Papers (7)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1307 KB) | HTML iconHTML

    The performance of the most clustering algorithms highly relies on the representation of data in the input space or the Hilbert space of kernel methods. This paper is to obtain an appropriate data representation through feature selection or kernel learning within the framework of the Local Learning-Based Clustering (LLC) (Wu and Schölkopf 2006) method, which can outperform the global learn... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Graph Regularized Nonnegative Matrix Factorization for Data Representation

    Publication Year: 2011, Page(s):1548 - 1560
    Cited by:  Papers (65)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1443 KB) | HTML iconHTML

    Matrix factorization techniques have been frequently applied in information retrieval, computer vision, and pattern recognition. Among them, Nonnegative Matrix Factorization (NMF) has received considerable attention due to its psychological and physiological interpretation of naturally occurring data whose representation may be parts based in the human brain. On the other hand, from the geometric ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maximum Correntropy Criterion for Robust Face Recognition

    Publication Year: 2011, Page(s):1561 - 1576
    Cited by:  Papers (39)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2109 KB) | HTML iconHTML

    In this paper, we present a sparse correntropy framework for computing robust sparse representations of face images for recognition. Compared with the state-of-the-art l1norm-based sparse representation classifier (SRC), which assumes that noise also has a sparse representation, our sparse algorithm is developed based on the maximum correntropy criterion, which is much more insensitive ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion Field Estimation from Alternate Exposure Images

    Publication Year: 2011, Page(s):1577 - 1589
    Cited by:  Papers (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2915 KB) | HTML iconHTML

    Traditional optical flow algorithms rely on consecutive short-exposed images. In this work, we make use of an additional long-exposed image for motion field estimation. Long-exposed images integrate motion information directly in the form of motion-blur. With this additional information, more robust and accurate motion fields can be estimated. In addition, the moment of occlusion can be determined... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonnegative Matrix Factorization with Earth Mover's Distance Metric for Image Analysis

    Publication Year: 2011, Page(s):1590 - 1602
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1542 KB) | HTML iconHTML

    Nonnegative matrix factorization (NMF) approximates a given data matrix as a product of two low-rank nonnegative matrices, usually by minimizing the L2 or the KL distance between the data matrix and the matrix product. This factorization was shown to be useful for several important computer vision applications. We propose here two new NMF algorithms that minimize the Earth mover's dista... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Richardson-Lucy Deblurring for Scenes under a Projective Motion Path

    Publication Year: 2011, Page(s):1603 - 1618
    Cited by:  Papers (41)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3481 KB) | HTML iconHTML Multimedia Media

    This paper addresses how to model and correct image blur that arises when a camera undergoes ego motion while observing a distant scene. In particular, we discuss how the blurred image can be modeled as an integration of the clear scene under a sequence of planar projective transformations (i.e., homographies) that describe the camera's path. This projective motion path blur model is more effectiv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Object Tracking with Online Multiple Instance Learning

    Publication Year: 2011, Page(s):1619 - 1632
    Cited by:  Papers (308)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2236 KB) | HTML iconHTML

    In this paper, we address the problem of tracking an object in a video given its location in the first frame and no other information. Recently, a class of tracking techniques called “tracking by detection” has been shown to give promising results at real-time speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Point Set Registration Using Gaussian Mixture Models

    Publication Year: 2011, Page(s):1633 - 1645
    Cited by:  Papers (79)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1434 KB) | HTML iconHTML

    In this paper, we present a unified framework for the rigid and nonrigid point set registration problem in the presence of significant amounts of noise and outliers. The key idea of this registration framework is to represent the input point sets using Gaussian mixture models. Then, the problem of point set registration is reformulated as the problem of aligning two Gaussian mixtures such that a s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Theory and Algorithms for Constructing Discrete Morse Complexes from Grayscale Digital Images

    Publication Year: 2011, Page(s):1646 - 1658
    Cited by:  Papers (13)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (827 KB) | HTML iconHTML Multimedia Media

    We present an algorithm for determining the Morse complex of a two or three-dimensional grayscale digital image. Each cell in the Morse complex corresponds to a topological change in the level sets (i.e., a critical point) of the grayscale image. Since more than one critical point may be associated with a single image voxel, we model digital images by cubical complexes. A new homotopic algorithm i... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-Adaptive Induction of Regression Trees

    Publication Year: 2011, Page(s):1659 - 1672
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1808 KB) | HTML iconHTML

    A new algorithm for incremental construction of binary regression trees is presented. This algorithm, called SAIRT, adapts the induced model when facing data streams involving unknown dynamics, like gradual and abrupt function drift, changes in certain regions of the function, noise, and virtual drift. It also handles both symbolic and numeric attributes. The proposed algorithm can automatically a... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Simplified Computation for Nonparametric Windows Method of Probability Density Function Estimation

    Publication Year: 2011, Page(s):1673 - 1680
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1686 KB) | HTML iconHTML

    Recently, Kadir and Brady proposed a method for estimating probability density functions (PDFs) for digital signals which they call the Nonparametric (NP) Windows method. The method involves constructing a continuous space representation of the discrete space and sampled signal by using a suitable interpolation method. NP Windows requires only a small number of observed signal samples to estimate ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A Physics-Based Analysis of Image Appearance Models

    Publication Year: 2011, Page(s):1681 - 1688
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (879 KB) | HTML iconHTML Multimedia Media

    Linear and multilinear models (PCA, 3DMM, AAM/ASM, and multilinear tensors) of object shape/appearance have been very popular in computer vision. In this paper, we analyze the applicability of these heuristic models from the fundamental physical laws of object motion and image formation. We prove that under suitable conditions, the image appearance space can be closely approximated to be multiline... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Meta-Recognition: The Theory and Practice of Recognition Score Analysis

    Publication Year: 2011, Page(s):1689 - 1695
    Cited by:  Papers (23)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1161 KB) | HTML iconHTML

    In this paper, we define meta-recognition, a performance prediction method for recognition algorithms, and examine the theoretical basis for its postrecognition score analysis form through the use of the statistical extreme value theory (EVT). The ability to predict the performance of a recognition system based on its outputs for each match instance is desirable for a number of important reasons, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IEEE Computer Society OnlinePlus for TPAMI

    Publication Year: 2011, Page(s): 1696
    Request permission for commercial reuse | PDF file iconPDF (522 KB)
    Freely Available from IEEE
  • TPAMI Information for authors

    Publication Year: 2011, Page(s): c3
    Request permission for commercial reuse | PDF file iconPDF (162 KB)
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2011, Page(s): c4
    Request permission for commercial reuse | PDF file iconPDF (149 KB)
    Freely Available from IEEE

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
e-mail: daf@illinois.edu