By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 12 • Date Dec. 2007

Filter Results

Displaying Results 1 - 23 of 23
  • [Front cover]

    Publication Year: 2007, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (138 KB)
    Freely Available from IEEE
  • [Inside front cover]

    Publication Year: 2007, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (85 KB)
    Freely Available from IEEE
  • From Scores to Face Templates: A Model-Based Approach

    Publication Year: 2007, Page(s):2065 - 2078
    Cited by:  Papers (12)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3145 KB) | HTML iconHTML

    Regeneration of templates from match scores has security and privacy implications related to any biometric authentication system. We propose a novel paradigm to reconstruct face templates from match scores using a linear approach. It proceeds by first modeling the behavior of the given face recognition algorithm by an affine transformation. The goal of the modeling is to approximate the distances ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic Graph Cuts for Efficient Inference in Markov Random Fields

    Publication Year: 2007, Page(s):2079 - 2088
    Cited by:  Papers (82)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1156 KB) | HTML iconHTML

    In this paper, we present a fast new fully dynamic algorithm for the st-mincut/max-flow problem. We show how this algorithm can be used to efficiently compute MAP solutions for certain dynamically changing MRF models in computer vision such as image segmentation. Specifically, given the solution of the max-flow problem on a graph, the dynamic algorithm efficiently computes the maximum flow in a mo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Flexible Spatial Configuration of Local Image Features

    Publication Year: 2007, Page(s):2089 - 2104
    Cited by:  Papers (36)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4640 KB) | HTML iconHTML

    Local image features have been designed to be informative and repeatable under rigid transformations and illumination deformations. Even though current state-of-the-art local image features present a high degree of repeatability, their local appearance alone usually does not bring enough discriminative power to support a reliable matching, resulting in a relatively high number of mismatches in the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Infinitely Divisible Cascades to Model the Statistics of Natural Images

    Publication Year: 2007, Page(s):2105 - 2119
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1704 KB) | HTML iconHTML

    We propose to model the statistics of natural images, thanks to the large class of stochastic processes called Infinitely Divisible Cascades (IDCs). IDCs were first introduced in one dimension to provide multifractal time series to model the so-called intermittency phenomenon in hydrodynamical turbulence. We have extended the definition of scalar IDCs from one to N dimensions and com... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Representing Images Using Nonorthogonal Haar-Like Bases

    Publication Year: 2007, Page(s):2120 - 2134
    Cited by:  Papers (18)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3075 KB) | HTML iconHTML

    The efficient and compact representation of images is a fundamental problem in computer vision. In this paper, we propose methods that use Haar-like binary box functions to represent a single image or a set of images. A desirable property of these box functions is that their inner product operation with an image can be computed very efficiently. We propose two closely related novel subspace method... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Nonsmooth Optimization Techniques for Semisupervised Classification

    Publication Year: 2007, Page(s):2135 - 2142
    Cited by:  Papers (21)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1287 KB) | HTML iconHTML

    We apply nonsmooth optimization techniques to classification problems, with particular reference to the transductive support vector machine (TSVM) approach, where the considered decision function is nonconvex and nondifferentiable, hence difficult to minimize. We present some numerical results obtained by running the proposed method on some standard test problems drawn from the binary classificati... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Orthogonal Neighborhood Preserving Projections: A Projection-Based Dimensionality Reduction Technique

    Publication Year: 2007, Page(s):2143 - 2156
    Cited by:  Papers (121)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2815 KB) | HTML iconHTML

    This paper considers the problem of dimensionality reduction by orthogonal projection techniques. The main feature of the proposed techniques is that they attempt to preserve both the intrinsic neighborhood geometry of the data samples and the global geometry. In particular, we propose a method, named orthogonal neighborhood preserving projections, which works by first building an "affinity" graph... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Object Tracking Via Online Dynamic Spatial Bias Appearance Models

    Publication Year: 2007, Page(s):2157 - 2169
    Cited by:  Papers (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3402 KB) | HTML iconHTML

    This paper presents a robust object tracking method via a spatial bias appearance model learned dynamically in video. Motivated by the attention shifting among local regions of a human vision system during object tracking, we propose to partition an object into regions with different confidences and track the object using a dynamic spatial bias appearance model (DSBAM) estimated from region confid... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bayesian Analysis of Lidar Signals with Multiple Returns

    Publication Year: 2007, Page(s):2170 - 2180
    Cited by:  Papers (28)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1416 KB) | HTML iconHTML

    Time-correlated single photon counting and burst illumination laser data can be used for range profiling and target classification. In general, the problem is to analyze the response from a histogram of either photon counts or integrated intensities to assess the number, positions, and amplitudes of the reflected returns from object surfaces. The goal of our work is a complete characterization of ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiscale Joint Segmentation and Registration of Image Morphology

    Publication Year: 2007, Page(s):2181 - 2194
    Cited by:  Papers (34)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2157 KB) | HTML iconHTML

    Multimodal image registration significantly benefits from previous denoising and structure segmentation and vice versa. In particular, combined information of different image modalities makes segmentation significantly more robust. Indeed, fundamental tasks in image processing are highly interdependent. A variational approach is presented, which combines the detection of corresponding edges, an ed... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Three-Dimensional Surface Mesh Segmentation Using Curvedness-Based Region Growing Approach

    Publication Year: 2007, Page(s):2195 - 2204
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1436 KB) | HTML iconHTML

    A new parameter-free graph-morphology-based segmentation algorithm is proposed to address the problem of partitioning a 3D triangular mesh into disjoint submeshes that correspond to the physical parts of the underlying object. Curvedness, which is a rotation and translation invariant shape descriptor, is computed at every vertex in the input triangulation. Iterative graph dilation and morphologica... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust Recovery of Shapes with Unknown Topology from the Dual Space

    Publication Year: 2007, Page(s):2205 - 2216
    Cited by:  Papers (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1864 KB) | HTML iconHTML

    In this paper, we address the problem of reconstructing an object surface from silhouettes. Previous works by other authors have shown that, based on the principle of duality, surface points can be recovered, theoretically, as the dual to the tangent plane space of the object. In practice, however, the identification of tangent basis in the tangent plane space is not trivial given a set of discret... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Iterative Extensions of the Sturm/Triggs Algorithm: Convergence and Nonconvergence

    Publication Year: 2007, Page(s):2217 - 2233
    Cited by:  Papers (49)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1561 KB) | HTML iconHTML

    We give the first complete theoretical convergence analysis for the iterative extensions of the Sturm/Triggs algorithm. We show that the simplest extension, SIESTA, converges to nonsense results. Another proposed extension has similar problems, and experiments with "balanced" iterations show that they can fail to converge or become unstable. We present CIESTA, an algorithm that avoids these proble... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Automatic Age Estimation Based on Facial Aging Patterns

    Publication Year: 2007, Page(s):2234 - 2240
    Cited by:  Papers (230)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1130 KB) | HTML iconHTML

    While recognition of most facial variations, such as identity, expression, and gender, has been extensively studied, automatic age estimation has rarely been explored. In contrast to other facial variations, aging variation presents several unique characteristics which make age estimation a challenging task. This paper proposes an automatic age estimation method named AGES (AGing pattErn Subspace)... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiview Stereo via Volumetric Graph-Cuts and Occlusion Robust Photo-Consistency

    Publication Year: 2007, Page(s):2241 - 2246
    Cited by:  Papers (105)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1142 KB) | HTML iconHTML

    This paper presents a volumetric formulation for the multiview stereo problem which is amenable to a computationally tractable global optimization using Graph-cuts. Our approach is to seek the optimal partitioning of 3D space into two regions labeled as "object" and "empty" under a cost functional consisting of the following two terms: 1) A term that forces the boundary between the two regions to ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Actions as Space-Time Shapes

    Publication Year: 2007, Page(s):2247 - 2253
    Cited by:  Papers (526)  |  Patents (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1720 KB) | HTML iconHTML

    Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three-dimensional shapes induced by the silhouettes in the space-time volume. We adopt a recent approach [14] for analyzing 2D shapes and generalize it to deal with volumetric space-time action shapes. Our method utilizes properties of the solu... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 180,000 aritlces in the IEEE Computer Society Digital Library [advertisement]

    Publication Year: 2007, Page(s): 2254
    Request permission for commercial reuse | PDF file iconPDF (114 KB)
    Freely Available from IEEE
  • Join the IEEE Computer Society Today!

    Publication Year: 2007, Page(s): 2255
    Request permission for commercial reuse | PDF file iconPDF (68 KB)
    Freely Available from IEEE
  • Don't let the future pass you by. subscribe to IEEE Intelligent Systems

    Publication Year: 2007, Page(s): 2256
    Request permission for commercial reuse | PDF file iconPDF (1955 KB)
    Freely Available from IEEE
  • TPAMI Information for authors

    Publication Year: 2007, Page(s): c3
    Request permission for commercial reuse | PDF file iconPDF (85 KB)
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2007, Page(s): c4
    Request permission for commercial reuse | PDF file iconPDF (138 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