By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 7 • July 2006

Filter Results

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

    Publication Year: 2006, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (128 KB)
    Freely Available from IEEE
  • [Inside front cover]

    Publication Year: 2006, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (91 KB)
    Freely Available from IEEE
  • A generative sketch model for human hair analysis and synthesis

    Publication Year: 2006, Page(s):1025 - 1040
    Cited by:  Papers (22)  |  Patents (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4358 KB) | HTML iconHTML

    In this paper, we present a generative sketch model for human hair analysis and synthesis. We treat hair images as 2D piecewise smooth vector (flow) fields and, thus, our representation is view-based in contrast to the physically-based 3D hair models in graphics. The generative model has three levels. The bottom level is the high-frequency band of the hair image. The middle level is a piecewise sm... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Minimum classification error training for online handwriting recognition

    Publication Year: 2006, Page(s):1041 - 1051
    Cited by:  Papers (25)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1372 KB) | HTML iconHTML

    This paper describes an application of the minimum classification error (MCE) criterion to the problem of recognizing online unconstrained-style characters and words. We describe an HMM-based, character and word-level MCE training aimed at minimizing the character or word error rate while enabling flexibility in writing style through the use of multiple allographs per character. Experiments on a w... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recovering 3D human body configurations using shape contexts

    Publication Year: 2006, Page(s):1052 - 1062
    Cited by:  Papers (130)  |  Patents (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2731 KB) | HTML iconHTML

    The problem we consider in this paper is to take a single two-dimensional image containing a human figure, locate the joint positions, and use these to estimate the body configuration and pose in three-dimensional space. The basic approach is to store a number of exemplar 2D views of the human body in a variety of different configurations and viewpoints with respect to the camera. On each of these... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A locally constrained watershed transform

    Publication Year: 2006, Page(s):1063 - 1074
    Cited by:  Papers (27)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1808 KB) | HTML iconHTML

    The watershed transform, from mathematical morphology, is a powerful and flexible tool for segmentation. However, it does not allow a priori knowledge relating to characteristics of region boundaries to be included in the way that other approaches do. This paper introduces the locally constrained watershed transform, which includes border constraints by modifying the underlying path definition upo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Edge-preserving image denoising and estimation of discontinuous surfaces

    Publication Year: 2006, Page(s):1075 - 1087
    Cited by:  Papers (40)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3702 KB) | HTML iconHTML

    In this paper, we are interested in the problem of estimating a discontinuous surface from noisy data. A novel procedure for this problem is proposed based on local linear kernel smoothing, in which local neighborhoods are adapted to the local smoothness of the surface measured by the observed data. The procedure can therefore remove noise correctly in continuity regions of the surface and preserv... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval

    Publication Year: 2006, Page(s):1088 - 1099
    Cited by:  Papers (399)  |  Patents (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3114 KB) | HTML iconHTML

    Relevance feedback schemes based on support vector machines (SVM) have been widely used in content-based image retrieval (CBIR). However, the performance of SVM-based relevance feedback is often poor when the number of labeled positive feedback samples is small. This is mainly due to three reasons: 1) an SVM classifier is unstable on a small-sized training set, 2) SVM's optimal hyperplane may be b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning weighted metrics to minimize nearest-neighbor classification error

    Publication Year: 2006, Page(s):1100 - 1110
    Cited by:  Papers (80)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1563 KB) | HTML iconHTML

    In order to optimize the accuracy of the nearest-neighbor classification rule, a weighted distance is proposed, along with algorithms to automatically learn the corresponding weights. These weights may be specific for each class and feature, for each individual prototype, or for both. The learning algorithms are derived by (approximately) minimizing the leaving-one-out classification error of the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rapid object indexing using locality sensitive hashing and joint 3D-signature space estimation

    Publication Year: 2006, Page(s):1111 - 1126
    Cited by:  Papers (43)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1356 KB) | HTML iconHTML

    We propose a new method for rapid 3D object indexing that combines feature-based methods with coarse alignment-based matching techniques. Our approach achieves a sublinear complexity on the number of models, maintaining at the same time a high degree of performance for real 3D sensed data that is acquired in largely uncontrolled settings. The key component of our method is to first index surface d... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A systolic algorithm for Euclidean distance transform

    Publication Year: 2006, Page(s):1127 - 1134
    Cited by:  Papers (5)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1685 KB) | HTML iconHTML

    The Euclidean distance transform is one of the fundamental operations in image processing. It has been widely used in computer vision, pattern recognition, morphological filtering, and robotics. This paper proposes a systolic algorithm that computes the Euclidean distance map of an N times N binary image in 3N clocks on 2N2 processing cells. The algorithm is designed so that the hardwar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Structure from motion with wide circular field of view cameras

    Publication Year: 2006, Page(s):1135 - 1149
    Cited by:  Papers (87)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2157 KB) | HTML iconHTML

    This paper presents a method for fully automatic and robust estimation of two-view geometry, autocalibration, and 3D metric reconstruction from point correspondences in images taken by cameras with wide circular field of view. We focus on cameras which have more than 180deg field of view and for which the standard perspective camera model is not sufficient, e.g., the cameras equipped with circular... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Full-frame video stabilization with motion inpainting

    Publication Year: 2006, Page(s):1150 - 1163
    Cited by:  Papers (164)  |  Patents (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4095 KB) | HTML iconHTML

    Video stabilization is an important video enhancement technology which aims at removing annoying shaky motion from videos. We propose a practical and robust approach of video stabilization that produces full-frame stabilized videos with good visual quality. While most previous methods end up with producing smaller size stabilized videos, our completion method can produce full-frame videos by natur... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Detection and analysis of hair

    Publication Year: 2006, Page(s):1164 - 1169
    Cited by:  Papers (40)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2039 KB) | HTML iconHTML

    We develop computational models for measuring hair appearance for comparing different people. The models and methods developed have applications to person recognition and image indexing. An automatic hair detection algorithm is described and results reported. A multidimensional representation of hair appearance is presented and computational algorithms are described. Results on a data set of 524 s... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Rotation recovery from spherical images without correspondences

    Publication Year: 2006, Page(s):1170 - 1175
    Cited by:  Papers (40)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (912 KB) | HTML iconHTML

    This paper addresses the problem of rotation estimation directly from images defined on the sphere and without correspondence. The method is particularly useful for the alignment of large rotations and has potential impact on 3D shape alignment. The foundation of the method lies in the fact that the spherical harmonic coefficients undergo a unitary mapping when the original image is rotated. The c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion and shape recovery based on iterative stabilization for modest deviation from planar motion

    Publication Year: 2006, Page(s):1176 - 1181
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1180 KB) | HTML iconHTML

    We describe an iterative stabilization method that can simultaneously recover camera motion and 3D shape from an image sequence captured under modest deviation from planar motion. This technique iteratively applies a factorization method based on planar motion and can approximate the observed image points to the 2D points projected under planar motion by stabilizing the camera motion. We apply the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • IEEE ReadyNotes from the Computer Society

    Publication Year: 2006, Page(s): 1182
    Request permission for commercial reuse | PDF file iconPDF (66 KB)
    Freely Available from IEEE
  • IEEE Computer Society celebrates two 60-year anniversaries

    Publication Year: 2006, Page(s): 1183
    Request permission for commercial reuse | PDF file iconPDF (102 KB)
    Freely Available from IEEE
  • Join the IEEE Computer Society

    Publication Year: 2006, Page(s): 1184
    Request permission for commercial reuse | PDF file iconPDF (43 KB)
    Freely Available from IEEE
  • TPAMI Information for authors

    Publication Year: 2006, Page(s): c3
    Request permission for commercial reuse | PDF file iconPDF (91 KB)
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2006, Page(s): c4
    Request permission for commercial reuse | PDF file iconPDF (128 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
Sven Dickinson
University of Toronto
e-mail: sven@cs.toronto.edu