IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 9 • Sept. 2010

Filter Results

Displaying Results 1 - 17 of 17
  • [Front cover]

    Publication Year: 2010, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (178 KB)
    Freely Available from IEEE
  • [Inside front cover]

    Publication Year: 2010, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (139 KB)
    Freely Available from IEEE
  • Color to Gray: Visual Cue Preservation

    Publication Year: 2010, Page(s):1537 - 1552
    Cited by:  Papers (58)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3827 KB) | HTML iconHTML

    Both commercial and scientific applications often need to transform color images into gray-scale images, e.g., to reduce the publication cost in printing color images or to help color blind people see visual cues of color images. However, conventional color to gray algorithms are not ready for practical applications because they encounter the following problems: 1) Visual cues are not well defined... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coupled Prediction Classification for Robust Visual Tracking

    Publication Year: 2010, Page(s):1553 - 1567
    Cited by:  Papers (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3835 KB) | HTML iconHTML

    This paper addresses the problem of robust template tracking in image sequences. Our work falls within the discriminative framework in which the observations at each frame yield direct probabilistic predictions of the state of the target. Our primary contribution is that we explicitly address the problem that the prediction accuracy for different observations varies, and in some cases, can be very... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient Sequential Correspondence Selection by Cosegmentation

    Publication Year: 2010, Page(s):1568 - 1581
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5373 KB) | HTML iconHTML

    In many retrieval, object recognition, and wide-baseline stereo methods, correspondences of interest points (distinguished regions) are commonly established by matching compact descriptors such as SIFTs. We show that a subsequent cosegmentation process coupled with a quasi-optimal sequential decision process leads to a correspondence verification procedure that 1) has high precision (is highly dis... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluating Color Descriptors for Object and Scene Recognition

    Publication Year: 2010, Page(s):1582 - 1596
    Cited by:  Papers (724)  |  Patents (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3223 KB) | HTML iconHTML

    Image category recognition is important to access visual information on the level of objects and scene types. So far, intensity-based descriptors have been widely used for feature extraction at salient points. To increase illumination invariance and discriminative power, color descriptors have been proposed. Because many different descriptors exist, a structured overview is required of color invar... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Geometric Feature Extraction by a Multimarked Point Process

    Publication Year: 2010, Page(s):1597 - 1609
    Cited by:  Papers (27)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4630 KB) | HTML iconHTML

    This paper presents a new stochastic marked point process for describing images in terms of a finite library of geometric objects. Image analysis based on conventional marked point processes has already produced convincing results but at the expense of parameter tuning, computing time, and model specificity. Our more general multimarked point process has simpler parametric setting, yields notably ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Local-Learning-Based Feature Selection for High-Dimensional Data Analysis

    Publication Year: 2010, Page(s):1610 - 1626
    Cited by:  Papers (106)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (2518 KB) | HTML iconHTML Multimedia Media

    This paper considers feature selection for data classification in the presence of a huge number of irrelevant features. We propose a new feature-selection algorithm that addresses several major issues with prior work, including problems with algorithm implementation, computational complexity, and solution accuracy. The key idea is to decompose an arbitrarily complex nonlinear problem into a set of... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Object Detection with Discriminatively Trained Part-Based Models

    Publication Year: 2010, Page(s):1627 - 1645
    Cited by:  Papers (2593)  |  Patents (43)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5631 KB) | HTML iconHTML

    We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL data sets. Our system re... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Range Flow in Varying Illumination: Algorithms and Comparisons

    Publication Year: 2010, Page(s):1646 - 1658
    Cited by:  Papers (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3859 KB) | HTML iconHTML

    We extend estimation of range flow to handle brightness changes in image data caused by inhomogeneous illumination. Standard range flow computes 3D velocity fields using both range and intensity image sequences. Toward this end, range flow estimation combines a depth change model with a brightness constancy model. However, local brightness is generally not preserved when object surfaces rotate rel... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Skewed Rotation Symmetry Group Detection

    Publication Year: 2010, Page(s):1659 - 1672
    Cited by:  Papers (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5112 KB) | HTML iconHTML Multimedia Media

    We present a novel and effective algorithm for affinely skewed rotation symmetry group detection from real-world images. We define a complete skewed rotation symmetry detection problem as discovering five independent properties of a skewed rotation symmetry group: 1) the center of rotation, 2) the affine deformation, 3) the type of the symmetry group, 4) the cardinality of the symmetry group, and ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stages as Models of Scene Geometry

    Publication Year: 2010, Page(s):1673 - 1687
    Cited by:  Papers (28)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (5180 KB) | HTML iconHTML

    Reconstruction of 3D scene geometry is an important element for scene understanding, autonomous vehicle and robot navigation, image retrieval, and 3D television. We propose accounting for the inherent structure of the visual world when trying to solve the scene reconstruction problem. Consequently, we identify geometric scene categorization as the first step toward robust and efficient depth estim... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Training-Free, Generic Object Detection Using Locally Adaptive Regression Kernels

    Publication Year: 2010, Page(s):1688 - 1704
    Cited by:  Papers (51)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4645 KB) | HTML iconHTML

    We present a generic detection/localization algorithm capable of searching for a visual object of interest without training. The proposed method operates using a single example of an object of interest to find similar matches, does not require prior knowledge (learning) about objects being sought, and does not require any preprocessing step or segmentation of a target image. Our method is based on... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • WLD: A Robust Local Image Descriptor

    Publication Year: 2010, Page(s):1705 - 1720
    Cited by:  Papers (332)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3196 KB) | HTML iconHTML

    Inspired by Weber's Law, this paper proposes a simple, yet very powerful and robust local descriptor, called the Weber Local Descriptor (WLD). It is based on the fact that human perception of a pattern depends not only on the change of a stimulus (such as sound, lighting) but also on the original intensity of the stimulus. Specifically, WLD consists of two components: differential excitation and o... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Resolution Enhancement in Multi-Image Stereo

    Publication Year: 2010, Page(s):1721 - 1728
    Cited by:  Papers (10)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1867 KB) | HTML iconHTML

    Under stereo settings, the twin problems of image superresolution (SR) and high-resolution (HR) depth estimation are intertwined. The subpixel registration information required for image superresolution is tightly coupled to the 3D structure. The effects of parallax and pixel averaging (inherent in the downsampling process) preclude a priori estimation of pixel motion for superresolution. These fa... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TPAMI Information for authors

    Publication Year: 2010, Page(s): c3
    Request permission for commercial reuse | PDF file iconPDF (139 KB)
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2010, Page(s): c4
    Request permission for commercial reuse | PDF file iconPDF (178 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