By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 10 • Date Oct. 2005

Filter Results

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

    Publication Year: 2005, Page(s): c1
    Request permission for commercial reuse | PDF file iconPDF (137 KB)
    Freely Available from IEEE
  • [Inside front cover]

    Publication Year: 2005, Page(s): c2
    Request permission for commercial reuse | PDF file iconPDF (76 KB)
    Freely Available from IEEE
  • Recognition and verification of unconstrained handwritten words

    Publication Year: 2005, Page(s):1509 - 1522
    Cited by:  Papers (42)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1327 KB) | HTML iconHTML

    This paper presents a novel approach for the verification of the word hypotheses generated by a large vocabulary, offline handwritten word recognition system. Given a word image, the recognition system produces a ranked list of the N-best recognition hypotheses consisting of text transcripts, segmentation boundaries of the word hypotheses into characters, and recognition scores. The verification c... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Guided-MLESAC: faster image transform estimation by using matching priors

    Publication Year: 2005, Page(s):1523 - 1535
    Cited by:  Papers (68)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1692 KB) | HTML iconHTML

    MLESAC is an established algorithm for maximum-likelihood estimation by random sampling consensus, devised for computing multiview entities like the fundamental matrix from correspondences between image features. A shortcoming of the method is that it assumes that little is known about the prior probabilities of the validities of the correspondences. This paper explains the consequences of that om... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrating relevance feedback techniques for image retrieval using reinforcement learning

    Publication Year: 2005, Page(s):1536 - 1551
    Cited by:  Papers (29)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1859 KB) | HTML iconHTML

    Relevance feedback (RF) is an interactive process which refines the retrievals to a particular query by utilizing the user's feedback on previously retrieved results. Most researchers strive to develop new RF techniques and ignore the advantages of existing ones. In this paper, we propose an image relevance reinforcement learning (IRRL) model for integrating existing RF techniques in a content-bas... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive smoothing via contextual and local discontinuities

    Publication Year: 2005, Page(s):1552 - 1567
    Cited by:  Papers (55)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1130 KB) | HTML iconHTML

    A novel adaptive smoothing approach is proposed for noise removal and feature preservation where two distinct measures are simultaneously adopted to detect discontinuities in an image. Inhomogeneity underlying an image is employed as a multiscale measure to detect contextual discontinuities for feature preservation and control of the smoothing speed, while local spatial gradient is used for detect... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Point processes for unsupervised line network extraction in remote sensing

    Publication Year: 2005, Page(s):1568 - 1579
    Cited by:  Papers (61)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (709 KB) | HTML iconHTML

    This paper addresses the problem of unsupervised extraction of line networks (for example, road or hydrographic networks) from remotely sensed images. We model the target line network by an object process, where the objects correspond to interacting line segments. The prior model, called "quality candy," is designed to exploit as fully as possible the topological properties of the network under co... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimates of error probability for complex Gaussian channels with generalized likelihood ratio detection

    Publication Year: 2005, Page(s):1580 - 1591
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1097 KB) | HTML iconHTML

    We derive approximate expressions for the probability of error in a two-class hypothesis testing problem in which the two hypotheses are characterized by zero-mean complex Gaussian distributions. These error expressions are given in terms of the moments of the test statistic employed and we derive these moments for both the likelihood ratio test, appropriate when class densities are known, and the... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On visualization and aggregation of nearest neighbor classifiers

    Publication Year: 2005, Page(s):1592 - 1602
    Cited by:  Papers (22)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (647 KB) | HTML iconHTML

    Nearest neighbor classification is one of the simplest and most popular methods for statistical pattern recognition. A major issue in k-nearest neighbor classification is how to find an optimal value of the neighborhood parameter k. In practice, this value is generally estimated by the method of cross-validation. However, the ideal value of k in a classification problem not only depends on the ent... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the use of error propagation for statistical validation of computer vision software

    Publication Year: 2005, Page(s):1603 - 1614
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1178 KB) | HTML iconHTML

    Computer vision software is complex, involving many tens of thousands of lines of code. Coding mistakes are not uncommon. When the vision algorithms are run on controlled data which meet all the algorithm assumptions, the results are often statistically predictable. This renders it possible to statistically validate the computer vision software and its associated theoretical derivations. In this p... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A performance evaluation of local descriptors

    Publication Year: 2005, Page(s):1615 - 1630
    Cited by:  Papers (2449)  |  Patents (132)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (4874 KB) | HTML iconHTML

    In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector [Mikolajczyk, K and Schmid, C, 2004]. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Online selection of discriminative tracking features

    Publication Year: 2005, Page(s):1631 - 1643
    Cited by:  Papers (567)  |  Patents (10)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3085 KB) | HTML iconHTML

    This paper presents an online feature selection mechanism for evaluating multiple features while tracking and adjusting the set of features used to improve tracking performance. Our hypothesis is that the features that best discriminate between object and background are also best for tracking the object. Given a set of seed features, we compute log likelihood ratios of class conditional sample den... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Motion layer extraction in the presence of occlusion using graph cuts

    Publication Year: 2005, Page(s):1644 - 1659
    Cited by:  Papers (65)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (3869 KB) | HTML iconHTML

    Extracting layers from video is very important for video representation, analysis, compression, and synthesis. Assuming that a scene can be approximately described by multiple planar regions, this paper describes a robust and novel approach to automatically extract a set of affine or projective transformations induced by these regions, detect the occlusion pixels over multiple consecutive frames, ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing articulated objects using a region-based invariant transform

    Publication Year: 2005, Page(s):1660 - 1665
    Cited by:  Papers (6)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (445 KB) | HTML iconHTML

    In this paper, we present a new method for representing and recognizing objects, based on invariants of the object's regions. We apply the method to articulated objects in low-resolution, noisy range images. Articulated objects such as a back-hoe can have many degrees of freedom, in addition to the unknown variables of viewpoint. Recognizing such an object in an image can involve a search in a hig... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • How to put probabilities on homographies

    Publication Year: 2005, Page(s):1666 - 1670
    Cited by:  Papers (16)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (416 KB) | HTML iconHTML

    We present a family of "normal" distributions over a matrix group together with a simple method for estimating its parameters. In particular, the mean of a set of elements can be calculated. The approach is applied to planar projective homographies, showing that using priors defined in this way improves object recognition. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An improved rotation-invariant thinning algorithm

    Publication Year: 2005, Page(s):1671 - 1674
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (393 KB) | HTML iconHTML

    Ahmed and Ward [Sept. 1995] have recently presented an elegant, rule-based rotation-invariant thinning algorithm to produce a single-pixel wide skeleton from a binary image. We show examples where this algorithm fails on two-pixel wide lines and propose a modified method which corrects this shortcoming based on graph connectivity. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Clustered blockwise PCA for representing visual data

    Publication Year: 2005, Page(s):1675 - 1679
    Cited by:  Papers (9)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (365 KB) | HTML iconHTML

    Principal component analysis (PCA) is extensively used in computer vision and image processing. Since it provides the optimal linear subspace in a least-square sense, it has been used for dimensionality reduction and subspace analysis in various domains. However, its scalability is very limited because of its inherent computational complexity. We introduce a new framework for applying PCA to visua... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Building k edge-disjoint spanning trees of minimum total length for isometric data embedding

    Publication Year: 2005, Page(s):1680 - 1683
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (574 KB) | HTML iconHTML

    Isometric data embedding requires construction of a neighborhood graph that spans all data points so that geodesic distance between any pair of data points could be estimated by distance along the shortest path between the pair on the graph. This paper presents an approach for constructing k-edge-connected neighborhood graphs. It works by finding k edge-disjoint spanning trees the sum of whose tot... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • [Advertisement]

    Publication Year: 2005, Page(s): 1684
    Request permission for commercial reuse | PDF file iconPDF (402 KB)
    Freely Available from IEEE
  • TPAMI Information for authors

    Publication Year: 2005, Page(s): c3
    Request permission for commercial reuse | PDF file iconPDF (76 KB)
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2005, Page(s): c4
    Request permission for commercial reuse | PDF file iconPDF (137 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