By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 7 • Date July 2004

Filter Results

Displaying Results 1 - 18 of 18
  • [Front cover]

    Publication Year: 2004 , Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (61 KB)  
    Freely Available from IEEE
  • [Inside front cover]

    Publication Year: 2004 , Page(s): c2
    Save to Project icon | Request Permissions | PDF file iconPDF (56 KB)  
    Freely Available from IEEE
  • Focus-of-attention from local color symmetries

    Publication Year: 2004 , Page(s): 817 - 830
    Cited by:  Papers (22)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3231 KB) |  | HTML iconHTML  

    In this paper, a continuous valued measure for local color symmetry is introduced. The new algorithm is an extension of the successful gray value-based symmetry map proposed by Reisfeld et al. The use of color facilitates the detection of focus points (FPs) on objects that are difficult to detect using gray-value contrast only. The detection of FPs is aimed at guiding the attention of an object recognition system; therefore, FPs have to fulfill three major requirements: stability, distinctiveness, and usability. The proposed algorithm is evaluated for these criteria and compared with the gray value-based symmetry measure and two other methods from the literature. Stability is tested against noise, object rotation, and variations of lighting. As a measure for the distinctiveness of FPs, the principal components of FP-centered windows are compared with those of windows at randomly chosen points on a large database of natural images. Finally, usability is evaluated in the context of an object recognition task. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiresolution histograms and their use for recognition

    Publication Year: 2004 , Page(s): 831 - 847
    Cited by:  Papers (66)  |  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3958 KB) |  | HTML iconHTML  

    The histogram of image intensities is used extensively for recognition and for retrieval of images and video from visual databases. A single image histogram, however, suffers from the inability to encode spatial image variation. An obvious way to extend this feature is to compute the histograms of multiple resolutions of an image to form a multiresolution histogram. The multiresolution histogram shares many desirable properties with the plain histogram, including that they are both fast to compute, space efficient, invariant to rigid motions, and robust to noise. In addition, the multiresolution histogram directly encodes spatial information. We describe a simple yet novel matching algorithm based on the multiresolution histogram that uses the differences between histograms of consecutive image resolutions. We evaluate it against five widely used image features. We show that with our simple feature we achieve or exceed the performance obtained with more complicated features. Further, we show our algorithm to be the most efficient and robust. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On pose recovery for generalized visual sensors

    Publication Year: 2004 , Page(s): 848 - 861
    Cited by:  Papers (17)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2320 KB) |  | HTML iconHTML  

    With the advances in imaging technologies for robot or machine vision, new imaging devices are being developed for robot navigation or image-based rendering. However, to satisfy some design criterion, such as image resolution or viewing ranges, these devices are not necessarily being designed to follow the perspective rule and, thus, the imaging rays may not pass through a common point. Such generalized imaging devices may not be perspective and, therefore, their poses cannot be estimated with traditional techniques. In this paper, we propose a systematic method for pose estimation of such a generalized imaging device. We formulate it as a nonperspective n point (NPnP) problem. The case with exact solutions, n = 3, is investigated comprehensively. Approximate solutions can be found for n > 3 in a least-squared-error manner by combining an initial-pose-estimation procedure and an orthogonally iterative procedure. This proposed method can be applied not only to nonperspective imaging devices but also perspective ones. Results from experiments show that our approach can solve the NPnP problem accurately. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Skin color-based video segmentation under time-varying illumination

    Publication Year: 2004 , Page(s): 862 - 877
    Cited by:  Papers (61)  |  Patents (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4518 KB) |  | HTML iconHTML  

    A novel approach for real-time skin segmentation in video sequences is described. The approach enables reliable skin segmentation despite wide variation in illumination during tracking. An explicit second order Markov model is used to predict evolution of the skin-color (HSV) histogram over time. Histograms are dynamically updated based on feedback from the current segmentation and predictions of the Markov model. The evolution of the skin-color distribution at each frame is parameterized by translation, scaling, and rotation in color space. Consequent changes in geometric parameterization of the distribution are propagated by warping and resampling the histogram. The parameters of the discrete-time dynamic Markov model are estimated using maximum likelihood estimation and also evolve over time. The accuracy of the new dynamic skin color segmentation algorithm is compared to that obtained via a static color model. Segmentation accuracy is evaluated using labeled ground-truth video sequences taken from staged experiments and popular movies. An overall increase in segmentation accuracy of up to 24 percent is observed in 17 out of 21 test sequences. In all but one case, the skin-color classification rates for our system were higher, with background classification rates comparable to those of the static segmentation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Higher-order nonlinear priors for surface reconstruction

    Publication Year: 2004 , Page(s): 878 - 891
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1383 KB) |  | HTML iconHTML  

    For surface reconstruction problems with noisy and incomplete range data, a Bayesian estimation approach can improve the overall quality of the surfaces. The Bayesian approach to surface estimation relies on a likelihood term, which ties the surface estimate to the input data, and the prior, which ensures surface smoothness or continuity. This paper introduces a new high-order, nonlinear prior for surface reconstruction. The proposed prior can smooth complex, noisy surfaces, while preserving sharp, geometric features, and it is a natural generalization of edge-preserving methods in image processing, such as anisotropic diffusion. An exact solution would require solving a fourth-order partial differential equation (PDE), which can be difficult with conventional numerical techniques. Our approach is to solve a cascade system of two second-order PDEs, which resembles the original fourth-order system. This strategy is based on the observation that the generalization of image processing to surfaces entails filtering the surface normals. We solve one PDE for processing the normals and one for refitting the surface to the normals. Furthermore, we implement the associated surface deformations using level sets. Hence, the algorithm can accommodate very complex shapes with arbitrary and changing topologies. This paper gives the mathematical formulation and describes the numerical algorithms. We also show results using range and medical data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Camera calibration with one-dimensional objects

    Publication Year: 2004 , Page(s): 892 - 899
    Cited by:  Papers (115)  |  Patents (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (687 KB) |  | HTML iconHTML  

    Camera calibration has been studied extensively in computer vision and photogrammetry and the proposed techniques in the literature include those using 3D apparatus (two or three planes orthogonal to each other or a plane undergoing a pure translation, etc.), 2D objects (planar patterns undergoing unknown motions), and 0D features (self-calibration using unknown scene points). Yet, the paper proposes a new calibration technique using 1D objects (points aligned on a line), thus filling the missing dimension in calibration. In particular, we show that camera calibration is not possible with free-moving 1D objects, but can be solved if one point is fixed. A closed-form solution is developed if six or more observations of such a 1D object are made. For higher accuracy, a nonlinear technique based on the maximum likelihood criterion is then used to refine the estimate. Singularities have also been studied. Besides the theoretical aspect, the proposed technique is also important in practice especially when calibrating multiple cameras mounted apart from each other, where the calibration objects are required to be visible simultaneously. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast branch & bound algorithms for optimal feature selection

    Publication Year: 2004 , Page(s): 900 - 912
    Cited by:  Papers (64)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1919 KB) |  | HTML iconHTML  

    A novel search principle for optimal feature subset selection using the branch & bound method is introduced. Thanks to a simple mechanism for predicting criterion values, a considerable amount of time can be saved by avoiding many slow criterion evaluations. We propose two implementations of the proposed prediction mechanism that are suitable for use with nonrecursive and recursive criterion forms, respectively. Both algorithms find the optimum usually several times faster than any other known branch & bound algorithm. As the algorithm computational efficiency is crucial, due to the exponential nature of the search problem, we also investigate other factors that affect the search performance of all branch & bound algorithms. Using a set of synthetic criteria, we show that the speed of the branch & bound algorithms strongly depends on the diversity among features, feature stability with respect to different subsets, and criterion function dependence on feature set size. We identify the scenarios where the search is accelerated the most dramatically (finish in linear time), as well as the worst conditions. We verify our conclusions experimentally on three real data sets using traditional probabilistic distance criteria. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Spectral filter optimization for the recovery of parameters which describe human skin

    Publication Year: 2004 , Page(s): 913 - 922
    Cited by:  Papers (13)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (707 KB) |  | HTML iconHTML  

    The paper presents a method for finding spectral filters that minimize the error associated with histological parameters characterizing normal skin tissue. These parameters can be recovered from digital images of the skin using a physics-based model of skin coloration. The relationship between the image data and histological parameter values is defined as a mapping function from the image space to the parameter space. The accuracy of this function is determined by the choice of optical filters. An optimization criterion for finding the optimal filters is defined by combing methodology from differential geometry with statistical error analysis. It is shown that the magnitude of errors associated with the optimal filters is typically half of that for typical RGB filters on a three-parameter model of human skin coloration. Finally, other medical image applications are identified to which this generic methodology could be applied. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new convexity measure for polygons

    Publication Year: 2004 , Page(s): 923 - 934
    Cited by:  Papers (31)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1241 KB) |  | HTML iconHTML  

    Convexity estimators are commonly used in the analysis of shape. In this paper, we define and evaluate a new convexity measure for planar regions bounded by polygons. The new convexity measure can be understood as a "boundary-based" measure and in accordance with this it is more sensitive to measured boundary defects than the so called "area-based" convexity measures. When compared with the convexity measure defined as the ratio between the Euclidean perimeter of the convex hull of the measured shape and the Euclidean perimeter of the measured shape then the new convexity measure also shows some advantages-particularly for shapes with holes. The new convexity measure has the following desirable properties: 1) the estimated convexity is always a number from (0, 1], 2) the estimated convexity is I if and only if the measured shape is convex, 3) there are shapes whose estimated convexity is arbitrarily close to 0, 4) the new convexity measure is invariant under similarity transformations, and 5) there is a simple and fast procedure for computing the new convexity measure. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new way to detect arrows in line drawings

    Publication Year: 2004 , Page(s): 935 - 941
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1123 KB) |  | HTML iconHTML  

    A new way of detecting arrows in line drawings is proposed. We provide a set of criteria which are aggregated using the Choquet integral. These criteria are defined from the geometric properties of an arrow. Experimental results on two kinds of line-drawing documents show the interest of our approach. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Multiview panoramic cameras using mirror pyramids

    Publication Year: 2004 , Page(s): 941 - 946
    Cited by:  Papers (15)  |  Patents (18)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (395 KB) |  | HTML iconHTML  

    A mirror pyramid consists of a set of planar mirror faces arranged around an axis of symmetry and inclined to form a pyramid. By strategically positioning a number of conventional cameras around a mirror pyramid, the viewpoints of the cameras' mirror images can be located at a single point within the pyramid and their optical axes pointed in different directions to effectively form a virtual camera with a panoramic field of view. Mirror pyramid-based panoramic cameras have a number of attractive properties, including single-viewpoint imaging, high resolution, and video rate capture. It is also possible to place multiple viewpoints within a single mirror pyramid, yielding compact designs for simultaneous multiview panoramic video rate imaging. V.S. Nalwa (1996) first described some of the basic ideas behind mirror pyramid cameras. We analyze the general class of multiview panoramic cameras, provide a method for designing these cameras, and present experimental results using a prototype we have developed to validate single-pyramid multiview designs. We first give a description of mirror pyramid cameras, including the imaging geometry, and investigate the relationship between the placement of viewpoints within the pyramid and the cameras' field of view (FOV), using simulations to illustrate the concepts. A method for maximizing sensor utilization in a mirror pyramid-based multiview panoramic camera is also presented. Images acquired using the experimental prototype for two viewpoints are shown. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contrast definition for optical coherent polarimetric images

    Publication Year: 2004 , Page(s): 947 - 951
    Cited by:  Papers (13)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (456 KB) |  | HTML iconHTML  

    We consider polarimetric images formed with coherent waves, such as in laser-illuminated imagery or synthetic aperture radar. A definition of the contrast between regions with different polarimetric properties in such images is proposed, and it is shown that the performances of maximum likelihood-based detection and segmentation algorithms are bijective functions of this contrast parameter. This makes it possible to characterize the performance of such algorithms by simply specifying the value of the contrast parameter. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Gaussian MRF rotation-invariant features for image classification

    Publication Year: 2004 , Page(s): 951 - 955
    Cited by:  Papers (37)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (629 KB) |  | HTML iconHTML  

    Features based on Markov random field (MRF) models are sensitive to texture rotation. This paper develops an anisotropic circular Gaussian MRF (ACGMRF) model for retrieving rotation-invariant texture features. To overcome the singularity problem of the least squares estimate method, an approximate least squares estimate method is designed and implemented. Rotation-invariant features are obtained from the ACGMRF model parameters using the discrete Fourier transform. The ACGMRF model is demonstrated to be a statistical improvement over three published methods. The three methods include a Laplacian pyramid, an isotropic circular GMRF (ICGMRF), and gray level cooccurrence probability features. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Eye gaze correction with stereovision for video-teleconferencing

    Publication Year: 2004 , Page(s): 956 - 960
    Cited by:  Papers (11)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (497 KB) |  | HTML iconHTML  

    The lack of eye contact in desktop video teleconferencing substantially reduces the effectiveness of video contents. While expensive and bulky hardware is available on the market to correct eye gaze, researchers have been trying to provide a practical software-based solution to bring video-teleconferencing one step closer to the mass market. This paper presents a novel approach: based on stereo analysis combined with rich domain knowledge (a personalized face model), we synthesize, using graphics hardware, a virtual video that maintains eye contact. A 3D stereo head tracker with a personalized face model is used to compute initial correspondences across two views. More correspondences are then added through template and feature matching. Finally, all the correspondence information is fused together for view synthesis using view morphing techniques. The combined methods greatly enhance the accuracy and robustness of the synthesized views. Our current system is able to generate an eye-gaze corrected video stream at five frames per second on a commodity 1 GHz PC. 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: 2004 , Page(s): c3
    Save to Project icon | Request Permissions | PDF file iconPDF (53 KB)  
    Freely Available from IEEE
  • [Back cover]

    Publication Year: 2004 , Page(s): c4
    Save to Project icon | Request Permissions | PDF file iconPDF (107 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