By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 1 • Date Jan 2004

Filter Results

Displaying Results 1 - 20 of 20
  • The use of force histograms for affine-invariant relative position description

    Page(s): 1 - 18
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4968 KB)  

    Affine invariant descriptors have been widely used for recognition of objects regardless of their position, size, and orientation in space. Examples of color, texture, and shape descriptors abound in the literature. However, many tasks in computer vision require looking not only at single objects or regions in images but also at their spatial relationships. In an earlier work, we showed that the relative position of two objects can be quantitatively described by a histogram of forces. Here, we study how affine transformations affect this descriptor. The position of an object with respect to another changes when the objects are affine transformed. We analyze the link between: 1) the applied affinity, 2) the relative position before transformation (described through a force histogram), and 3) the relative position after transformation. We show that any two of these elements allow the third one to be recovered. Moreover, it is possible to determine whether (or how well) two relative positions are actually related through an affine transformation. If they are not, the affinity that best approximates the unknown transformation can be retrieved, and the quality of the approximation assessed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The image foresting transform: theory, algorithms, and applications

    Page(s): 19 - 29
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1616 KB)  

    The image foresting transform (IFT) is a graph-based approach to the design of image processing operators based on connectivity. It naturally leads to correct and efficient implementations and to a better understanding of how different operators relate to each other. We give here a precise definition of the IFT, and a procedure to compute it-a generalization of Dijkstra's algorithm-with a proof of correctness. We also discuss implementation issues and illustrate the use of the IFT in a few applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Affine invariant features from the trace transform

    Page(s): 30 - 44
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (4402 KB)  

    The trace transform is a generalization of the Radon transform that allows one to construct image features that are invariant to a chosen group of image transformations. In this paper, we propose a methodology and appropriate functionals that can be computed from the image function and which can be used to calculate features invariant to the group of affine transforms. We demonstrate the usefulness of the constructed image descriptors in retrieving images from an image database and compare it with relevant state-of-the-art object retrieval methods. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stereo reconstruction from multiperspective panoramas

    Page(s): 45 - 62
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (6601 KB)  

    A new approach to computing a panoramic (360 degrees) depth map is presented in this paper. Our approach uses a large collection of images taken by a camera whose motion has been constrained to planar concentric circles. We resample regular perspective images to produce a set of multiperspective panoramas and then compute depth maps directly from these resampled panoramas. Our panoramas sample uniformly in three dimensions: rotation angle, inverse radial distance, and vertical elevation. The use of multiperspective panoramas eliminates the limited overlap present in the original input images and, thus, problems as in conventional multibaseline stereo can be avoided. Our approach differs from stereo matching of single-perspective panoramic images taken from different locations, where the epipolar constraints are sine curves. For our multiperspective panoramas, the epipolar geometry, to the first order approximation, consists of horizontal lines. Therefore, any traditional stereo algorithm can be applied to multiperspective panoramas with little modification. In this paper, we describe two reconstruction algorithms. The first is a cylinder sweep algorithm that uses a small number of resampled multiperspective panoramas to obtain dense 3D reconstruction. The second algorithm, in contrast, uses a large number of multiperspective panoramas and takes advantage of the approximate horizontal epipolar geometry inherent in multiperspective panoramas. It comprises a novel and efficient 1D multibaseline matching technique, followed by tensor voting to extract the depth surface. Experiments show that our algorithms are capable of producing comparable high quality depth maps which can be used for applications such as view interpolation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Smart nonlinear diffusion: a probabilistic approach

    Page(s): 63 - 72
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1896 KB)  

    In this paper, a stochastic interpretation of nonlinear diffusion equations used for image filtering is proposed. This is achieved by relating the problem of evolving/smoothing images to that of tracking the transition probability density functions of an underlying random process. We show that such an interpretation of, e.g., Perona-Malik equation, in turn allows additional insight and sufficient flexibility to further investigate some outstanding problems of nonlinear diffusion techniques. In particular, upon unraveling the limitations as well as the advantages of such an equation, we are able to propose a new approach which is demonstrated to improve performance over existing approaches and, more importantly, to lift the longstanding problem of a stopping criterion for a nonlinear evolution equation with no data term constraint. Substantiating examples in image enhancement and segmentation are provided. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Transparent surface modeling from a pair of polarization images

    Page(s): 73 - 82
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2201 KB)  

    We propose a method for measuring surface shapes of transparent objects by using a polarizing filter. Generally, the light reflected from an object is partially polarized. The degree of polarization depends upon the incident angle, which, in turn, depends upon the surface normal. Therefore, we can obtain surface normals of objects by observing the degree of polarization at each surface point. Unfortunately, the correspondence between the degree of polarization and the surface normal is not one to one. Hence, to obtain the correct surface normal, we have to solve the ambiguity problem. In this paper, we introduce a method to solve the ambiguity by comparing the polarization data in two objects, i.e., normal position and tilted with small angle position. We also discuss the geometrical features of the object surface and propose a method for matching two sets of polarization data at identical points on the object surface. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fundamental limits of reconstruction-based superresolution algorithms under local translation

    Page(s): 83 - 97
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5485 KB)  

    Superresolution is a technique that can produce images of a higher resolution than that of the originally captured ones. Nevertheless, improvement in resolution using such a technique is very limited in practice. This makes it significant to study the problem: "Do fundamental limits exist for Superresolution?" In this paper, we focus on a major class of superresolution algorithms, called the reconstruction-based algorithms, which compute high-resolution images by simulating the image formation process. Assuming local translation among low-resolution images, this paper is the first attempt to determine the explicit limits of reconstruction-based algorithms, under both real and synthetic conditions. Based on the perturbation theory of linear systems, we obtain the superresolution limits from the conditioning analysis of the coefficient matrix. Moreover, we determine the number of low-resolution images that are sufficient to achieve the limit. Both real and synthetic experiments are carried out to verify our analysis. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reactive control of zoom while fixating using perspective and affine cameras

    Page(s): 98 - 112
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (6380 KB)  

    This paper describes reactive visual methods of controlling the zoom setting of the lens of an active camera while fixating upon an object. The first method assumes a perspective projection and adjusts zoom to preserve the ratio of focal length to scene depth. The active camera is constrained to rotate, permitting self-calibration from the image motion of points on the static background. A planar structure from motion algorithm is used to recover the depth of the foreground. The foreground-background segmentation exploits the properties of the two different interimage homographies which are observed. The fixation point is updated by transfer via the observed planar structure. The planar method is shown to work on real imagery, but results from simulated data suggest that its extension to general 3D structure is problematical under realistic viewing and noise regimes. The second method assumes an affine projection. It requires no self-calibration and the zooming camera may move generally. Fixation is again updated using transfer, but now via the affine structure recovered by factorization. Analysis of the projection matrices allows the relative scale of the affine bases in different views to be found in a number of ways and, hence, controlled to unity. The various ways are compared and the best used on real imagery captured from an active camera fitted with a controllable zoom lens in both look-move and continuous operation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust histogram construction from color invariants for object recognition

    Page(s): 113 - 118
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (825 KB)  

    An effective object recognition scheme is to represent and match images on the basis of histograms derived from photometric color invariants. A drawback, however, is that certain color invariant values become very unstable in the presence of sensor noise. To suppress the effect of noise for unstable color invariant values, in this paper, histograms are computed by variable kernel density estimators. To apply variable kernel density estimation in a principled way, models are proposed for the propagation of sensor noise through color invariant variables. As a result, the associated uncertainty is obtained for each color invariant value. The associated uncertainty is used to derive the parameterization of the variable kernel for the purpose of robust histogram construction. It is empirically verified that the proposed density estimator compares favorably to traditional histogram schemes for the purpose of object recognition. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Topologically faithful fitting of simple closed curves

    Page(s): 118 - 123
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1031 KB)  

    Implicit representations of curves have certain advantages over explicit representation, one of them being the ability to determine with ease whether a point is inside or outside the curve (inside-outside functions). However, save for some special cases, it is not known how to construct implicit representations which are guaranteed to preserve the curve's topology. As a result, points may be erroneously classified with respect to the curve. The paper offers to overcome this problem by using a representation which is guaranteed to yield the correct topology of a simple closed curve by using homeomorphic mappings of the plane to itself. If such a map carries the curve onto the unit circle, then a point is inside the curve if and only if its image is inside the unit circle. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Online handwritten script recognition

    Page(s): 124 - 130
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1530 KB)  

    Automatic identification of handwritten script facilitates many important applications such as automatic transcription of multilingual documents and search for documents on the Web containing a particular script. The increase in usage of handheld devices which accept handwritten input has created a growing demand for algorithms that can efficiently analyze and retrieve handwritten data. This paper proposes a method to classify words and lines in an online handwritten document into one of the six major scripts: Arabic, Cyrillic, Devnagari, Han, Hebrew, or Roman. The classification is based on 11 different spatial and temporal features extracted from the strokes of the words. The proposed system attains an overall classification accuracy of 87.1 percent at the word level with 5-fold cross validation on a data set containing 13,379 words. The classification accuracy improves to 95 percent as the number of words in the test sample is increased to five, and to 95.5 percent for complete text lines consisting of an average of seven words. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-dimensional PCA: a new approach to appearance-based face representation and recognition

    Page(s): 131 - 137
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2462 KB)  

    In this paper, a new technique coined two-dimensional principal component analysis (2DPCA) is developed for image representation. As opposed to PCA, 2DPCA is based on 2D image matrices rather than 1D vectors so the image matrix does not need to be transformed into a vector prior to feature extraction. Instead, an image covariance matrix is constructed directly using the original image matrices, and its eigenvectors are derived for image feature extraction. To test 2DPCA and evaluate its performance, a series of experiments were performed on three face image databases: ORL, AR, and Yale face databases. The recognition rate across all trials was higher using 2DPCA than PCA. The experimental results also indicated that the extraction of image features is computationally more efficient using 2DPCA than PCA. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 2003 Reviewers list

    Page(s): 138 - 141
    Save to Project icon | Request Permissions | PDF file iconPDF (181 KB)  
    Freely Available from IEEE
  • IEEE Transactions on Pattern Analysis and Machine Intelligence

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (245 KB)  
    Freely Available from IEEE
  • IEEE Transactions on Pattern Analysis and Machine Intelligence

    Page(s): 0_2
    Save to Project icon | Request Permissions | PDF file iconPDF (224 KB)  
    Freely Available from IEEE
  • New for 2004!

    Page(s): 142
    Save to Project icon | Request Permissions | PDF file iconPDF (74 KB)  
    Freely Available from IEEE
  • New for 2004!

    Page(s): 143
    Save to Project icon | Request Permissions | PDF file iconPDF (74 KB)  
    Freely Available from IEEE
  • Not a member yet?

    Page(s): 144
    Save to Project icon | Request Permissions | PDF file iconPDF (98 KB)  
    Freely Available from IEEE
  • Information for authors

    Page(s): 145
    Save to Project icon | Request Permissions | PDF file iconPDF (224 KB)  
    Freely Available from IEEE
  • IEEE Computer Society

    Page(s): 146
    Save to Project icon | Request Permissions | PDF file iconPDF (245 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