By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 2 • Date Feb 2001

Filter Results

Displaying Results 1 - 14 of 14
  • Correspondence with cumulative similarity transforms

    Page(s): 222 - 227
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (676 KB) |  | HTML iconHTML  

    A local image transform based on cumulative similarity measures is defined and is shown to enable efficient correspondence and tracking near occluding boundaries. Unlike traditional methods, this transform allows correspondences to be found when the only contrast present is the occluding boundary itself and when the sign of contrast along the boundary is possibly reversed. The transform is based on the idea of a cumulative similarity measure which characterizes the shape of local image homogeneity; both the value of an image at a particular point and the shape of the region with locally similar and connected values is captured. This representation is insensitive to structure beyond an occluding boundary but is sensitive to the shape of the boundary itself, which is often an important cue. We show results comparing this method to traditional least-squares and robust correspondence matching View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • PCA versus LDA

    Page(s): 228 - 233
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (600 KB) |  | HTML iconHTML  

    In the context of the appearance-based paradigm for object recognition, it is generally believed that algorithms based on LDA (linear discriminant analysis) are superior to those based on PCA (principal components analysis). In this communication, we show that this is not always the case. We present our case first by using intuitively plausible arguments and, then, by showing actual results on a face database. Our overall conclusion is that when the training data set is small, PCA can outperform LDA and, also, that PCA is less sensitive to different training data sets View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The role of holistic paradigms in handwritten word recognition

    Page(s): 149 - 164
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2408 KB) |  | HTML iconHTML  

    The holistic paradigm in handwritten word recognition treats the word as a single, indivisible entity and attempts to recognize words from their overall shape, as opposed to their character contents. In this survey, we have attempted to take a fresh look at the potential role of the holistic paradigm in handwritten word recognition. The survey begins with an overview of studies of reading which provide evidence for the existence of a parallel holistic reading process,in both developing and skilled readers. In what we believe is a fresh perspective on handwriting recognition, approaches to recognition are characterized as forming a continuous spectrum based on the visual complexity of the unit of recognition employed and an attempt is made to interpret well-known paradigms of word recognition in this framework. An overview of features, methodologies, representations, and matching techniques employed by holistic approaches is presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generality-based conceptual clustering with probabilistic concepts

    Page(s): 196 - 206
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (408 KB) |  | HTML iconHTML  

    Statistical research in clustering has almost universally focused on data sets described by continuous features and its methods are difficult to apply to tasks involving symbolic features. In addition, these methods are seldom concerned with helping the user in interpreting the results obtained. Machine learning researchers have developed conceptual clustering methods aimed at solving these problems. Following a long term tradition in AI, early conceptual clustering implementations employed logic as the mechanism of concept representation. However, logical representations have been criticized for constraining the resulting cluster structures to be described by necessary and sufficient conditions. An alternative are probabilistic concepts which associate a probability or weight with each property of the concept definition. In this paper, we propose a symbolic hierarchical clustering model that makes use of probabilistic representations and extends the traditional ideas of specificity-generality typically found in machine learning. We propose a parameterized measure that allows users to specify both the number of levels and the degree of generality of each level. By providing some feedback to the user about the balance of the generality of the concepts created at each level and given the intuitive behavior of the user parameter, the system improves user interaction in the clustering process View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Encoding visual information using anisotropic transformations

    Page(s): 207 - 211
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (536 KB) |  | HTML iconHTML  

    The evolution of information in images undergoing fine-to-coarse anisotropic transformations is analyzed by using an approach based on the theory of irreversible transformations. In particular, we show that, when an anisotropic diffusion model is used, local variation of entropy production over space and scale provides the basis for a general method to extract relevant image features View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • First-order tree-type dependence between variables and classification performance

    Page(s): 233 - 239
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (384 KB) |  | HTML iconHTML  

    Structuralization of the covariance matrix reduces the number of parameters to be estimated from the training data and does not affect an increase in the generalization error asymptotically as both the number of dimensions and training sample size grow. A method to benefit from approximately correct assumptions about the first order tree dependence between components of the feature vector is proposed. We use a structured estimate of the covariance matrix to decorrelate and scale the data and to train a single-layer perceptron in the transformed feature space. We show that training the perceptron can reduce negative effects of inexact a priori information. Experiments performed with 13 artificial and 10 real world data sets show that the first-order tree-type dependence model is the most preferable one out of two dozen of the covariance matrix structures investigated View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Empirical Bayesian motion segmentation

    Page(s): 217 - 221
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (652 KB) |  | HTML iconHTML  

    We introduce an empirical Bayesian procedure for the simultaneous segmentation of an observed motion field and estimation of the hyperparameters of a Markov random field prior. The new approach exhibits the Bayesian appeal of incorporating prior beliefs, but requires only a qualitative description of the prior, avoiding the requirement for a quantitative specification of its parameters. This eliminates the need for trial-and-error strategies for the determination of these parameters and leads to better segmentations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The quotient image: class-based re-rendering and recognition with varying illuminations

    Page(s): 129 - 139
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1908 KB) |  | HTML iconHTML  

    The paper addresses the problem of “class-based” image-based recognition and rendering with varying illumination. The rendering problem is defined as follows: Given a single input image of an object and a sample of images with varying illumination conditions of other objects of the same general class, re-render the input image to simulate new illumination conditions. The class-based recognition problem is similarly defined: Given a single image of an object in a database of images of other objects, some of them multiply sampled under varying illumination, identify (match) any novel image of that object under varying illumination with the single image of that object in the database. We focus on Lambertian surface classes and, in particular, the class of human faces. The key result in our approach is based on a definition of an illumination invariant signature image which enables an analytic generation of the image space with varying illumination. We show that a small database of objects-in our experiments as few as two objects-is sufficient for generating the image space with varying illumination of any new object of the class from a single input image of that object. In many cases, the recognition results outperform by far conventional methods and the re-rendering is of remarkable quality considering the size of the database of example images and the mild preprocess required for making the algorithm work View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Self-organization of pulse-coupled oscillators with application to clustering

    Page(s): 180 - 195
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1064 KB) |  | HTML iconHTML  

    We introduce an efficient synchronization model that organizes a population of integrate-and-fire oscillators into stable and structured groups. Each oscillator fires synchronously with all the others within its group, but the groups themselves fire with a constant phase difference. The structure of the synchronized groups depends on the choice of the coupling function. We show that by defining the interaction between oscillators according to the relative distance between them, our model can be used as a general clustering algorithm. Unlike existing models, our model incorporates techniques from relational and prototype-based clustering methods and results in a clustering algorithm that is simple, efficient, robust, unbiased by the size of the clusters, and that can find an arbitrary number of clusters. In addition to helping the model self-organize into stable groups, the synergy between clustering and synchronization reduces the computational complexity significantly. The resulting clustering algorithm has several advantages over conventional clustering techniques. In particular, it can generate a nested sequence of partitions and it can determine the optimum number of clusters in an efficient manner. Moreover, since our approach does not involve optimizing an objective function, it is not sensitive to initialization and it can incorporate nonmetric similarity measures. We illustrate the performance of our algorithms with several synthetic and real data sets View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Robust point correspondence applied to two- and three-dimensional image registration

    Page(s): 165 - 179
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2340 KB) |  | HTML iconHTML  

    Accurate and robust correspondence calculations are very important in many medical and biological applications. Often, the correspondence calculation forms part of a rigid registration algorithm, but accurate correspondences are especially important for elastic registration algorithms and for quantifying changes over time. In this paper, a new correspondence calculation algorithm, CSM (correspondence by sensitivity to movement), is described. A robust corresponding point is calculated by determining the sensitivity of a correspondence to movement of the point being matched. If the correspondence is reliable, a perturbation in the position of this point should not result in a large movement of the correspondence. A measure of reliability is also calculated. This correspondence calculation method is independent of the registration transformation and has been incorporated into both a 2D elastic registration algorithm for warping serial sections and a 3D rigid registration algorithm for registering pre and postoperative facial range scans. These applications use different methods for calculating the registration transformation and accurate rigid and elastic alignment of images has been achieved with the CSM method. It is expected that this method will be applicable to many different applications and that good results would be achieved if it were to be inserted into other methods for calculating a registration transformation from correspondences View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Two-way ambiguity in 2D projective reconstruction from three uncalibrated 1D images

    Page(s): 212 - 216
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (292 KB) |  | HTML iconHTML  

    We show that there is, in general, a two-way ambiguity for 2D projective reconstruction from three uncalibrated 1D views, independent of the number of point correspondences. The two distinct projective reconstructions are exactly related by a quadratic transformation with the three camera centers as fundamental points. Unique 2D reconstruction is possible only when the three camera centers are aligned. By Carlsson duality (1995), there is a dual two-way ambiguity for 2D projective reconstruction from six point correspondences, independent of the number of 1D views. The theoretical results are demonstrated on numerical examples View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient linear solution of exterior orientation

    Page(s): 140 - 148
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (552 KB) |  | HTML iconHTML  

    This paper concerns an efficient algorithm for the solution of the exterior orientation problem. Orthogonal decompositions are used to first isolate the unknown depths of feature points in the camera reference frame, allowing the problem to be reduced to an absolute orientation with scale problem, which is solved using the singular value decomposition (SVD). The key feature of this approach is the low computational cost compared to existing approaches View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Model-based recognition of 3D objects from single images

    Page(s): 116 - 128
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1740 KB) |  | HTML iconHTML  

    In this work, we treat major problems of object recognition which have received relatively little attention lately. Among them are the loss of depth information in the projection from a 3D object to a single 2D image, and the complexity of finding feature correspondences between images. We use geometric invariants to reduce the complexity of these problems. There are no geometric invariants of a projection from 3D to 2D. However, given certain modeling assumptions about the 3D object, such invariants can be found. The modeling assumptions can be either a particular model or a generic assumption about a class of models. Here, we use such assumptions for single-view recognition. We find algebraic relations between the invariants of a 3D model and those of its 2D image under general projective projection. These relations can be described geometrically as invariant models in a 3D invariant space, illuminated by invariant “light rays,” and projected onto an invariant version of the given image. We apply the method to real images View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognizing action units for facial expression analysis

    Page(s): 97 - 115
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3704 KB)  

    Most automatic expression analysis systems attempt to recognize a small set of prototypic expressions, such as happiness, anger, surprise, and fear. Such prototypic expressions, however, occur rather infrequently. Human emotions and intentions are more often communicated by changes in one or a few discrete facial features. In this paper, we develop an automatic face analysis (AFA) system to analyze facial expressions based on both permanent facial features (brows, eyes, mouth) and transient facial features (deepening of facial furrows) in a nearly frontal-view face image sequence. The AFA system recognizes fine-grained changes in facial expression into action units (AU) of the Facial Action Coding System (FACS), instead of a few prototypic expressions. Multistate face and facial component models are proposed for tracking and modeling the various facial features, including lips, eyes, brows, cheeks, and furrows. During tracking, detailed parametric descriptions of the facial features are extracted. With these parameters as the inputs, a group of action units (neutral expression, six upper face AU and 10 lower face AU) are recognized whether they occur alone or in combinations. The system has achieved average recognition rates of 96.4 percent (95.4 percent if neutral expressions are excluded) for upper face AU and 96.7 percent (95.6 percent with neutral expressions excluded) for lower face AU. The generalizability of the system has been tested by using independent image databases collected and FACS-coded for ground-truth by different research teams View full abstract»

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

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