By Topic

IEEE Transactions on Pattern Analysis and Machine Intelligence

Issue 9 • Sep 1994

Filter Results

Displaying Results 1 - 13 of 13
  • A stereo matching algorithm with an adaptive window: theory and experiment

    Publication Year: 1994, Page(s):920 - 932
    Cited by:  Papers (527)  |  Patents (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1092 KB)

    A central problem in stereo matching by computing correlation or sum of squared differences (SSD) lies in selecting an appropriate window size. The window size must be large enough to include enough intensity variation for reliable matching, but small enough to avoid the effects of projective distortion. If the window is too small and does not cover enough intensity variation, it gives a poor disp... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Handwritten character classification using nearest neighbor in large databases

    Publication Year: 1994, Page(s):915 - 919
    Cited by:  Papers (42)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (488 KB)

    Shows that systems built on a simple statistical technique and a large training database can be automatically optimized to produce classification accuracies of 99% in the domain of handwritten digits. It is also shown that the performance of these systems scale consistently with the size of the training database, where the error rate is cut by more than half for every tenfold increase in the size ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Adaptive termination of voting in the probabilistic circular Hough transform

    Publication Year: 1994, Page(s):911 - 915
    Cited by:  Papers (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    Reliable detection of objects using the Hough transform is often possible even if just a small random poll of edge points is used for voting. This can lead to significant computational savings. To reduce the risk of errors, it is customary to preset the poll size to a value that is much larger than necessary in average conditions. An adaptive setting of the poll size in the probabilistic Hough tra... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Generating image filters for target recognition by genetic learning

    Publication Year: 1994, Page(s):906 - 910
    Cited by:  Papers (23)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (536 KB)

    Describes results obtained from applying genetic algorithms to the problem of detecting targets in image data. The method described is a two-layered approach, with the first layer providing a focus-of-attention function for the second layer. The first layer is called a Screener and selects subimages from the original image data to be processed by the second layer, called the Classifier. The Screen... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Vector field analysis for oriented patterns

    Publication Year: 1994, Page(s):946 - 950
    Cited by:  Papers (19)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (432 KB)

    Presents a method, based on the properties of vector fields, for the estimation of a set of symbolic descriptors (node, saddle, star-node, improper-node, center, and spiral) from linear orientation fields. Planar first-order phase portraits are used to model the linear orientation fields. A weighted linear estimator is developed to estimate linear phase portraits, using only the flow orientation. ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning and feature selection in stereo matching

    Publication Year: 1994, Page(s):869 - 881
    Cited by:  Papers (58)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1176 KB)

    We present a novel stereo matching algorithm which integrates learning, feature selection, and surface reconstruction. First, a new instance based learning (IBL) algorithm is used to generate an approximation to the optimal feature set for matching. In addition, the importance of two separate kinds of knowledge, image dependent knowledge and image independent knowledge, is discussed. Second, we de... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Geometric primitive extraction using a genetic algorithm

    Publication Year: 1994, Page(s):901 - 905
    Cited by:  Papers (95)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (632 KB)

    Extracting geometric primitives from geometric sensor data is an important problem in model-based vision. A minimal subset is the smallest number of points necessary to define a unique instance of a geometric primitive. A genetic algorithm based on a minimal subset representation is used to perform primitive extraction. It is shown that the genetic approach is an improvement over random search and... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning compatibility coefficients for relaxation labeling processes

    Publication Year: 1994, Page(s):933 - 945
    Cited by:  Papers (43)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (1128 KB)

    Relaxation labeling processes have been widely used in many different domains including image processing, pattern recognition, and artificial intelligence. They are iterative procedures that aim at reducing local ambiguities and achieving global consistency through a parallel exploitation of contextual information, which is quantitatively expressed in terms of a set of “compatibility coeffic... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fast Parzen density estimation using clustering-based branch and bound

    Publication Year: 1994, Page(s):950 - 954
    Cited by:  Papers (20)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (524 KB)

    This correspondence proposes a fast Parzen density estimation algorithm that would be especially useful in nonparametric discriminant analysis problems. By preclustering the data and applying a simple branch and bound procedure to the clusters, significant numbers of data samples that would contribute little to the density estimate can be excluded without detriment to actual evaluation via the ker... View full abstract»

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

    Publication Year: 1994, Page(s):882 - 888
    Cited by:  Papers (14)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (644 KB)

    This paper is a summary of a new approach to learning shape concepts. In this system, a shape is represented by conjunctions of local shape properties. Conjunctions of local properties are consistent and unique for distinct shapes and are robust enough to represent shape in the presence of occlusion. A new learning method, called property based learning, is developed and used to learn conjunctions... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A least biased fuzzy clustering method

    Publication Year: 1994, Page(s):954 - 960
    Cited by:  Papers (50)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (568 KB)

    A new operational definition of cluster is proposed, and a fuzzy clustering algorithm with minimal biases is formulated by making use of the maximum entropy principle to maximize the entropy of the centroids with respect to the data points (clustering entropy). The authors make no assumptions on the number of clusters or their initial positions. For each value of an adimensional scale parameter &b... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Goal-directed classification using linear machine decision trees

    Publication Year: 1994, Page(s):888 - 893
    Cited by:  Papers (25)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (620 KB)

    Recent work in feature-based classification has focused on nonparametric techniques that can classify instances even when the underlying feature distributions are unknown. The inference algorithms for training these techniques, however, are designed to maximize the accuracy of the classifier, with all errors weighted equally. In many applications, certain errors are far more costly than others, an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning texture discrimination rules in a multiresolution system

    Publication Year: 1994, Page(s):894 - 901
    Cited by:  Papers (33)  |  Patents (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (892 KB)

    We describe a texture analysis system in which informative discrimination rules are learned from a multiresolution representation of time textured input. The system incorporates unsupervised and supervised learning via statistical machine learning and rule-based neural networks, respectively. The textured input is represented in the frequency-orientation space via a log-Gabor pyramidal decompositi... 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
Sven Dickinson
University of Toronto
e-mail: sven@cs.toronto.edu