Scheduled System Maintenance on May 29th, 2015:
IEEE Xplore will be upgraded between 11:00 AM and 10:00 PM EDT. During this time there may be intermittent impact on performance. For technical support, please contact us at onlinesupport@ieee.org. We apologize for any inconvenience.
By Topic

Pattern Analysis and Machine Intelligence, IEEE Transactions on

Issue 3 • Date Mar 1990

Filter Results

Displaying Results 1 - 7 of 7
  • On the sensitivity of the Hough transform for object recognition

    Publication Year: 1990 , Page(s): 255 - 274
    Cited by:  Papers (63)  |  Patents (57)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1516 KB)  

    Object recognition from sensory data involves, in part, determining the pose of a model with respect to a scene. A common method for finding an object's pose is the generalized Hough transform, which accumulates evidence for possible coordinate transformations in a parameter space whose axes are the quantized transformation parameters. Large clusters of similar transformations in that space are taken as evidence of a correct match. A theoretical analysis of the behavior of such methods is presented. The authors derive bounds on the set of transformations consistent with each pairing of data and model features, in the presence of noise and occlusion in the image. Bounds are provided on the likelihood of false peaks in the parameter space, as a function of noise, occlusion, and tessellation effects. It is argued that haphazardly applying such methods to complex recognition tasks is risky, as the probability of false positives can be very high View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Convolution on mesh connected multicomputers

    Publication Year: 1990 , Page(s): 315 - 318
    Cited by:  Papers (10)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (300 KB)  

    An efficient parallel algorithm is presented for convolution on a mesh-connected computer with wraparound. The algorithm does not require a broadcast feature for data values, as assumed by previously proposed algorithms. As a result, the algorithm is applicable to both SIMD and MIMD meshes. For an N×N image and a M×M template, the previous algorithms take O (M2q) time on an N×N mesh-connected multicomputer (q is the number of bits in each entry of the convolution matrix). The algorithms have complexity O(M2r), where r=max {number of bits in an image entry, number of bits in a template entry}. In addition to not requiring a broadcast capability, these algorithms are faster for binary images View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Stereo correspondence by surface reconstruction

    Publication Year: 1990 , Page(s): 309 - 315
    Cited by:  Papers (11)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (856 KB)  

    An algorithm that solves the computational stereo correspondence and the surface reconstruction is presented. The algorithm integrates the reconstruction process in the correspondence analysis by means of multipass attribute matching and disparity refinement. In the matching process, the requirement of attribute similarity is relaxed with the pass number while the requirement for agreement between the predicted and the measured disparity is tightened. Disparity discontinuities and occluded areas are detected by analyzing the partial derivatives of the reconstructed disparity surface. Results on synthetic and on real stereo image pairs are reported View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Discrete black and white object recognition via morphological functions

    Publication Year: 1990 , Page(s): 275 - 293
    Cited by:  Papers (6)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1524 KB)  

    Two morphological algorithms that attempt to recognize a black and white object directly in its discrete domain are presented. The first algorithm is based on covariance functions, while the second is based on a variant of size distribution functions. In both these algorithms, the scale correction has been automated. Also presented is a complete geometric and algebraic characterization of objects that are identical with respect to the proposed methodologies, and it is shown that the induced equivalent classes over binary images contain objects that are structurally very similar. This has been accomplished by introducing the notions of a strongly attached pixel, discrete structure of an image, and a structure preserving operation. An outcome of the analysis is the insight into the relationship between the discrete structure of an image and the induced equivalence classes View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Integrating region growing and edge detection

    Publication Year: 1990 , Page(s): 225 - 233
    Cited by:  Papers (137)  |  Patents (5)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1304 KB)  

    A method that combines region growing and edge detection for image segmentation is presented. The authors start with a split-and merge algorithm wherein the parameters have been set up so that an over-segmented image results. Region boundaries are then eliminated or modified on the basis of criteria that integrate contrast with boundary smoothness, variation of the image gradient along the boundary, and a criterion that penalizes for the presence of artifacts reflecting the data structure used during segmentation (quadtree in this case). The algorithms were implemented in the C language on a Sun 3/160 workstation running under the Unix operating system. Simple tool images and aerial photographs were used to test the algorithms. The impression of human observers is that the method is very successful on the tool images and less so on the aerial photograph images. It is thought that the success in the tool images is because the objects shown occupy areas of many pixels, making it is easy to select parameters to separate signal information from noise View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • LEW: learning by watching

    Publication Year: 1990 , Page(s): 294 - 308
    Cited by:  Papers (1)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1424 KB)  

    LEW (learning by watching), a machine learning system, is described. It was designed for knowledge acquisition in cooperation with an expert. LEW learns from examples of problem-solution (or question-answer) pairs by generalizing on differences in those pairs. In this sense, it belongs to the family of inductive learning methods. It provides for using background knowledge through the environment component of problem-solution pairs, thereby making constructive learning possible. The user can control the extent of the generalizations performed by LEW. The learning method is incremental and, to some extent, noise-resistant. The authors give an informal overview of the knowledge representation and the basic learning algorithm of LEW and indicate that the system's design meets the stated criteria and enables it to give helpful assistance, even in situations characterized by noisy or conflicting information and by lack of extensive background knowledge. The theory behind LEW is presented, along with rigorous definitions of its fundamental concepts and a general description of its learning algorithm. LEW's functioning with some larger examples, one from the QUIZ Advisor domain and another from the domain of block-world planning, is illustrated. The authors compare LEW with several other knowledge acquisition tools and introduce a precise characterization of learning from near misses and a near-miss metric. Possible extensions and enhancements to the system are noted View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Scale-space for discrete signals

    Publication Year: 1990 , Page(s): 234 - 254
    Cited by:  Papers (98)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1648 KB)  

    A basic and extensive treatment of discrete aspects of the scale-space theory is presented. A genuinely discrete scale-space theory is developed and its connection to the continuous scale-space theory is explained. Special attention is given to discretization effects, which occur when results from the continuous scale-space theory are to be implemented computationally. The 1D problem is solved completely in an axiomatic manner. For the 2D problem, the author discusses how the 2D discrete scale space should be constructed. The main results are as follows: the proper way to apply the scale-space theory to discrete signals and discrete images is by discretization of the diffusion equation, not the convolution integral; the discrete scale space obtained in this way can be described by convolution with the kernel, which is the discrete analog of the Gaussian kernel, a scale-space implementation based on the sampled Gaussian kernel might lead to undesirable effects and computational problems, especially at fine levels of scale; the 1D discrete smoothing transformations can be characterized exactly and a complete catalogue is given; all finite support 1D discrete smoothing transformations arise from repeated averaging over two adjacent elements (the limit case of such an averaging process is described); and the symmetric 1D discrete smoothing kernels are nonnegative and unimodal, in both the spatial and the frequency domain 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