Journal ArticleDOI
Generalized chord transformation for distortion-invariant optical pattern recognition.
TLDR
An optical processor that realizes a generalized chord transformation is described and the wedge-ring detector samples of an autocorrelation are shown to be the histograms of the chord distributions.Abstract:
An optical processor that realizes a generalized chord transformation is described. The wedge-ring detector samples of an autocorrelation are shown to be the histograms of the chord distributions. This dimensionality reduced set of features is used as the feature vector inputs for a Fisher linear classifier to determine the class of the input object independent of geometrical distortions. Initial discussions on the use of different classifiers, the polarity of the classifier’s output, and selection of the image training set are also advanced.read more
Citations
More filters
Journal ArticleDOI
Review of shape coding techniques
TL;DR: This review reports the techniques used to code shape and investigates whether the schemes allow reconstruction of shape from the descriptor, their ability to recognize an object from a partial description, computational complexity and their limitations.
Journal ArticleDOI
Comparison of statistical pattern-recognition algorithms for hybrid processing. II: Eigenvector-based algorithm
TL;DR: It is shown that all eigen vector-based algorithms can be represented in a generalized eigenvector form, and the classification performance with discriminant functions of the F-S, HTC, and F-K with the LDF and GMF algorithms and the linear-mapping- based algorithms with the eigen vectors.
Journal ArticleDOI
Comparison of statistical pattern-recognition algorithms for hybrid processing. I. Linear-mapping algorithms
TL;DR: The relations among various linear-mapping-based algorithms are studied by formulating a more general unified pseudoinverse algorithm and it is shown that the least-squares linear-Mapping technique, the simplified least-Squares linear, the synthetic discriminant function, the equal-correlation-peak method, and the Caulfield–Maloney filter are in fact all special cases of the unified pseudo inverse algorithm.
Journal ArticleDOI
Error-correction coding in an associative processor.
TL;DR: A technique for encoding binary outputs from optical filters or matrix memories used in an associative processor for object recognition is discussed and Binary coded output vectors (rather than unit vectors) are used and considerably improve storage capacity.
Proceedings ArticleDOI
Scene Analysis Research: Optical Pattern Recognition And Artificial Intelligence
TL;DR: Recent optical data processing research at Carnegie-Mellon University (CMU) is reviewed, including pattern recognition work on feature extraction and correlation, optical linear algebra processing, and most recently optical symbolic, associative, and adaptive artificial intelligence optical processors.
References
More filters
Journal ArticleDOI
On the effectiveness of receptors in recognition systems
T. Marill,D. Green +1 more
TL;DR: Some of the theoretical problems encountered in trying to determine a more formal measure of the effectiveness of a set of tests are discussed; a measure which might be a practical substitute for the empirical evaluation.
Journal ArticleDOI
Multivariant technique for multiclass pattern recognition.
TL;DR: A technique for multiclass optical pattern recognition of different perspective views of an object is described and a single averaged matched spatial filter is produced from a weighted linear combination of these functions.
Journal ArticleDOI
New optical transforms for pattern recognition
TL;DR: In this article, new optical transformations are discussed, including Mellin transforms, Fourier-Mellin transforms and combinations of Geometrical transformations and Fourier Mellin operations.
Journal ArticleDOI
Detection of Differences in Real Distributions
TL;DR: In this paper, the Fourier transform of the record contains comparative data about the two input distributions, i.e., a cross-correlation function, which is used to identify spatial distributions by heterodyning a reference distribution with the field of view.