Showing papers in "Pattern Recognition in 1972"
••
TL;DR: In this article, a recognition procedure with a range finder has been developed for the eye of the ETL-ROBOT, an intelligent robot studied at the Electrotechnical Laboratory.
141 citations
••
TL;DR: A formal system for defining abstract languages for textures is given, where a texture is represented as a tree, namely a tree made of subtrees representing the occurrences of the unit pattern.
67 citations
••
TL;DR: It is shown that polygons represented as unions of some of their convex subsets can provide information about topological properties of the figure and its shape in general.
49 citations
••
TL;DR: An algorithm for parsing strings generated by Stochastic Context-Free Programmed Grammars is described and an example is presented of one such grammar which generates “noisy” squares.
45 citations
••
TL;DR: In this paper, the ETL-ROBOT, an intelligent hand-eye automaton being developed at the Electrotechnical Laboratory, is used to transform a 3D physical scene to a line-drawing.
28 citations
••
TL;DR: A recognition processing between patterns represented by N points in R 2 does not depend on either translation, rotation or homothety and also allows up to 10 per cent distortion.
24 citations
••
TL;DR: It is shown that the membership question is recursively solvable for large classes of automata while the emptiness question is r, unsolvable even for the class of M-way finite automata.
23 citations
••
TL;DR: The technique of “cepstrum” analysis is shown to give a reliable indication of the firing rate even when the engine sound is deeply embedded in noise, in contrast to results obtained by some earlier workers using this analysis in speech studies.
23 citations
••
TL;DR: It is shown that pattern dichotomizers trained with the iterative least squares procedure can obtain predictive abilities of 98% in classifying unknown low resolution mass spectra into useful chemical categories.
20 citations
••
TL;DR: In this paper, a general description of a scene is described in general terms for an unspecified future use, where the robot, similar to the human, will build up an "encyclopedia" of descriptions for possible use.
11 citations
••
TL;DR: Techniques involving the computer processing of scanning electron microscope images using a binary coded map approach have been developed and the results are viewed step by step with an explanation of the possibilities.
••
TL;DR: A new method of shape characterization has been developed, based on representation of the silhouette of the aggregate as an ellipse with equivalent radii of gyration, which should be of quite general utility for studying fused aggregates.
••
TL;DR: A mathematical formulation of the clustering problem in which no parameters to be controlled by the user are included, thus no outside interference is required, and the model was applied to clustering data points defined in a multi-dimentional space.
••
TL;DR: A picture-processing system that was first developed to locate ridge-endings in a fingerprint, but has since been expanded to solve a number of other picture- processing problems, that extracts from a picture contour a set of features or nodes which are tied together in a bidirectional list structure.
••
TL;DR: Three measures of syntactic complexity, developed for context-free grammars, are shown to have application to Dacey's two-dimensional languages for simple polygons.
••
TL;DR: A new type of spatial filtering method namedθ-Fourier Method which extracts some features of patterns on the Fraunhofer diffraction plane is proposed, and some practical performances of this method are also experimentally investigated.
••
TL;DR: A direct real space method is given for reconstructing three-dimensional objects from a rotation series of electron micrographs based on the solution of the coupled integral equations which relate the picture densities and the original object.
••
TL;DR: Instead of the vocabulary of primitives and grammar being selected by the designer, this new pattern-recognition system is able to make a new description, give the vocabulary, and construct the grammar.
••
TL;DR: It is demonstrated that using the Redman and Reid method it is possible to obtain a shape characteristic spectrum by direct optical processing procedures which enable a profile to be described in terms of an equivalent ellipse or rectangle.
••
TL;DR: This paper considers unsupervised learning, structure and parameter adaptive binary pattern recognition when a nongaussian pattern is observed in gaussian noise and certain judicious approximations are made use of.
••
TL;DR: An artificial language, called PADEL, which may be used to describe line drawings, is described, which is noted to be phrase structured, finite, context free language.
••
TL;DR: In this review the various areas of interest to the Fine Particle analyst of Pattern recognition procedures are outlined and recent research developments are indicated and reviewed.
••
TL;DR: This paper proposes various adaptive algorithms which converge rapidly to a separating hyperplane whose location is well-balanced with regard to the distances of the centroids of the clusters from the plane and to the direction of the plane relative to the line connecting the two Centroids.
••
TL;DR: A technique useful in solving problems involving forcing states is developed for the class of position games including n k tic-tac-toe, Go-Moku, Hex, and Bridg-It, with power in the forcing pattern description.
••
TL;DR: A procedure and computer program is presented which locates and extracts features from a nerve cell characterized by having a cytoplasm, nucleus, and a nucleolus and is implemented in an interactive system.
••
••
TL;DR: An algorithm for calculating recognition error for minimum Hamming distance classifiers, a special case of the Bayes (optimum) classifier under certain constraints, is presented, verifying the ability of the algorithnm to predict recognition error of categorizers.
••
TL;DR: The order and convergence of a numerical approxiamation for determining the expectation of a statistical function of the object-pair similarities with prescribed accuracy is examined in the sub-asymptotic case in which normality does not occur.