Showing papers in "Pattern Recognition in 1970"

TL;DR: The use of the “minimum-perimeter polygon” in an algorithm for testing the convexity of cellular blobs on a rectangular mosaic is described.

TL;DR: The computed directions are in good agreement with those determined by manual methods with indications that computed speeds are more accurately resolved than those determined manually.

TL;DR: A simple technique for improving, in real time, the quality of wirephoto pictures is presented and can be incorporated in conventional wirephoto transmitters with very little cost.

TL;DR: In this article, a conic section is represented by a quadratic form Q ( x, y ) = 0, and a best conic for f is one for which ∫∫ f ( x, y ) ·| Q( x, Y )| 2 d x d y is a minimum.

TL;DR: It is shown that a mathematical group summarizes the structure holding between languages constructed for polygons that are related by proper and improper rotations.

TL;DR: Digital images of handdrawn characters are treated by a noise insensitive process to yield a skeleton-like structure which preserves the main features of the original stroke pattern, but has a local syntax which allows its points to be classified in a way useful for recognition of the pattern.

TL;DR: The Mellin transform was introduced as a technique for restoring images degraded by a class of spatially-variant degradations as mentioned in this paper, which includes the coma aberration and tilt in a cylindrical lens system.

TL;DR: Reliable determination of spatial frequencies beyond the nominal atmospheric cut off may still be possible if one takes a large number of independent measurements of the short-term mutual coherence and then averages the results in the proper manner.

TL;DR: This paper presents a general review of character recognition techniques and problems for people not intimately acquainted with this field, to give perspective to more detailed papers on character recognition, as well as to the more general field of pattern recognition.

TL;DR: A technique of pattern processing implemented by microprogram control and stored recognition logic has high flexibility to accommodate an almost unlimited variability of handwritten character shapes and has direct linkage with backup computer simulation.

TL;DR: Future application of hardwired Fourier operators mounted on the spacecraft and operating on imagery transforms could provide data compression, thereby reducing the burden imposed on the down-link, and permit near-real time application of the reduced data to various user-oriented decision models.

TL;DR: An optical image processor works by corrective convolution rather than by complex spatial filtering, and an incorporated flexible function generator permits quantization, contour generation and other non-linear operations to be performed in the playback, with or without the optical processing.

TL;DR: Techniques involving the computer processing of scanning electron microscope images using a contour approach have been developed and computer plotting enables both the visual comparison of the reconstructed picture with a photograph of the image on the cathode ray tube of the SEM and an estimate of the accuracy of the ellipse fits.

TL;DR: Spin scan cloud pictures from NASA's Applications Technology Satellites are being computer processed as an operational experiment and the treatment of horizon and landmark features in support of the photogrammetric aspects and the subsequent transformation of images onto standard map projections.

TL;DR: Digital image processing techniques have been developed at the Jet Propulsion Laboratory which enable us to characterize these various distortions using calibration data, and to remove them from images returned by the two Mariner spacecraft.

TL;DR: A system which automatically classifies terrain types from photography based on spatial texture in the region of the input point and a learning strategy enables the system to refine its processing operations in order to improve classification performance with time.

TL;DR: Three computer programs are described which employ a “coding method” to learn to recognize classes of number sequences representing line drawings, which forms an interesting framework for considering methods for automatic pattern recognition.

TL;DR: A non-parametric, unsupervised learning technique that makes use of a relation matrix to classify binary pattern vectors presented in random sequence that produces decision surfaces of a reasonable form.

TL;DR: An understanding of the biological principles that govern the development of vegetation is a prerequisite to successful pattern recognition by aerial photography or remote sensing and the possibility that periodicities exist in the distribution of trees and stands is examined.

TL;DR: A key new element of the INPUT 2 Document Reader is in the logic used for interpreting handprinting, based on a unique multilevel-logic technique developed by Recognition Equipment engineers.

TL;DR: The techniques that can be used to produce spatial filters for coherent or incoherent optical data-processing systems are discussed and some experimental results of using a coherent optical system and spatial filters generated with a digital computer are given.

TL;DR: This work discusses this limitation and presents examples illustrating why under some conditions digital processing of the image may increase the extraction of information.

TL;DR: A large-aperture optical system may be operated as a multi-element interferometer such that a posteriori image processing can yield images that are free from the usual distortions of atmospheric “seeing”.

TL;DR: The properties and algebraic structure of error correcting codes are shown to be applicable to adaptive pattern recognition and a decision algorithm is postulated upon the basis of a criterion of maximum joint entropy in excess of a calculable minimum.

TL;DR: A mathematically rigorous procedure is developed which transforms the underlying unknown probability structure of a pattern discrimination problem to the real line and partitions this transformed probability space using the fact that the locations of the relative extrema of the difference of empirical distribution functions will converge to the boundaries of the likelihood ratio decision rule.