Showing papers on "Feature (computer vision) published in 1975"

Mathematical methods of feature selection in pattern recognition

Abstract: In the 15 years of its existence pattern recognition has made considerable progress on both the theoretical and practical fronts. Starting from the original application of pattern recognition techniques to the problem of character recognition at the time when pattern recognition was conceived these techniques have now penetrated such diverse areas of science as medical diagnosis, remote sensing, finger prints and speech recognition, image classification, etc.* This wide applicability derives from the inherent generality of pattern recognition, which is a direct consequence of the adopted threestage concept of pattern recognition process. According to this concept the process of pattern recognition is viewed as a sequence of three independent functions--representation, feature selection and classification (Fig. 1). Among these functions only the representation stage, which transforms the input patterns into a form suitable for computer processing, is problemdependent. Both the feature selector, the function of which is to reduce the dimensionality of the representation vector, and the classifier, which carries out the actual decision process, work with a vector of measurements which can be considered as an abstract pattern. As a result, the feature selection and classification stages can be implemented using mathematical methods irrespective of the original application. Naturally, this has had a beneficial effect on the progress in the theory of pattern recognition. Although all three stages of the pattern recognition system play an essential role in the process of classifying patterns by machine, the quality of the system's performance depends chiefly on the feature selector. The reasons

Typicality, Diversity, and Feature Pattern of an Ensemble

Abstract: In this paper, issues concerning feature patterns in terms of both feature composition and feature interdependence are discussed, and the concepts of typicality and diversity of an ensemble are formulated. The features of the specimens investigated are organized in a two-dimensional array, called an observation matrix, with each row vector representing the ordered set of features of a specimen. An algorithm (based upon the proposed measures and statistical screening) is implemented for extracting feature patterns. In the algorithm, schemes for feature patterns and specimen reweighting are proposed to optimize the utilization of available information in the array, and to minimize possible bias caused by the uneven sampling of the ensemble. Two sets of real world data in the environmental and molecular biology areas are used to exemplify the physical meaning of the proposed measures as well as to demonstrate the operational feasibility and significance of this methodology in analyzing homologous ensemble which is subject to variable degrees of diversity.

Image analysis data transfer

Abstract: This system measures features or objects each represented by an image by scanning the image in a line scan raster and processing the resulting video signal to determine measurement parameters describing each feature. The system practices methods for obtaining the measurements from signals generated from line intercepts of individual or groups of features. Signal information defining the position of line intercepts intersecting the features, or topological points of each feature is obtained. This information is related to X and Y coordinates and is stored for subsequent use to generate index signals at respective positions in the scan format relating to the stored positions of the X and Y coordinates. The index signals are used to read measurement parameter information from measurement logic or memory.

Image analysis indexing apparatus and methods

Abstract: Described are techniques for extracting indexing data from images scanned in a television raster format and for processing a wide variety of measurement data from images during or subsequent to the scanning operation for determining measurement parameters related to image features. Techniques are described for extracting data at specific multiple points of a feature and correlating the multiple point data from the feature during subsequent data processing. Systems and techniques are also described for storing and indexing data.

Regulator structure and system

Abstract: A regulator for evacuation systems including hospital aspiration systems, such regulator being inexpensively manufactured and assembled and providing a number of unique features. The subject regulator is designed to be essentially independent of altitude of operation or humidity conditions, may be made discretely or continuously variable, and also is provided with features reducing, if not eliminating, any noise of air drawn into the system for regulation purposes. An important feature of the invention is the provision of one or more metering apertures of reduced cross section such that possible error of observable knob setting is reduced to an absolute minumum, thus eliminating the necessity of mechanical-adjustment calibration. Settings are essentially accurate for all altitudes, humidity conditions, and particular pumping parameters of existing vacuum systems. The particular metering apertures, above referenced, are serially related to a unique, slotted airway metering pattern designed to give wide versatility through extended permissible settings. Full-vacuum, and shut-off structural features are also provided.

Tongue musculature and the feature of tension in English vowels.

Abstract: Electromyographic techniques were employed to discover which, if any, intrinsic and extrinsic tongue muscles displayed a difference in overall amount of activity corresponding to the traditional tense

Recognition of an object in a stack of industrial parts

Abstract: This paper describes a method for analyzing an input scene of a stack of industrial parts in order to recognize an object which is not obscured by others. Detecting a simple familiar pattern such as an ellipse in a set of strong feature points, an analyzer selects models of the machine parts from the attributes of other feature points around the pattern under the constraints of the proposed models. Finally one of the models is verified through processes of matching the detailed structures of the models to the less obvious feature points.

A comparison of methods for measuring the interletter similarity between capital letters

Abstract: Measures of interletter similarity are often required in perception experiments. The most reliable and valid of the available measures appears to be Townsend’s (1971) set of similarity parameters based on the Luce choice model. A simple mechanical measure offered a fairly strong prediction of the Luce choice-model similarity measure, as did a subjective rating measure based on the 10-point visual similarity ratings of eight subjects. By comparison, Gibson et al.’s (1963) matching-confusion matrix faired poorly, as did Gibson’s (1969) distinctive feature analysis based on a letter pair’s number of shared features. Distinctive feature analysis was significantly improved by substituting the feature set proposed by Geyer and DeWald (1973) or by weighting the features optimally via regression analysis. Such analyses suggested that figural curvature may be a particularly important perceptual feature, but in no case did these feature-analytic models predict the Luce measure as well as the mechanical or subjective rating measures.

IPL processing of the Mariner 10 images of Mercury

Abstract: This paper describes the digital processing performed on the images of Mercury returned to earth from Mariner 10. Each image contains considerably more information than can be displayed in a single picture. Several specialized processing techniques and procedures are utilized to display the particular information desired for specific scientific analyses: radiometric decalibration for photometric investigations, high-pass filtering to characterize morphology, modulation transfer function restoration to provide the highest possible resolution, scene-dependent filtering of the terminator images to provide maximum feature discriminability in the regions of low illumination, and rectification to cartographic projections to provide known geometric relationships between features. A principal task was the construction of full disk mosaics as an aid to the understanding of surface structure on a global scale.

Motorcycle suspension system

Abstract: The invention comprises a suspension system for a motorcycle or the like wherein the rear wheel suspension spring is connected to the frame in such a manner that upward impacts received by the rear tire are reacted on the frame in a substantially horizontal direction rather than vertically as in conventional motorcycles so that the pitching motion and vertical thrust on the rear end of the motorcycle is considerably reduced over rough terrain, a feature which is particularly advantageous in offroad racing.

Low profile integrated circuit socket

Abstract: An integrated circuit package socket of a "low profile" construction having a built-in anti-wicking feature and arranged to accept leads of varying widths without overstressing.

The causes and effects of mergers

Abstract: A major feature of many industrial economies over the last twenty years has been a large wave of merger activity. This has naturally resulted in increased attention being paid to the subject, and in particular to questions concerning the underlying causes of intense merger activity and also to the economic consequences. Before turning to some of the possible causes and consequences, and to policy considerations, it is worth looking at some facts and figures.

Word boundary detector for speech recognition equipment

Abstract: The present invention pertains to an apparatus which receives acoustic input, the input including words spoken in isolation, finds the word boundary instants at which a word begins and ends, and performs recognition functions on the words. A feature of the invention is the compensation for breath noise after the true end of a word, using a variable backup of the estimated word end. The apparatus includes means for generating feature signals indicative of feature characteristics in the received input and further includes means for comparing the feature signals which occurred during determined time boundaries with stored features corresponding to words in a vocabulary. The invention is directed to an improved system for detecting word boundaries which includes a means responsive to the input for generating a first feature signal indicative of the substantially continuing presence of speech-like sounds which meet a first selection criterion. Means are provided for storing the feature signals which occur during the presence of this first feature signal. Further means, responsive to the input, are provided for generating a second feature signal indicative of the presence of speech-like sounds which meet a second selection criterion, this second selection criterion being more restrictive than the first selection criterion. Means are also provided for determining the last occurrence of the second feature signal among the stored feature signals. The end boundary of an input spoken word is determined as a function of this last occurrence.

Method and apparatus for detecting characteristic features of surfaces

Abstract: A novel system is provided for detecting the presence of a characteristic feature on an illuminated surface of an object when used in conjunction with known electro-optical systems for determining the position of the centroid of the outline of the object with relation to the supporting surface and the rotation of the object relative to the rotational orientation of a test part. The surface is illuminated at an angle that enhances the contrast of the characteristic feature while using a vidicon-type image converter tube which scans the field which includes the object. The location, with respect to the centroid, of a circular window area encompassing the characteristic feature and the radius of the circular window are determined utilizing a television monitor connected to the vidicon. Next the operator determines and stores a pair of separated threshold levels which control a level detector which compares the vidicon output to the threshold level to derive a binary output so that one of the threshold levels separates the white area in the window area from the gray-black area while the other threshold level separates the black area in the window area from the white-grey areas. The system then analyzes and stores the relative amounts of white, gray and black areas in the window as a signature signal representative of the characteristic feature of the surface. Following this "teach" phase, the system may be used to determine whether a subsequent object contains a feature which correlates well with the characteristic of the test part by analyzing the output of the vidicon at the window for both threshold levels and determining the correlation between these levels and the values obtained during the teach phase.

Device and processes for alleviation of muscular pain and stiffness, and symptoms of non-muscular ailments

Abstract: A device and processes comprising the application of a device containing one or more small, rigid objects to produce pressure at designated points of a person's body without puncturing the person's skin, with the added feature of magnetization of the rigid objects to enhance the effectiveness of the device and processes.

Character recognition apparatus

Abstract: Character recognition apparatus which converts two dimensional feature information derived from an unknown character into one dimensional feature information, such as a code train, and recognizes the unknown character by comparing the converted one dimensional feature information with corresponding information relating to selected reference characters The starting point of the one dimensional feature information representing the unknown character is selected by scanning the terminal points of the unknown character in a direction predetermined for each particular reference character as indicated by a scan parameter stored with the one dimensional feature information of the reference character The starting point is then selected on the basis of a relationship including the scan parameter of the reference character and the feature points of the unknown character

Apparatus for supplementing the operation of the ribbon selecting and backspacing means of a typewriter

Abstract: A typewriter has two separate ribbons, at least one of which has two printing fields. An attachment for the typewriter has keys, or other manually operable members, selects any desired one of the three ribbon fields and at the same time backspaces the typewriter. The aforesaid arrangement permits one of the ribbon fields to be a "correcting" field so that the typewriter may be easily operated as a correcting typewriter. A separate feature is that part of the attachment may be in the form of a cassette.

On the topologization of commutative semigroups

Abstract: The paper provides a sufficient feature for nondiscrete topologization of commutative semigroups as well as certain of its consequences.

Superficial fibrillary lines. A feature of the normal cornea.

Abstract: A biomicroscopical study of keratoconus patients has demonstrated the presence of bundles of fine fibrillar structures, sub-epithelially, internal to Fleischer's ring (Bron and Tripathi, I974; Bron, Lobascher, Dixon, Das, and Ruben, I975). A search for similar structures in the normal cornea has revealed identical fibrils, differing only in their visibility and arrangement at the corneal surface. These structures have been called fibrillary lines and the present paper reports their arrangement in the normal cornea and discusses their possible nature.

The microstructure of the cuticle-less shell of the eggs of the domestic hen.

Abstract: 1. Open pores were a notable feature of the shell of hens' eggs which were naturally devoid of cuticle. 2. In contrast with normal eggs, the surface of the cuticle‐less shell was irregularly contoured and, in many instances, deeply fissured.

Methods of and apparatus for determining the physical parameters of selected objects

Abstract: Apparatus for determining parameters of any number of selected regularly or randomly oriented particles, or images or image patterns thereof, of various size and shape lying within a discrete region. A scanning device is swept over the discrete region causing the generation of electrical signals in response to the interception of the boundaries of one or more of the particles. Apparatus, including, for example, a light pen, for use in cooperation with a display of the feature images is operated to best identify, select or prepare for analysis features of interest within the discrete region. In cooperation with such apparatus appropriate logic and electronic circuitry which is adapted to receive the initially generated signals provide, in response thereto, other signals related to the feature or features of interest and any particular parameter related to those features.

Clamping method of bolt and its washer

Abstract: PURPOSE: To discover means for controlling axial clamping force to stay almost constant, by utilizing special feature of washer COPYRIGHT: (C)1977,JPO&Japio

Color picture processing by computer

Abstract: This paper introduces a computer system for color picture processing and its principal features. First the hardware aspects are explained, including the basic characteristics of I/O devices. The interactive feature of our system is singled out, and it is developed to a system concept called "Color Picture Analysis and Display System" The color analysis method and its software are presented and discussed, since the correct recognition of color information is important in color picture processing. This paper also contains some methods and applications of effective use of color information in picture processing. They include(1) domain identification by color information (2) color effect method (3) color separation (4) conversational retouching of color (5) pseudo-color displaying and their applications.