Showing papers on "Feature (computer vision) published in 1984"

Feature enhancement of film mammograms using fixed and adaptive neighborhoods.

Abstract: Digital techniques are presented for xerographylike enhancement of features in film mammograms. The mammographic image is first digitized using a procedure for gray scale dynamic range expansion. A pixel operator is then applied to the image, which performs contrast enhancement according to a specified function. The final transformation leads to either a positive or negative mode display as desired. We also present an adaptive neighborhood feature enhancement technique that enhances visibility of objects and details in an image. The availability of the enhanced images should aid diagnosis of breast cancer without requiring additional x-ray dose such as for xeromammography.

Signal processing method and apparatus for sampled image signals.

Abstract: A signal processing method and apparatus for providing interpolated values between sampled values in a sampled image signal, is characterized by providing a plurality of different interpolation routines for producing interpolated signal values for appropriately completing a respective plurality of known features, detecting which of the geometrical image features is represented by a neighborhood of sample values and applying the interpolation routine appropriate for completing the detected feature, to produce the interpolated signal value. The signal processing method and apparatus has the advantage that reconstruction errors in the reproduced image are reduced. In one mode of the invention for processing images to be viewed by humans, reconstruction errors are forced to occur in areas of the image composed of natural textures where the errors are not readily visible to the human observer. The appearance of the reconstructed image is thereby improved.

What do nurses want in a mentor

Abstract: Recognizing the increasing importance of mentoring in helping professional nurses adapt to and function effectively in this vastly changed health care world, JONA introduces a monthly feature article entitled The Mentoring Dimension. The Mentoring Dimension will be a dialogue between you the readers

HIPS: A unix-based image processing system

Abstract: A software system for image processing, HIPS, was developed for use in a UNIX environment. It includes a small set of subroutines which primarily deals with a standardized descriptive image sequence header, and an ever-growing library of image transformation tools in the form of UNIX “filters.” Programs have been developed for simple image transformations, filtering, convolution, Fourier and other transform processing, edge detection and line drawing manipulation, simulation of digital compression and transmission, noise generation, and image statistics computation. The system has the useful feature that images are self-documenting to the extent that each image as stored in the system includes a history of the transformations that have been applied to that image. Although it has been used primarily with a Grinnell image processor, the bulk of the system is machine-independent. The system has proven itself a highly flexible system, both as an interactive research tool, and for more production-oriented tasks. It is both easy to use, and quickly adapted and extended to new uses.

System for recognizing three-dimensional objects

Abstract: A system for recognizing a three-dimensional object includes a plurality of image pickup apparatus, e.g. TV cameras, by which images of the object are picked up from at least three directions. Feature points are extracted from each of at least three images obtained. Two sets of feature points on epipolarly lines are formed which lines are formed on at least two of the images by a feature point on another image. A set of feature points is selected which satisfy a restricting condition determined by the relationship of the image picking-up direction.

Binocular shading and visual surface reconstruction

Abstract: Zero-crossing or feature-point based stereo algorithms can, by definition, determine explicit depth information only at particular points in the image. To compute a complete surface description, this sparse depth map must be interpolated. A computational theory of this interpolation or reconstruction process, based on a surface consistency constraint, has previously been proposed, implemented, and tested. In order to provide stronger boundary conditions for the interpolation process, other visual cues to surface shape are examined in this paper. In particular, it is shown that in theory, shading information from the two views can be used to determine the orientation of the surface normal along the feature-point contours, provided the photometric properties of the surface material are known. This computation can be performed by using a simple modification of existing photometric stereo algorithms. It is further shown that these photometric properties need not be known a priori, but can be computed directly from image irfadiance information for a particular class of surface materials. The numerical stability of the resulting equations is also examined.

Image processing-system

Abstract: Level data on an output line (24) carrying the digitized output of a video camera and analog-to-digital converter (12) is processed by a combination circuit (10) to store in an acquisition memory (16) the results of a feature-identification or histogram operation. In a histogram operation, the memory locations of the acquistion memory (16) represent the bins into which the levels represented by the level data are sorted, and the contents of those locations indicate the number of picture elements whose levels fall in those bins. In feature identification, the contents of successive memory locations in the acquistion memory (16) contain the positions of those picture elements whose levels have a selected feature. Common circuitry performs both the histogram and feature-identification functions. To perform the histogram function, a counter (39), whose output provides the address for the acquisition memory (16), is operated to load the output of a look-up-table memory (22), which acts as an encoder to indicate the bin into which the level represented by the level signal belongs. An increment circuit (52) is then operated to read the contents of that location in the acquisition memory (16), increment it, and return the incremented value to the specified memory location. For feature identification, the contents of the look-up table (22) indicate whether the levels represented by the level signals have the selected features. A control circuit (30) monitors the output of the look-up-table memory and clocks the counter (39) whenever the selected feature is encountered. This changes the address for the random-access memory (16) to that of the next location in memory, and the increment circuit (52), which is incremented on the occurrence of every picture element to keep track of picture-element location, writes the position of the picture element having the selected feature into the next location in the random-access memory (16).

Developmental aspects of the perception of acoustic cues in determining the voicing feature of final stop consonants.

Abstract: The developmental use of vowel duration, final transition and voicing during closure as cues to voicing in final stop consonants were investigated, using 10 three-year-old, 10 six-year-old and 10 adult subjects. The stimuli were alterations of eight stop-vowel-stop words. The presentation of each stimulus item was response contingent. The resulting data supported the ability of adults and children to use both temporal and spectral cues to acoustic/ phonetic distinctions. However, three-year olds relied more on temporal cues, six-year olds relied more on spectral cues, while adults used both spectral and temporal cues in judging the voicing feature of final stop consonants.

Optimum feature selection by zero-one integer programming

Abstract: An optimal method for finding a minimum feature subset based on box classifiers is described. Feature selection is represented as a problem of zero-one integer programming. An implicit enumeration method is developed in order to solve this problem. Numerical examples are presented to illustrate the effectiveness of the approach.

Modeling feature perception in brief displays with evidence for positive interdependencies

Abstract: Recent studies have begun to test certain fundamental assumptions underlying popular models of feature perception. This research is continued here. It was discovered that every basic assumption that was open to test in the present study was disconfirmed. However, several new characteristics of line and curve feature perception were discovered: (1) Feature perception sensitivity was inversely related to the number of features present in a stimulus pattern, and the decision criteria for reporting a feature decreased with the number of features contained in a pattern; (2) the decrements in sensitivity reported in (1) were greater for features lying inside a pattern than for those on the exterior; and (3) feature perception sensitivity actually improved if another feature was known to be correctly perceived during the same trial. Likewise, feature sensitivity decreased if another feature was missed on any trial. At the present time, a system that first extracts global and then local (more detailed) featural information provides a basis that qualitatively accounts for our findings and is also compatible with several other studies in the literature.

Picture input device

Abstract: PURPOSE: To discriminate automatically an input start timing by starting the collection processing of stripe patterns according to the concentration level of picture signals at positions of picture elements spread over a prescribed two-dimensional area on a picture obtained by a reflected light. CONSTITUTION: A picture pattern of fingerprints obtained from a fingerprint input part 1 is supplied to an input timing processing circuit 2 after photoelectric conversion. The circuit 2 collects the information on the fingerprint patterns in response to the density level of the picture signal and stores a collected pattern information temporarily in a picture memory 3. A collation processor 4 compares the fingerprint feature information given from a file 6 which receives an access by an ID number supplied from a keyboard 5 with the pattern information stored temporarily in the memory 3. COPYRIGHT: (C)1986,JPO&Japio

Active help systems

Abstract: Good on-line help systems are of crucial importance for the computer systems of the future. An increased functionality (required by the many different tasks which a user wants to do) will lead to an increased complexity. Empirical investigations have shown that on the average only 40% of the functionality of complex computer systems are used. Passive help systems (which require that the user requests help explicitly from the system) are of little use if the user does not know the existence of a system feature. Active help systems should guide and advise an user similar to a knowledgeable colleague or assistant.

Introduction to psychology : an integrated approach

Abstract: An introduction to psychology which assumes no previous knowledge of the subject. A special feature is the integrated approach to human processes which brings together the contributions of the various traditional branches of psychology into one unified treatment.

The influence of generalization decrement on the outcome of a feature-positive discrimination

Abstract: In a feature-positive discrimination subjects receive training in which reinforced presentations of a compound, AB+, are intermixed among non-reinforced presentations of one element, Ao. The three reported experiments compared the results of this procedure when using a light or a tone as the feature-positive stimulus, B. In all three experiments, the tone elicited a stronger conditioned response than the light when it was presented alone. The main concern of Experiments 2 and 3 was to examine whether this effect was due to training being incomplete for subjects receiving the light as the B element. In Experiment 2 it was found that extended discrimination training did not diminish the difference between the properties of the light and the tone. Experiment 3 revealed that this effect was not due to differences in the asymptotic associative strength of either A or the compound. It is argued that these results are not readily compatible with contemporary theories of learning, and an alternative account is presented.

Method for retrieving unedited video still pictures

Abstract: In editing video still pictures, the pictures are reproduced from a video disk and displayed one by one in combination with subject-matter categories into which they may be grouped. The list of categories appears as a descriptive overlay on each picture being evaluated. Ordinarily, some pictures are assigned to categories and some are skipped. It often happens that it is necessary to reevaluate the pictures that were skipped during the initial stage of evaluation. To encourage such a reevaluation, a special editing feature is provided for retrieving and redisplaying only those pictures that were not initially assigned to a category. Since these pictures are not intermixed with those already assigned to categories, they are quickly retrieved and conveniently assigned, if desired, to one or more of the subject-matter categories.

Visual Recognition of Simple Objects by a Connection Network.

Abstract: : A difficult problem in vision research is specifying how meaningful objects are recognized using the visual feature information extracted from an image The fundamental issue involves the interaction of different levels of representation of visual information The technical and theoretical problems that must be addressed in specifying this interaction arise in any attempt to model visual object perception We attempt to deal with some difficult aspects of this process within the context of Feldman's Four Frames model of visual perception The model consists of four continually interacting representational frames, expressed in terms of a massively parallel, connectionist formalism Within the Four Frames model, the problem of accessing object representations using visual feature information can be defined in specific computational terms This paper presents the detailed design of a connectionist model as a possible solution to some of the major problems in the visual recognition of objects The model proposes that an object is represented as a hierarchical structure of geometric subparts Recognition proceeds by determining in parallel that all subparts of an object are present in the image, and then sequentially verifying that each subpart is in the proper spatial relation to the others Implementation results demonstrate that the model can recognize any of a set of simple objects given fairly general feature input Although the model is developed in the context of a drastically simplified visual domain, the principles it embodies are argued to adhere to many of the behavioral and biological constraints of real-world vision

On the comparison between magnetic and electromagnetic prospection methods for magnetic features detection

Abstract: A comparison is made using a 3D model between the response of the magnetic prospection (M.) response and the electromagnetic (E.M.) prospection one for the same feature. From this comparison the investigation depth of both methods is discussed. Three other main points are then studied: the influence of the shape of the feature and of the primary field, the significance of the measurements and the influence of parasites. Contrary to some preceding studies, the conclusion points out that the E.M. method is very valuable and more interesting to develop than the M. method.

Creative Computer Graphics

Abstract: Introduction 1. History 2. Modelling techniques 3. Views 4. Design and industry 5. Science and simulation 6. Art 7. Feature films 8. Television 9. Video games and home computing.

Lockable plier tool

Abstract: A lockable plier-type tool having the lockable features selectively engageable and including handle flexibility and locking element positioning that enhances its gripping capabilities. The locking elements are also arranged and constructed so that the plier may conveniently be used in the conventional manner (i.e. without the locking feature) and may exhibit any desired jaw configuration.

Feature extractors for distortion- invariant robot vision

Abstract: Various feature extractors/classifiers for a hierarchical feature-space pattern recognition system are described. The system is intended to achieve multiclass distortion-invariant object identification. Although only a Fourier transform feature space is used, our basic hierarchical concepts, our theoretical analysis, and our general conclusions are applicable to other feature spaces. The performance using intensity and phase Fourier transform features and the performance in the presence of noise are studied and quantified for two different two-class pattern recognition data bases.