scispace - formally typeset
Search or ask a question

Showing papers on "Feature (computer vision) published in 1981"


Book
01 Jan 1981
TL;DR: Modelling, prediction, description and interpretation proceed concurrently from coarse object subpart and class interpretations of images, to fine distinctions among object subclasses and more precise three dimensional quantification of objects.
Abstract: We describe model-based vision systems in terms of four components: models, prediction of image features, description of image features, and interpretation which relates image features to models. We describe details of modelling, prediction and interpretation in an implemented model-based vision system. Both generic object classes and specific objects are represented by volume models which are independent of viewpoint. We model complex real world object classes. Variations of size, structure and spatial relations within object classes can be modelled. New spatial reasoning techniques are described which are useful both for prediction within a vision system, and for planning within a manipulation system. We introduce new approaches to prediction and interpretation based on the propagation of symbolic constraints. Predictions are two pronged. First, prediction graphs provide a coarse filter for hypothesizing matches of objects to image feature. Second, they contain instructions on how to use measurements of image features to deduce three dimensional information about tentative object interpretations. Interpretation proceeds by merging local hypothesized matches, subject to consistent derived implications about the size, structure and spatial configuration of the hypothesized objects. Prediction, description and interpretation proceed concurrently from coarse object subpart and class interpretations of images, to fine distinctions among object subclasses and more precise three dimensional quantification of objects. We distinguish our implementations from the fundamental geometric operations required by our general image understanding scheme. We suggest directions for future research for improved algorithms and representations.

785 citations


Proceedings Article
24 Aug 1981
TL;DR: The derivation and use of invariants for image feature prediction is described and predictions of image features and their relations are made from three-dimensional geometric models.
Abstract: ACRONYM IS a comprehensive domain independent model-based system for vision and manipulation related tasks. Many of its sub-modules and representations have been described elsewhere. Here the derivation and use of invariants for image feature prediction is described. We describe how predictions of image features and their relations are made and how instructions are generated which tell the interpretation algorithms how to make use of image feature measurments to derive three dimensional sizes and structural and spatial constraints on the original three-dimensional models. Some preliminary examples of ACRONYM'S interpretations of aerial images are shown.

375 citations


Journal ArticleDOI
TL;DR: The segmentation algorithm proposed in this paper is a complex form of thresholding which utilizes multiple thresholds and not only works well for simple images but also produces reasonable segmentations for complex images.

287 citations


Journal ArticleDOI
D.J. Burr1
TL;DR: In this article, an iterative technique for gradually updating the local registration of two images based on a dynamic cooperative model is described. But this method is limited to the case when registration is expected to be poor and feature measures unreliable.

174 citations


Journal ArticleDOI
TL;DR: This paper presents a method for evaluating the properties of features that describe the shape of a QRS complex by examining the distances in the feature space for a class of nearly similar complexes.
Abstract: Automated classification of ECG patterns is facilitated by careful selection of waveform features This paper presents a method for evaluating the properties of features that describe the shape of a QRS complex By examining the distances in the feature space for a class of nearly similar complexes, shape transitions which are poorly described by the feature under investigation can be readily identified To obtain a continuous range of waveforms, which is required by the method, a mathematical model is used to simulate the QRS complexes

114 citations


Journal ArticleDOI
TL;DR: Hierarchical template matching as discussed by the authors allows both a savings in computation time (by a problem-dependent amount) and a considerable degree of insensitivity to noise, which is an important feature of template matching locations that would be difficult to enforce and evene to express.

107 citations



Journal ArticleDOI
TL;DR: A procedure for extracting a set of textural features for characterizing small areas in radar images is presented and it is shown that these features can be used for classifying segments of radar images corresponding to different geological formations.
Abstract: Texture is an important spatial feature useful for identifying objects or regions of interest in an image. While textural features have been widely used in the analysis of a variety of photographic images, they have not been used for processing radar images. In this paper, we present a procedure for extracting a set of textural features for characterizing small areas in radar images and show that these features can be used for classifying segments of radar images corresponding to different geological formations.

99 citations


Proceedings Article
24 Aug 1981
TL;DR: This theory explains segmentation in terms of massively parallel cooperative computation among intrinsic images and a set of parameter spaces at different levels of abstraction.
Abstract: One of the most fundamental problems in vision is segmentation; the way in which parts of an image are perceived as a meaningful whole. Recent work has shown how to calculate images of physical parameters from raw intensity data. Such images are known as intrinsic images, and examples are images of velocity (optical flow), surface orientation, occluding contour, and disparity. While intrinsic images are not segmented, they are distinctly easier to segment than the original intensity image. Segments can be detected by a general Hough transform technique. Networks of feature parameters are appended to the intrinsic image organization. Then the intrinsic image points are mapped into these networks. This mapping will be many-to-one onto parameter values that represent segments. This basic method is extended into a general representation and control technique with the addition of three main ideas: abstraction levels; sequential search; and tight counting These ideas are a nucleus of a connectionist theory of low 'eve and m'ermediate-level vision. This theory explains segmentation in terms of massively parallel cooperative computation among intrinsic images and a set of parameter spaces at different levels of abstraction.

66 citations


01 Apr 1981
TL;DR: In this paper, a connectionist theory of low and m'ermediate-level vision is proposed for segmentation in terms of massively parallel cooperative computation among intrinsic images and a set of parameter spaces at different levels of abstraction.
Abstract: One of the most fundamental problems in vision is segmentation; the way in which parts of an image are perceived as a meaningful whole. Recent work has shown how to calculate images of physical parameters from raw intensity data. Such images are known as intrinsic images, and examples are images of velocity (optical flow), surface orientation, occluding contour, and disparity. While intrinsic images are not segmented, they are distinctly easier to segment than the original intensity image. Segments can be detected by a general Hough transform technique. Networks of feature parameters are appended to the intrinsic image organization. Then the intrinsic image points are mapped into these networks. This mapping will be many-to-one onto parameter values that represent segments. This basic method is extended into a general representation and control technique with the addition of three main ideas: abstraction levels; sequential search; and tight counting These ideas are a nucleus of a connectionist theory of low 'eve and m'ermediate-level vision. This theory explains segmentation in terms of massively parallel cooperative computation among intrinsic images and a set of parameter spaces at different levels of abstraction.

65 citations




01 Jul 1981
TL;DR: The goal of this research is the investigation of the ability of certain cluster techniques to segment monochromatic data collected by remote sensing devices, and the work was done on three levels: underlying motivations, simulations, and real data analysis.
Abstract: : The goal of this research is the investigation of the ability of certain cluster techniques to segment monochromatic data collected by remote sensing devices. The particular example that will be considered consists of temperature data collected by the Air Force Geophysical Laboratory at Hanscom Air Force Base. The work was done on three levels: underlying motivations, simulations, and real data analysis. In this particular paper, we shall restrict our consideration to a single feature, with multiple feature selection to be investigated at a later date. Section 2 presents the motivation for both the cluster techniques and the statistics that they use, while section 3 briefly explains the techniques. In section 4, some simulated data is analyzed, and in section 5, the techniques are applied to actual infrared temperature data. The paper concludes with an indication of possible future directions for the current research effort.


Journal ArticleDOI
TL;DR: Two related methods for the hierarchical representation of curve information are presented and an edge quadtree representation is presented, which is a variable-resolution representation of the linear information in the image.

Journal ArticleDOI
TL;DR: Classification of characteristic neural spike shapes in multi-unit recordings is performed in real time using a reduced feature set using a model of uncorrelated signal-related noise to reduce the feature set.
Abstract: Classification of characteristic neural spike shapes in multi-unit recordings is performed in real time using a reduced feature set. A model of uncorrelated signal-related noise is used to reduce the feature set by choosing a subset of aperiodic samples which is effective for discrimination between signals by a nearest-mean algorithm. Initial signal classes are determined by an unsupervised clustering algorithm applied to the reduced features of the learning set events. Classification is carried out in real time using a distance measure derived for the reduced feature set. Examples of separation and correlation of multiunit activity from cat and frog visual systems are described.

Patent
29 Jun 1981
TL;DR: In this paper, a method and apparatus for determining the height, width, leh and orientation of an object from the feature image of the object found on oblique panoramic aerial photography is disclosed.
Abstract: A method and apparatus is disclosed for determining the height, width, leh and orientation of an object from the feature image of the object found on oblique panoramic aerial photography. A magnifying eyepiece is provided with a calibrated reticle for measuring the dimensions of the feature image. The eyepiece also has a reference mark and indicia about the eyepiece for measuring the orientation from true north of the longitudinal axis of the feature image. The actual measurements of the object are quickly determined from the measurements of the feature image using a suitably programmed calculator supplied with the photograph and camera parameters.


Journal ArticleDOI
TL;DR: This paper presents an algorithm for obtaining a small frontwidth that is of interest when employing the frontal technique for solution of systems of linear equations in the finite element method.
Abstract: This paper presents an algorithm for obtaining a small frontwidth. This feature is of interest when employing the frontal technique for solution of systems of linear equations in the finite element method. The performance of the algorithm is assessed by several examples at the end of the paper.

Journal ArticleDOI
TL;DR: The basic feature estimation and whole exemplar tests were designed such that both models make the same predictions, whereas the typicality rating, classification, and confignral feature estimation tests weredesigned to distinguish between the models.
Abstract: Frequency theories of concept learning assume that people count how often features occur among instances of a concept, but different versions make various assumptions about what features they count. According to the basic feature model, only basic features are counted, whereas according to the configural model, basic features and configural features (all combinations of basic features) are counted. Two experiments assessed the predictions of both versions of frequency theory. Subjects viewed schematic human faces, which included both positive and negative instances of the concept to be learned, and then provided typicality ratings, classification responses, and frequency estimates of configural features, basic features, and whole exemplars. Because both models assume that basic features are counted, they make the same predictions in many situations. Here, the basic feature estimation and whole exemplar tests were designed such that both models make the same predictions, whereas the typicality rating, classification, and confignral feature estimation tests were designed to distinguish between the models. The pattern of results clearly supported the basic feature version of frequency theory.

Proceedings Article
24 Aug 1981
TL;DR: Genera/ constraints on the interpretation of image curves are described and implemented and the use of these constraints to interpret three dimensional structure from an image up to the volumetric level is illustrated.
Abstract: Genera/ constraints on the interpretation of image curves are described and implemented We illustrate the use of these constraints to interpret three dimensional structure from an image up to the volumetric level These constraints do not use any knowledge regarding the specific objects in the image, but rely on general assumptions regarding illumination, occlusion, object geometry, and the imaging process They are based on coincidence assumptions that various coincidental lcatures or alignments in an image are unlikely to arise without reason. The strength of these coincidence assumptions depends on the accuracy of the low-level description of an image. Since any one feature can be the result of pure coincidence or errors in the detection process, it is necessary to use a reasoning system which can use these hypotheses to derive consistent global interpretations, while maintaining the ability to remove the implications of hypotheses which are disproved in the face of further evidence We demonstrate the successful interpretation of some hand derived image curves up to the volumetric level, including the construction of a three- space model.

Patent
13 Apr 1981
TL;DR: An audio-visual, child-participating, educational entertainment center as discussed by the authors provides a child with an educational entertainment device in which the child can actively participate, at his own pace, in an audio visual feature.
Abstract: An audio-visual, child-participating, educational entertainment center, which provides a child with an educational entertainment device in which the child can actively participate, at his own pace, in an audio-visual feature. The educational entertainment center comprises a screen upon which visual images are projected, an animated audio-visual feature, a kit containing different types of appliques, the appliques being capable of integration with the audio-visual animated feature, and a switch to stop and restart the audio-visual feature at will, thus permitting the child to apply the applique means at his own pace.


Patent
19 Jan 1981
TL;DR: In this paper, an extraction method for optical character recognition systems is presented, in which the necessary character features for recognition process are extracted from a character information detected and digitized by an optical scanner.
Abstract: Disclosed is an extraction method for optical character recognition systems in which the necessary character features for recognition process are extracted from a character information detected and digitized by an optical scanner. In accordance with this method, the local features of every adjacent two rows or columns of a digitized character pattern on a two-dimensional plane are extracted row by row or column by column and are successively integrated so as to extract in a global manner the respective feature types such as concavity and convexity, loop and connectivity of the character pattern. At the same time, the global feature regions or segments are separated and each of the separated feature segments is coded without any loss of the information. The feature quantity of each segment is obtained on the basis of the coded representation. Any local concavity or convexity noises are eliminated simultaneously with the extraction of the global features.

Book ChapterDOI
01 Jan 1981
TL;DR: The characteristic feature of a longitudinal research design is that the same measurements are obtained from the same people at two or more occasions.
Abstract: The characteristic feature of a longitudinal research design is that the same measurements are obtained from the same people at two or more occasions. The purpose of a longitudinal or panel study is to assess the changes that occur between occasions and to attribute these changes to certain background characteristics and events existing or occurring before the first occasion and/or to various treatments and developments that occur after the first occasion. A schematic illustration of a two-wave longitudinal design is given in Figure 7.1.

Patent
14 Dec 1981
TL;DR: In this paper, a method for simultaneously producing two continuous cigarette rods is described, consisting of two simultaneous successions of stages, the first for forming two equal strips of paper starting from a single continuous web, and the second for forming substantially uniform and equal fillers of shredded tobacco starting from single inlet hopper.
Abstract: A method for simultaneously producing two continuous cigarette rods is described. The main feature of this method is to comprise two simultaneous successions of stages, the first for forming two equal strips of paper starting from a single continuous web, and the second for forming two substantially uniform and equal fillers of shredded tobacco starting from a single inlet hopper.


Journal ArticleDOI
TL;DR: A layout for the shuffle-exchange network with O(N2/log3/2N) area is described and an interesting feature of the layout is that both the shuffle and the exchange edges have the same average length.
Abstract: A layout for the shuffle-exchange network with O(N2/log3/2N) area is described. The layout combines ideas proposed by Thompson, Hoey, and Leiseron, and Preparata and Vuillemin. An interesting feature of the layout is that both the shuffle and the exchange edges have the same average length.

Proceedings ArticleDOI
12 Nov 1981
TL;DR: The derivation and use of invariants for image feature prediction is described and how predictions of image features and their relations are made and how instructions are generated which tell the interpretation algorithms how to make use of image feature measurments to derive three dimensional sizes and structural and spatial constraints on the original three-dimensional models.
Abstract: ACRONYM is a comprehensive domain independent model-based system for vision and manipulation related tasks. Many of its sub-modules and representations have been described elsewhere. Here the derivation and use of invariants for image feature prediction is described. We describe how predictions of image features and their relations are made and how instructions are generated which tell the interpretation algorithms how to make use of image feature measurments to derive three dimensional sizes and structural and spatial constraints on the original three-dimensional models. Some preliminary examples of ACRONYM'S interpretations of aerial images are shown.

Journal ArticleDOI
TL;DR: Even though computer technology may challenge one of man's last and most cherished illusions—that he alone is capable of thought—it can also show him how to live in harmony with nature.
Abstract: Even though computer technology may challenge one of man's last and most cherished illusions—that he alone is capable of thought—it can also show him how to live in harmony with nature.