scispace - formally typeset
Search or ask a question

Showing papers on "Feature (computer vision) published in 1988"


Journal ArticleDOI
TL;DR: The results of a series of search experiments are interpreted as evidence that focused attention to single items or to groups is required to reduce background activity when the Weber fraction distinguishing the pooled feature activity with displayscontaining a target and with displays containing only distractors is too small to allow reliable discrimination.
Abstract: In this article we review some new evidence relating to early visual processing and propose an explanatory framework. A series of search experiments tested detection of targets distinguished from the distractors by differences on a single dimension. Our aim was to use the pattern of search latencies to infer which features are coded automatically in early vision. For each of 12 different dimensions, one or more pairs of contrasting stimuli were tested. Each member of a pair played the role of target in one condition and the role of distractor in the other condition. Many pairs gave rise to a marked asymmetry in search latencies, such that one stimulus in the pair was detected either through parallel processing or with small increases in latency as display size increased, whereas the other gave search functions that increased much more steeply. Targets denned by larger values on the quantitative dimensions of length, number, and contrast, by line curvature, by misaligned orientation, and by values that deviated from a standard or prototypical color or shape were detected easily, whereas targets defined by smaller values on the quantitative dimensions, by straightness, by frame-aligned orientation, and by prototypical colors or shapes required slow and apparently serial search. These values appear to be coded by default, as the absence of the contrasting values. We found no feature of line arrangements that allowed automatic, preattentive detection; nor did connectedness or containment—the two examples of topological features that we tested. We interpret the results as evidence that focused attention to single items or to groups is required to reduce background activity when the Weber fraction distinguishing the pooled feature activity with displays containing a target and with displays containing only distractors is too small to allow reliable discrimination.

2,240 citations


Book
01 Jan 1988
TL;DR: The notion of science is a dominant and enduring feature of Western thought as mentioned in this paper, which has begun to transform attitudes to science traditionally upheld by historians and philosophers, which has been called the social study of science.
Abstract: The notion of science is a dominant and enduring feature of Western thought. This book looks at the social study of science, which has begun to transform attitudes to science traditionally upheld by historians and philosophers.

794 citations


Journal ArticleDOI
TL;DR: Although differences in surface characteristics such as color, brightness, and texture can be instrumental in defining edges and can provide cues for visual search, they play only a secondary role in the real-time recognition of an intact object when its edges can be readily extracted.

614 citations


Journal ArticleDOI
TL;DR: In this paper, a review of feature selection for multidimensional pattern classification is presented, and the potential benefits of Monte Carlo approaches such as simulated annealing and genetic algorithms are compared.
Abstract: We review recent research on methods for selecting features for multidimensional pattern classification. These methods include nonmonotonicity-tolerant branch-and-bound search and beam search. We describe the potential benefits of Monte Carlo approaches such as simulated annealing and genetic algorithms. We compare these methods to facilitate the planning of future research on feature selection.

366 citations


Proceedings ArticleDOI
24 Jul 1988
TL;DR: A neural-network clustering algorithm proposed by T. Kohonen (1986, 88) is used to design a codebook for the vector quantization of images and the results are compared with coded images when the cookbook is designed by the Linde-Buzo-Gray algorithm.
Abstract: A neural-network clustering algorithm proposed by T. Kohonen (1986, 88) is used to design a codebook for the vector quantization of images. This neural-network clustering algorithm, which is better known as the Kohonen self-organizing feature maps, is a two-dimensional set of extensively interconnected nodes or unit of processors. The synaptic strengths between the input and the output nodes represent the centroid of the clusters after the network has been adapted to the input patterns. Input vectors are presented one at a time, and the weights connecting the input signals to the neurons are adaptively updated such that the point density function of the weights tends to approximate the probability density function of the input vector. Results are presented for a number of coded images using the codebook designed by the self-organization feature maps. The results are compared with coded images when the cookbook is designed by the Linde-Buzo-Gray algorithm. >

247 citations


Journal ArticleDOI
TL;DR: An explicit three-dimensional representation is constructed from feature points extracted from a sequence of images taken by a moving camera, and their 3D locations are accurately determined by use of Kalman filters.

178 citations


Journal ArticleDOI
TL;DR: A method of classifying single view deaf-and-mute sign language motion images by extracting 2-D features of the location of a hand and its movement from the red component of the input color image sequence.

159 citations


Journal ArticleDOI
TL;DR: A neural-network clustering algorithm proposed by T. Kohonen (1986, 88) is used to design a codebook for the vector quantization of images and the results are compared with coded images when the cookbook is designed by the Linde-Buzo-Gray algorithm.

155 citations


Journal ArticleDOI
TL;DR: A robotic system for object recognition is described that uses passive stereo vision and active exploratory tactile sensing and the ability of such a system to recognize objects that would be difficult for a system using vision alone is demonstrated.
Abstract: A robotic system for object recognition is described that uses passive stereo vision and active exploratory tactile sensing. The complementary nature of these sensing modalities allows the system to discover the underlying 3-D structure of the objects to be recognized. This structure is embodied in rich, hierarchical, viewpoint-independent 3-D models of the objects which include curved surfaces, concavities and holes. The vision processing provides sparse 3-D data about regions of interest that are then actively explored by the tactile sensor mounted on the end of a six-degree-of-freedom manipulator. A robust, hierarchical procedure has been developed to inte grate the visual and tactile data into accurate 3-D surface and feature primitives. This integration of vision and touch provides geometric measures of the surfaces and features that are used in a matching phase to find model objects that are consistent with the sensory data. Methods for verification of the hypothesis are presented, including the sen...

149 citations


Journal ArticleDOI
TL;DR: The utilization of the technique is demonstrated in its application to a simulated MR image sequence as well as to acquired MR image sequences of a normal and an abnormal brain.
Abstract: This article presents the technical aspects of a linear filter, referred to as eigenimage filtering, and its applications in magnetic resonance (MR) imaging. The technique is used to obtain a single composite image depicting a particular feature of interest while suppressing one or more interfering features. The appropriate weighting components to be used in the linear filter are determined on the criterion that the desired feature is enhanced while the interfering features are suppressed. The criterion is expressed mathematically as a ratio. By applying Rayleigh's principle, the ratio is maximized by finding the eigenvector associated with the maximum eigenvalue of the corresponding generalized eigenvalue problem. The appropriate weighting factors for the linear filter are the elements of the eigenvector which maximize the ratio. The utilization of the technique is demonstrated in its application to a simulated MR image sequence as well as to acquired MR image sequences of a normal and an abnormal brain.

137 citations


Patent
08 Dec 1988
TL;DR: In this article, a machine is presented that is capable of locating human faces in video scenes with random content within two minutes, and capable of recognizing the faces that it locates.
Abstract: A machine is disclosed that is capable of locating human faces in video scenes with random content within two minutes, and capable of recognizing the faces that it locates. The machine uses images obtained from a video camera and is insensitive to variations in brightness, scale, focus, and operates without any human intervention or inputs. When a motion detection feature is included, (one of its options), the location and recognition events occur in less than 1 minute. One embodiment of the system uses: a camera, a Micro-Vax computer, an analog-go-digital A/D converter, and a hard copy print out to process video scenes with random content using an original computer program to locate human faces and identify them. In operation, the camera converts the video scenes into an analog electrical signal, which is converted into digital and forwarded to the computer. The computer performs an original pattern recognition algorithm to search for facial components, identify a gestalt face, and compare the gestalt-face's detected facial characteristics with a stored set of facial characteristics of known human faces, to identify the face thereby.

Book ChapterDOI
01 Jan 1988
TL;DR: A property which is commonplace in the brain but which has always been ignored in the “learning machines” is a meaningful order of their processing units.
Abstract: A property which is commonplace in the brain but which has always been ignored in the “learning machines” is a meaningful order of their processing units. “Ordering” thereby usually does not mean moving of units to new places. The units may even be structurally identical; the specialized role is determined by their internal parameters which are made to change in certain processes. It then appears as if specific units having a meaningful organization were produced.

Journal ArticleDOI
Utpal Roy1, C. R. Liu1
TL;DR: This paper discusses the requirements of a new CAD data model and proposes a feature-based representation scheme based on the hybrid CSG/B-Rep data structure, which exploits the advantages of both CSG and B-Rep models in representing tolerance information.
Abstract: Presently available CAD data models have no problem handling the basic shape design of an object as required but they are not properly manufacturing-oriented. It is not possible to represent the dimensioning and tolerancing information or other technological information (such as material data, the surface roughness and accuracy data, feature information, etc.). This paper discusses the requirements of a new CAD data model and proposes a feature-based representation scheme based on the hybrid CSG/B-Rep data structure. This hybrid structure exploits the advantages of both CSG and B-Rep models in representing tolerance information. A relational graph structure (face-based data model of B-Rep) of the object is maintained at each hierarchical level of object construction for associating tolerance and other attributes.

Journal ArticleDOI
TL;DR: This paper identifies several transformation/mapping mechanisms, and discusses the implementation of a mapping shell for some of these transformations, and identifies several mechanisms most suited to a given reasoning process.
Abstract: Information sets (features) used in engineering design and manufacturing applications depend on the product type, the application and the process involved. Some features identified in a particular domain may be partially or fully mappable to other domains, while it may be that others are not. To integrate software for design, analysis and manufacturing, it is necessary to create feature mapping systems to transform information in shared or neutral databases to application-specific features most suited to a given reasoning process. This paper identifies several transformation/mapping mechanisms, and discusses the implementation of a mapping shell for some of these transformations.

Journal ArticleDOI
TL;DR: A procedure for assessing the state of a system in which the presence of a particular feature is tested on each trial is described, resulting in a modification of a class of plausible states.

Journal ArticleDOI
TL;DR: Results show that the proposed technique is intelligently tunable to the requirements of enhancement of specific mammographic features such as microcalcifications, soft-tissue characteristics, etc.

Journal ArticleDOI
TL;DR: The estimation of optical flow fields is discussed, exhibiting a common foundation for feature-based and differential approaches, and the desire to describe the spatio-temporal development recorded by an image sequence not only at the level of geometry, but also at higher conceptual levels.
Abstract: Many investigations of image sequences can be understood on the basis of a few concepts for which computational approaches become increasingly available. The estimation of optical flow fields is discussed, exhibiting a common foundation for feature-based and differential approaches. The interpretation of optical flow fields is mostly concerned so far with approaches which infer the 3-D structure of a rigid point configuration in 3-D space and its relative motion with respect to the image sensor from an image sequence. The combination of stereo and motion provides additional incentives to evaluate image sequences, especially for the control of robots and autonomous vehicles. Advances in all these areas lead to the desire to describe the spatio-temporal development recorded by an image sequence not only at the level of geometry, but also at higher conceptual levels, for example by natural language descriptions.

Journal ArticleDOI
TL;DR: A perceptual judgement task was carried out in which subjects were presented with a number of modified faces and asked to judge how dissimilar these were with respect to an original image and a multidimensional scaling analysis of the comparative judgements of the subjects revealed a two-dimensional solution involving displacement of the eyes and mouth.
Abstract: The effect of feature displacement within two well-known faces (Terry Wogan and Cyril Smith) was examined. Image processing equipment was used to produce stimuli in which the features of an original facial image were displaced to form a number of modified images. This technique was first reported by Haig, in a recognition study in which the effect of feature displacement within unfamiliar faces was investigated. In the present experiment a perceptual judgement task was carried out in which subjects were presented with a number of modified faces and asked to judge how dissimilar these were with respect to an original image. A multidimensional scaling analysis of the comparative judgements of the subjects revealed a two-dimensional solution involving displacement of the eyes and mouth. A clear division between up/down and inward/outward displacement within these features (particularly the eyes) was observed. A similar pattern of results was found for both well-known faces. This result indicates that subject...

Journal ArticleDOI
TL;DR: A novel texture segmentation algorithm that is based on a combination of the new feature description and multiresolution techniques is described and shown to give accurate segmentations on a range of synthetic and natural textures.
Abstract: For pt.I see ibid., vol.9, no.6, p.787 (1987). The problem of uncertainty in image feature description is discussed, and it is shown how finite prolate spheroidal sequences can be used in the construction of feature descriptions that combine spatial and frequency-domain locality in an optimal way. Methods of constructing such optimal feature sets, which are suitable for graphical implementation, are described, and some generalizations of the quadtree concept are presented. These methods are illustrated by examples from image processing applications, including feature extraction and texture description. The problem of image segmentation is discussed, and the importance of scale invariance in overcoming the limitations imposed by uncertainty is demonstrated. A novel texture segmentation algorithm that is based on a combination of the new feature description and multiresolution techniques is described and shown to give accurate segmentations on a range of synthetic and natural textures. >

Journal ArticleDOI
TL;DR: How do you explain to employees that computer abuse, information theft, and like crimes actually hurt the employees themselves?

Patent
07 Mar 1988
TL;DR: In this paper, a vision system for a mobile robot consisting of an optical sensor subsystem 20 which generates a substantially one dimensional image of an environment, a signal processing subsystem 24 for extracting and enhancing significant vertical visual features from the one-dimensional image and a feature processing system 26 which analyses rapidly and in real time the extracted features for use by a control system 28 for navigation of the robot.
Abstract: A vision system for a mobile robot 10 comprises an optical sensor subsystem 20 which generates a substantially one dimensional image of an environment, a signal processing subsystem 24 for extracting and enhancing significant vertical visual features from the one dimensional image and a feature processing system 26 which analyses rapidly and in real time the extracted features for use by a control system 28 for navigation of the robot. The optical sensor may be a line scan camera having a plurality of outputs which relate to brightness values received from the environment. Triangulation, optical flow and optical flow with log transforms methods are disclosed for processing the one dimensional image data to yield azimuth and/or distance to an object within the environment. Also disclosed is a binocular vision system which generates two, one dimensional images and a method of processing same.

Proceedings ArticleDOI
05 Jun 1988
TL;DR: The authors introduce a novel pixel-based (iconic) algorithm that estimates depth and depth uncertainty at each pixel and incrementally refines these estimates over time and suggest that it will play an important role in low-level vision.
Abstract: The authors introduce a novel pixel-based (iconic) algorithm that estimates depth and depth uncertainty at each pixel and incrementally refines these estimates over time. They describe the algorithm for translations parallel to the image plane and contrast its formulation and performance to that of a feature-based Kalman filtering algorithm. They compare the performance of the two approaches by analyzing their theoretical convergence rates, by conducting quantitative experiments with images of a flat poster, and by conducting qualitative experiments with images of a realistic outdoor scene model. The results show that the method is an effective way to extract depth from lateral camera translations and suggest that it will play an important role in low-level vision. >

Journal ArticleDOI
TL;DR: An online unsupervised feature-extraction method for high-dimensional remotely sensed image data compaction and the classification performance is improved slightly by using object features rather than the original data, and the CPU time required for classification is reduced.
Abstract: An online unsupervised feature-extraction method for high-dimensional remotely sensed image data compaction is proposed. This method is directed at the reduction of data redundancy in the scene representation of satellite-borne, high-resolution multispectral sensor data. The algorithm partitions the observation space into an exhaustive set of disjoint objects, and pixels belonging to each object are characterized by an object feature. The set of object features, rather than the pixel features, is used for data transmission and classification. Illustrative examples of high-dimensional image data compaction are presented, and the feature representation performance is investigated. Example results show an average compaction coefficient of more than 25 to 1 when this method is used; the classification performance is improved slightly by using object features rather than the original data, and the CPU time required for classification is reduced by a factor of more than 25 as well. The feature extraction CPU time is less than 15% of CPU time for original data classification. >

Proceedings ArticleDOI
05 Jun 1988
TL;DR: The authors show that image velocity estimates can be obtained from dynamic activation profiles using a modification of familiar gradient techniques, and formulate the velocity estimators for dynamic edges in 1-D and 2-D image sequences, as well as that for dynamic feature points in 2- D image sequences.
Abstract: A method is developed for the measurement of short-range visual motion in image sequences, making use of the motion of image features such as edges and points. Each feature generates a Gaussian activation profile in a spatiotemporal neighborhood of specified scale around the feature itself; this profile is then convected with motion of the feature. The authors show that image velocity estimates can be obtained from such dynamic activation profiles using a modification of familiar gradient techniques. The resulting estimators can be formulated in terms of simple ratios of spatiotemporal filters (i.e. receptive fields) convolved with image feature maps. A family of activation profiles of varying scale must be utilized to cover a range of possible image velocities. They suggest a characteristic speed normalization of the estimate obtained from each filter in order to decide which estimate is to be accepted. They formulate the velocity estimators for dynamic edges in 1-D and 2-D image sequences, as well as that for dynamic feature points in 2-D image sequences. >

Journal ArticleDOI
TL;DR: The method has been successfully applied on recognition of the spleen in abdominal X-ray CT scans and is proposed for segmentation of organs in CT-image sequences.

Proceedings ArticleDOI
07 Jun 1988
TL;DR: The paper describes a new implementation of feature structures containing disjunctive values, which can be characterized by the following main points: local representation of embedded disjunctions, avoidance of expansion to disJunctive normal form and of repeated test-unifications for checking consistence.
Abstract: The paper describes a new implementation of feature structures containing disjunctive values, which can be characterized by the following main points: Local representation of embedded disjunctions, avoidance of expansion to disjunctive normal form and of repeated test-unifications for checking consistence. The method is based on a modification of Kasper and Rounds' calculus of feature descriptions and its correctness therefore is easy to see. It can handle cyclic structures and has been incorporated successfully into an environment for grammar development.

PatentDOI
TL;DR: In this article, a linear predictive coder (LPC) generates a plurality of spectral feature vectors for each frame of the speech signals and a filter bank system transforms the spectral feature vector to filter bank representations.
Abstract: Recognition of sound units is improved by comparing frame-pair feature vectors which helps compensate for context variations in the pronunciation of sound units. A plurality of reference frames are stored of reference feature vectors representing reference words. A linear predictive coder (10) generates a plurality of spectral feature vectors for each frame of the speech signals. A filter bank system (12) transforms the spectral feature vectors to filter bank representations. A principal feature vector transformer (14) transforms the filter bank representations to an identity matrix of transformed input feature vectors. A concatenate frame system (16) concatenates the input feature vectors of adjacent frames to form the feature vector of a frame-pair. A transformer (18) and a comparator (20) compute the likelihood that each input feature vector for a frame-pair was produced by each reference frame. This computation is performed individually and independently for each reference frame-pairs. A dynamic time warper (22) constructs an optimum time path through the input speech signals for each of the computed likelihoods. A high level decision logic (24) recognizes the input speech signals as one of the reference words in response to the computed likelihoods and the optimum time paths.

Journal ArticleDOI
TL;DR: This project involves the automation of the 3D reconstruction process, focusing on the problem of registering or aligning successive serial sections, and demonstrates that good registration accuracy is obtained using both kinds of feature points under conditions in which the contours do not have exact matches.
Abstract: Three dimensional (3D) reconstruction of serial sections through biological tissue is a very important method for visualizing and quantifying the 3D relationships between internal structures. This project involves the automation of the 3D reconstruction process, focusing on the problem of registering or aligning successive serial sections. Serial sections can be misregistered with respect to rotation, translation and scaling (if magnification is not constant). A linear least squares fitting procedure is developed to determine the required registration transformation based on a set of labeled feature points. The results obtained from using two different types of feature points are evaluated and compared: (1) manually selected feature points and (2) characteristic shape points computed from the contours which describe specific shape properties (e.g., centroid and radius weighted mean point). These results demonstrate that good registration accuracy is obtained using both kinds of feature points under conditions in which the contours do not have exact matches.

Journal ArticleDOI
01 Mar 1988
TL;DR: The authors explain the use of units responsive to Gabor signals in vision, considered as a process in inference from the retinal signals to a symbolic description, which is derived directly from the fundamental constraints on visual inference.
Abstract: Recent physiological research has indicated that the visual system makes use of units responsive to Gabor signals in the analysis of visual stimuli. Such functions effect a tradeoff between pure spatial- and frequency-domain descriptions. The authors explain the use of such representations in vision, considered as a process in inference from the retinal signals to a symbolic description. The appropriate mathematical structure for the inference is that of the subspaces of the signal vector space, a feature which it shares with quantum mechanics. The theory is derived directly from the fundamental constraints on visual inference. It is then shown to be consistent with many of the known properties of the visual system. In particular, a major feature of the inference system-the occurrence of interference effects-has already been observed in visual system operation. >

Patent
09 Dec 1988
TL;DR: In this paper, a character recognition method is proposed to read a document having characters displayed thereon and entering a document data representative of the content of the document, where image data of one of the characters from the document data is extracted.
Abstract: A character recognition method includes reading a document having characters displayed thereon and entering a document data representative of the content of the document. Image data of one of the characters from the document data is extracted. The one character has an orientation rotated by an arbitrary rotation angle from a predefined reference position for the one character. A first feature quantity of the one character is extracted from the extracted image data. The extracted feature quantity is converted into a second feature quantity of the one character in the reference position based on the arbitrary rotation angle. A dictionary which contains stored feature quantities of a plurality of characters in the reference position is interrogated so as to find a primary candidate character which has a feature quantity matching or most closely resembling the converted feature quantity.