Showing papers on "Feature (computer vision) published in 1989"

Kalman Filter-based Algorithms for Estimating Depth from Image Sequences

Abstract: Using known camera motion to estimate depth from image sequences is an important problem in robot vision. Many applications of depth-from-motion, including navigation and manipulation, require algorithms that can estimate depth in an on-line, incremental fashion. This requires a representation that records the uncertainty in depth estimates and a mechanism that integrates new measurements with existing depth estimates to reduce the uncertainty over time. Kalman filtering provides this mechanism. Previous applications of Kalman filtering to depth-from-motion have been limited to estimating depth at the location of a sparse set of features. In this paper, we introduce a new, pixel-based (iconic) algorithm that estimates depth and depth uncertainty at each pixel and incrementally refines these estimates over time. We describe the algorithm and contrast its formulation and performance to that of a feature-based Kalman filtering algorithm. We 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 new method is an effective way to extract depth from lateral camera translations. This approach can be extended to incorporate general motion and to integrate other sources of information, such as stereo. The algorithms we have developed, which combine Kalman filtering with iconic descriptions of depth, therefore can serve as a useful and general framework for low-level dynamic vision.

Feature extraction from faces using deformable templates

Abstract: A method for detecting and describing the features of faces using deformable templates is described. The feature of interest, an eye for example, is described by a parameterized template. An energy function is defined which links edges, peaks, and valleys in the image intensity to corresponding properties of the template. The template then interacts dynamically with the image, by altering its parameter values to minimize the energy function, thereby deforming itself to find the best fit. The final parameter values can be used as descriptors for the features. This method is demonstrated by showing deformable templates detecting eyes and mouths in real images. >

Multiresolution feature extraction and selection for texture segmentation

Abstract: An approach is described for unsupervised segmentation of textured images. Local texture properties are extracted using local linear transforms that have been optimized for maximal texture discrimination. Local statistics (texture energy measures) are estimated at the output of an equivalent filter bank by means of a nonlinear transformation (absolute value) followed by an iterative Gaussian smoothing algorithm. This procedure generates a multiresolution sequence of feature planes with a half-octave scale progression. A feature reduction technique is then applied to the data and is determined by simultaneously diagonalizing scatter matrices evaluated at two different spatial resolutions. This approach provides a good approximation of R.A. Fisher's (1950) multiple linear discriminants and has the advantage of requiring no a priori knowledge. This feature reduction methods appears to be an improvement on the commonly used Karhunen-Loeve transform and allows efficient texture segmentation based on simple thresholding. >

Vision-guided servoing with feature-based trajectory generation (for robots)

Abstract: The authors present a vision module which is able to guide an eye-in-hand robot through general servoing and tracking problems using off-the-shelf image-processing equipment. The vision module uses the location of binary image features from a camera on the robot's end-effector to control the position and one degree of orientation of the robot manipulator. A unique feature-based trajectory generator provides smooth motion between the actual image features and the desired image features even with asynchronous and discontinuous vision updates. By performing the trajectory generation in image feature space, image-processing constraints such as the feature extraction time can be accounted for when determining the appropriate segmentation and acceleration times of the trajectory. Experimental results of a PUMA robot tracking objects with vision feedback are discussed. >

Using perceptual organization to extract 3D structures

Abstract: The authors describe an approach to perceptual grouping for detecting and describing 3-D objects in complex images and apply it to the task of detecting and describing complex buildings in aerial images. They argue that representations of structural relationships in the arrangements of primitive image features, as detected by the perceptual organization process, are essential for analyzing complex imagery. They term these representations collated features. The choice of collated features is determined by the generic shape of the desired objects in the scene. The detection process for collated features is more robust than the local operations for region segmentation and contour tracing. The important structural information encoded in collated features aids various visual tasks such as object segmentation, correspondence processes, and shape description. The proposed method initially detects all reasonable feature groupings. A constraint satisfaction network is then used to model the complex interactions between the collations and select the promising ones. Stereo matching is performed on the collations to obtain height information. This aids in further reasoning on the collated features and results in the 3-D description of the desired objects. >

Aging, selective attention, and feature integration.

Abstract: This study used feature-integration theory as a means of determining the point in processing at which selective attention deficits originate. The theory posits an initial stage of processing in which features are registered in parallel and then a serial process in which features are conjoined to form complex stimuli. Performance of young and older adults on feature versus conjunction search is compared. Analyses of reaction times and error rates suggest that elderly adults in addition to young adults, can capitalize on the early parallel processing stage of visual information processing, and that age decrements in visual search arise as a result of the later, serial stage of processing. Analyses of a third, unconfounded, conjunction search condition reveal qualitatively similar modes of conjunction search in young and older adults. The contribution of age-related data limitations is found to be secondary to the contribution of age decrements in selective attention.

Constructive induction on decision trees

Abstract: Selective induction techniques perform poorly when the features are inappropriate for the target concept One solution is to have the learning system construct new features automatically; unfortunately feature construction is a difficult and poorly understood problem In this paper we present a definition of feature construction in concept learning, and offer a framework for its study based on four aspects: detection, selection, generalization, and evaluation This framework is used in the analysis of existing learning systems and as the basis for the design of a new system, CITRE CITRE performs feature construction using decision trees and simple domain knowledge as constructive biases Initial results on a set of spatial-dependent problems suggest the importance of domain knowledge and feature generalization, ie, constructive induction

Local Area Networks

Abstract: From the Publisher: This book is an introductory course in analysis of local area networks or computer networks. Its primary market is in electrical engineering,although the course is also taught in computer science departments. A major feature of the text is that it covers both performance analysis and implementation considerations.

Image recognition system and method

Abstract: An image recognition system (10) and method are provided for identifying a pattern of a plurality of predetermined patterns in a video image. A plurality of feature image signatures are extracted (84) and the stored (86) corresponding to each of the plurality of predetermined patterns. A universal feature image signature is extracted (84) and is stored (88) that includes each of the stored feature image signatures. A predetermined series of portions of a captured video image (28A) is sequentially compared (100, 102) with the universal feature image signature to identify matching portions. Each of the identified matching video image portions is compared (104, 108) with the stored feature image signatures to identify the predetermined pattern.

Eye tracking image pickup apparatus for separating noise from feature portions

Abstract: Characteristic features of images of an object eye are extracted to enable non-contact detection of eye movement. Two images of the eye are focused, and a differential image is generated to eliminate background noise and to permit feature extraction to be performed. In one feature of the invention, the illuminating light is polarized for use as a reference and the reflected light is separated to two light paths, each of which is focused to form an image of the object. In one path a polarizing plate blocks the regularly reflected light from the cornea so that only a diffused reflection component of the illuminating light from the other parts of the eye is passed, while in the other path both the regularly and diffusedly reflected light components are passed. A resulting differential image emphasizes the regular reflection component from the cornea relative to the background. In another aspect of the invention, two light sources are placed at different positions relative to the optical axis, to provide bright and dark images of the pupil without otherwise affecting the reflected image. A resulting differential image emphasizes the pupil relative to background noise.

Image shake detecting device

Abstract: An image shake detecting device for detecting a shake of an image on an image sensing plane on the basis of a video signal output from an image sensor includes detection circuits arranged to detect image displacement in a plurality of areas set on the image sensing plane, and a control microcomputer which makes a discrimination, on the basis of information output from these detection circuits, between a movement of a camera and a solo movement of a photographed object. The device thus accurately makes compensation for an image shake by judging the state of the image on the basis of information output from these detection circuits. The image shake detecting device further includes a computing circuit arranged to compute a quantity of an image shake on the basis of a difference in detecting timing of a feature point of the image and a sensitivity control circuit arranged to change the detection sensitivity of the shake detection circuits. Further disclosed is an object tracing device to which the invented image shake detecting device is applied.

A robot vision system for recognizing 3D objects in low-order polynomial time

Abstract: The authors present 3D-POLY, a working system for recognizing objects in the presence of occlusion and against cluttered backgrounds The time complexity of this system is only O(n/sup 2/) for single-object recognition, where n is the number of features on the project The organisation of the feature data for the models is based on a data structure called the feature sphere Efficient constant-time algorithms for assigning a feature to its proper place on a feature sphere and for extracting the neighbors of a given feature from the feature sphere representation are presented For hypothesis generation, local feature sets are used The combination of the feature sphere idea for streamlining verification and the local feature sets for hypothesis generation results in a system whose time complexity has a low-order polynomial bound >

Image generator for generating perspective views from data defining a model having opaque and translucent features

Abstract: An apparatus for generating an image from data defining a model including a plurality of opaque and translucent features. The image is intended to represent a view of the model from a predetermined eyepoint and is made up from an array of screen space pixels. The image area is divided into an array of sub-areas each of which covers at least one pixel. For each feature in the model that is potentially visible from the eyepoint, a test is conducted to determine which of the sub-areas is at least partially covered by that feature. For each feature which covers a sampling point, a function of the distance from the eyepoint to that feature at the sampling point is determined. An output for each pixel within a sub-area is produced, the pixel output corresponding to the combined effects of the sampling point outputs for all sampling points which contribute to that pixel, and the pixel outputs are displayed.

Dynamic stereo vision

Abstract: Sensing 3-D shape and motion is an important problem in autonomous navigation and manipulation. Stereo vision is an attractive approach to this problem in several domains. In this thesis, I address fundamental components of this problem by using stereo vision to estimate the 3-D structure of "depth" of objects visible to a robot, as well as to estimate the motion of the robot as its travels through an unknown environment. I begin by using cameras on-board a robot vehicle to estimate the motion of the vehicle by tracking 3-D feature-points or "landmarks". I formulate this task as a statistical estimation problem, develop sequential methods for estimating the vehicle motion and updating the landmark model, and implement a system that successfully tracks landmarks through stereo image sequences. In laboratory experiments, this system has achieved an accuracy of 2$\\$% of distance over 5.5 meters and 55 stereo image pairs. These results establish the importance of statistical modelling in this problem and demonstrate the feasibility of visual motion estimation in unknown environments. This work embodies a successful paradigm for feature-based depth and motion estimation, but the feature-based approach results in a very limited 3-D model of the environment. To extend this aspect of the system, I address the problem of estimating "depth maps" from stereo images. Depth maps specify scene depth for each pixel in the image. I propose a system architecture in which exploratory camera motion is used to acquire a narrow-baseline image pair by moving one camera of the stereo system. Depth estimates obtained from this image pair are used to "bootstrap" matching of a wide-baseline image pair acquired with both cameras of the system. I formulate the bootstrap operation statistically by modelling depth maps as random fields and developing Bayesian matching algorithms in which depth information from the narrow-baseline image pair determines the prior density for matching the wide baseline image pair. This leads to efficient, area-based matching algorithms that are applied independently for each pixel or each scanline of the image. Experimental results with images of complex, outdoor scene models demonstrate the power of the approach.

The feature interaction problem in telecommunications systems

Abstract: The development of telecommunications features is difficult for many of the same reasons that software development is difficult. The need for rapid feature introduction requires separation of applications from the system, allowing multiple vendors to concurrently develop features. A key obstacle to the concurrent development of features, the feature interaction problems is examined. As a framework for studying feature interactions their effects on customers and developers are discussed, and tools and methods that exist or are emerging that reduce their impact on the development process are considered.

QRS feature extraction using linear prediction

Abstract: The use of linear prediction for analyzing digital ECG signals is discussed. There are several significant properties indicating that ECG signals have an important feature in the residual error signal obtained after processing by Durbin's linear prediction algorithm. The prediction order need not be more than two for fast arrhythmia detection. The ECG signal classification puts an emphasis on the residual error signal. For the QRS complex of each ECG, the feature for recognition is obtained from a nonlinear transformation which transforms every residual error signal to a set of three states pulse-code train relative to the original ECG signal. The pulse-code train has the advantage of easy implementation in digital hardware circuits to achieve automated ECG diagnosis. The algorithm performs very well in feature extraction in arrhythmia detection. Using this method, the studies indicate that the PVC (premature ventricular contraction) detection has at least 92% sensitivity for MIT/BIH arrhythmia database. >

A neural network for feature linking via synchronous activity: Results from cat visual cortex and from simulations

Abstract: Preface Can memory be the brain+s Rosetta Stone? Functions of neuronal networks in the hippocampus and cerebral cortex in memory Conscious subjective experience vs. unconscious mental functions: a theory of the cerebral processes involved A parallel vision machine that learns Colour algorithms for image segmentation Physiological constraints on models of visual cortical function A model of preattentive region definition based on texture analysis Analysis of complex motion signals in the brain of cats and monkeys A simplifying strategy for modelling the retino-cortical pathway Towards a network theory of cortical areas The primary visual system: an attempt to understand the function of its structure

Supervised textured image segmentation using feature smoothing and probabilistic relaxation techniques

Abstract: A description is given of a supervised textured image segmentation algorithm that provides improved segmentation results. An improved method for extracting textured energy features in the feature extraction stage is described. It is based on an adaptive noise smoothing concept that takes the nonstationary nature of the problem into account. Texture energy features are first estimated using a window of small size to reduce the possibility of mixing statistics along region borders. The estimated texture energy feature values are smoothed by a quadrant filtering method to reduce the variability of the estimates while retaining the region border accuracy. The estimated feature values of each pixel are used by a Bayes classifier to make an initial probabilistic labeling. The spatial constraints are enforced through the use of a probabilistic relaxation algorithm. Two probabilistic relaxation algorithms are investigated. Limiting the probability labels by probability threshold is proposed. The tradeoff between efficiency and degradation of performed is studied. >

Process and apparatus for the automatic detection and extraction of features in images and displays

Abstract: A pattern recognition process and apparatus automatically extracts features in displays, images, and complex signals. Complex signals are processed to two- or higher-dimensional displays or other imagery. The displays or other imagery are then processed to produce one or more visual fields in which regions with certain properties are enhanced. The enchanced regions are induced to produce attractive forces. Flexible templates placed in the visual fields are acted upon by the attractive forces, causing the templates to deform in such a way as to match features which are similar, but not identical to, the template. The deformed templates are then evaluated in order to identify or interpret the feature to which the template was attracted. Apparatus utilizing the process generates a display of the features extracted from the input signal. Desired information can be obtained from such a display, such as trajectories, the location of ridges, buildings, edges, or other boundaries. The extracted features can be used within a control system to automatically guide an object, such as a vehicle or airplane, along a desired course; or within a signal processing system to provide a display of the features in a way that aids in the interpretation of such features.

Edge detection and linear feature extraction using a 2-D random field model

Abstract: The edge-detection problem is posed as one of detecting step discontinuities in the observed correlated image, using directional derivatives estimated with a random field model. Specifically, the method consists of representing the pixels in a local window by a 2-D causal autoregressive (AR) model, whose parameters are adaptively estimated using a recursive least-squares algorithm. The directional derivatives are functions of parameter estimates. An edge is detected if the second derivative in the direction of the estimated maximum gradient is negatively sloped and the first directional derivative and a local estimate of variance satisfy some conditions. Because the ordered edge detector may not detect edges of all orientations well, the image scanned in four different directions, and the union of the four edge images is taken as the final output. The performance of the edge detector is illustrated using synthetic and real images. Comparisons to other edge detectors are given. A linear feature extractor that operates on the edges produced by the AR model is presented. >

A hierarchical structure for form features

Abstract: A model for describing form feature geometry is presented. The model treats form features as volumes enveloped by entry/exit and depth boundaries. The geometric characteristics of a feature are decided by the degree of accessibility to its volume, its boundary type, its exit boundary status and its form variation with respect to its depth axis. A hierarchical structure for form features classification is also presented. Based on their geometric characteristics, features are classified into categories, classes and sub-classes. These can be followed by secondary forms to fully describe compound features. The feature description method together with the associated hierarchy provide a very flexible model for feature description and classification. The model is of direct relevance to many of the CAD/CAM activities and contain concepts that can help to ease their integration.

3D location of circular and spherical features by monocular model-based vision

Abstract: Mathematics is presented for using monocular model-based vision to find 3D positions of circular and spherical model features, and, for the circular case, orientations as well. Monocular model-based vision here refers to the use of a single projective image of modeled objects to solve for the 3D positions and orientations of the objects in the scene. A novel closed-formed solution for the 3D position and orientation of a circular features and the 3D position of a spherical feature is described. There are two general solutions for the circular feature bu there is only one solution when the surface normal of the circular feature passes through the center of projection. There is only one solution for the circular case. Advantages of this method are: (1) it handles spherical as well as circular features; (2) it has a closed-form solution; (3) it gives only the necessary number of solutions (no redundant solutions); (4) it uses simple mathematics involving 3D analytic geometry; and (5) it is geometrically intuitive. >

Camera or printer capable of automatically changing print size

Abstract: A photographic print control system includes a camera having the feature of indicating print size data and recording data relating to the print size so that a printer can read out the stored print size data and control a printing process for obtaining a print in the indicated size.

Automatic recognition and representation of shape-based features in a geometric modeling system

Abstract: A method is presented for the automatic identification and extraction of feature information from the solid model of an object. The procedure consists in recognizing shape features, extracting these features as solid volumes, and arranging them in a hierarchical structure. This hierarchical model, described in this article, represents the main shape of the object at the highest levels of abstraction and its form features at lower levels of specification. The system is divided into three modules: feature recognition, feature extraction and feature organization. The recognitition step works on a face-based representation of solid objects, called a face adjacency hypergraph and it takes advantage of Kyprianou's method ( Shape Classification in Computer-Aided-Design , Ph.D. thesis, Computer Laboratory, University of Cambridge, England, July 1980). In the extraction phase each recognized form feature is completed by dummy entities in order to form a feasible object and in the organization step the completed features are arranged into a hierarchical graph, called Structured Face Adjacency Hypergraph.

Automatic color segmentation of images with application to detection of variegated coloring in skin tumors

Abstract: A description is given of a computer vision system, developed to serve as the front-end of a medical expert system, that automates visual feature identification for skin tumor evaluation. The general approach is to create different software modules that detect the presence or absence of critical features. Image analysis with artificial intelligence (AI) techniques, such as the use of heuristics incorporated into image processing algorithms, is the primary approach. On a broad scale, this research addressed the problem of segmentation of a digital image based on color information. The algorithm that was developed to segment the image strictly on the basis of color information was shown to be a useful aid in the identification of tumor border, ulcer, and other features of interest. As a specific application example, the method was applied to 200 digitized skin tumor images to identify the feature called variegated coloring. Extensive background information is provided, and the development of the algorithm is described. >

Model construction and shape recognition from occluding contours

Abstract: A technique is presented for recognizing a 3D object (a model in an image library) from a single 2D silhouette using information such as corners (points with high positive curvatures) and occluding contours, rather than straight line segments. The silhouette is assumed to be a parallel projection of the object. Each model is stored as a set of the principal quadtrees, from which the volume/surface octree of the model is generated. Feature points (i.e. corners) are extracted to guide the recognition process. Four-point correspondences between the 2D feature points of the observed object and 3D feature points of each model are hypothesized, and then verified by applying a variety of constraints to their associated viewing parameters. The result of the hypothesis and verification process is further validated by 2D contour matching. This approach allows for a method of handling both planar and curved objects in a uniform manner, and provides a solution to the recognition of multiple objects with occlusion as demonstrated by the experimental results. >