Showing papers on "Feature (computer vision) published in 1992"

The feature selection problem: traditional methods and a new algorithm

Abstract: For real-world concept learning problems, feature selection is important to speed up learning and to improve concept quality We review and analyze past approaches to feature selection and note their strengths and weaknesses We then introduce and theoretically examine a new algorithm Rellef which selects relevant features using a statistical method Relief does not depend on heuristics, is accurate even if features interact, and is noise-tolerant It requires only linear time in the number of given features and the number of training instances, regardless of the target concept complexity The algorithm also has certain limitations such as nonoptimal feature set size Ways to overcome the limitations are suggested We also report the test results of comparison between Relief and other feature selection algorithms The empirical results support the theoretical analysis, suggesting a practical approach to feature selection for real-world problems

The Image Processing Handbook

Abstract: Consistently rated as the best overall introduction to computer-based image processing, The Image Processing Handbook covers two-dimensional (2D) and three-dimensional (3D) imaging techniques, image printing and storage methods, image processing algorithms, image and feature measurement, quantitative image measurement analysis, and more. Incorporating image processing and analysis examples at all scales, from nano- to astro-, this Seventh Edition: Features a greater range of computationally intensive algorithms than previous versions Provides better organization, more quantitative results, and new material on recent developments Includes completely rewritten chapters on 3D imaging and a thoroughly revamped chapter on statistical analysis Contains more than 1700 references to theory, methods, and applications in a wide variety of disciplines Presents 500+ entirely new figures and images, with more than two-thirds appearing in color The Image Processing Handbook, Seventh Edition delivers an accessible and up-to-date treatment of image processing, offering broad coverage and comparison of algorithms, approaches, and outcomes.

Feature extraction from faces using deformable templates

Abstract: We propose a method for detecting and describing features of faces using deformable templates. 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 parametr values can be used as descriptors for the feature. We illustrate this method by showing deformable templates detecting eyes and mouths in real images. We demonstrate their ability for tracking features.

Dynamic map building for an autonomous mobile robot

Abstract: This article presents an algorithm for autonomous map building and maintenance for a mobile robot. We believe that mobile robot navigation can be treated as a problem of tracking ge ometric features that occur naturally in the environment. We represent each feature in the map by a location estimate (the feature state vector) and two distinct measures of uncertainty: a covariance matrix to represent uncertainty in feature loca tion, and a credibility measure to represent our belief in the validity of the feature. During each position update cycle, pre dicted measurements are generated for each geometric feature in the map and compared with actual sensor observations. Suc cessful matches cause a feature's credibility to be increased. Unpredicted observations are used to initialize new geometric features, while unobserved predictions result in a geometric feature's credibility being decreased. We describe experimental results obtained with the algorithm that demonstrate successful map building using real son...

Quantifying the neighborhood preservation of self-organizing feature maps

Abstract: It is shown that a topographic product P, first introduced in nonlinear dynamics, is an appropriate measure of the preservation or violation of neighborhood relations. It is sensitive to large-scale violations of the neighborhood ordering, but does not account for neighborhood ordering distortions caused by varying areal magnification factors. A vanishing value of the topographic product indicates a perfect neighborhood preservation; negative (positive) values indicate a too small (too large) output space dimensionality. In a simple example of maps from a 2D input space onto 1D, 2D, and 3D output spaces, it is demonstrated how the topographic product picks the correct output space dimensionality. In a second example, 19D speech data are mapped onto various output spaces and it is found that a 3D output space (instead of 2D) seems to be optimally suited to the data. This is an agreement with a recent speech recognition experiment on the same data set. >

A feature based approach to face recognition

Abstract: A feature-based approach to face recognition in which the features are derived from the intensity data without assuming any knowledge of the face structure is presented. The feature extraction model is biologically motivated, and the locations of the features often correspond to salient facial features such as the eyes, nose, etc. Topological graphs are used to represent relations between features, and a simple deterministic graph-matching scheme that exploits the basic structure is used to recognize familiar faces from a database. Each of the stages in the system can be fully implemented in parallel to achieve real-time recognition. Experimental results for a 128*128 image with very little noise are evaluated. >

Robust Model-based Motion Tracking Through the Integration of Search and Estimation

Abstract: A computer vision system has been developed for real-time motion tracking of 3-D objects, including those with variable internal parameters. This system provides for the integrated treatment of matching and measurement errors that arise during motion tracking. These two sources of error have very different distributions and are best handled by separate computational mechanisms. These errors can be treated in an integrated way by using the computation of variance in predicted feature measurements to determine the probability of correctness for each potential matching feature. In return, a best-first search procedure uses these probabilities to find consistent sets of matches, which eliminates the need to treat outliers during the analysis of measurement errors. The most reliable initial matches are used to reduce the parameter variance on further iterations, minimizing the amount of search required for matching more ambiguous features. These methods allow for much larger frame-to-frame motions than most previous approaches. The resulting system can robustly track models with many degrees of freedom while running on relatively inexpensive hardware. These same techniques can be used to speed verification during model-based recognition.

Shape and motion from image streams: a factorization method

Abstract: We propose a method for estimating the three-dimensional shape of objects and the motion of the camera from a stream of images. The goal is to give a robot the ability to localize itself with respect to the environment, draw a map of its own surroundings, and perceive the shape of objects in order to recognize or grasp them. Solutions proposed in the past were so sensitive to noise as to be of little use in practical applications. This sensitivity is closely related to the viewer-centered representation of scene geometry known as a depth map, and to the use of stereo triangulation to infer depth from the images. In fact, when objects are more than a few focal lengths away from the camera, parallax effects become subtle, and even a small amount of noise in the images produces large errors in the final shape and motion results. In our formulation, we represent shape in object-centered coordinates, and model image formation by orthographic, rather than perspective projection. In this way, depth, the distance between viewer and scene, plays no role, and the problem's sensitivity to noise is critically reduced. We collect the image coordinates of P feature points tracked through F frames into a 2F x P measurement matrix. If these coordinates are measured with respect to their centroid, we show that the measurement matrix can be written as the product of two matrices that represent the camera rotation and the positions of the feature points in space. The bilinear nature of this model, and its matrix formulation, lead to a factorization method for the computation of shape and motion, based on the Singular Value Decomposition. Previous solutions assumed motion to be smooth, in one form or another, in an attempt to constrain the solution and achieve reliable convergence. The factorization method, on the other hand, makes no assumption about the camera motion, and can deal with the large jumps from frame to frame found, for instance, in sequences taken with a hand-held camera. To make the factorization method into a working system, we solve several corollary problems: how to select image features, how to track them from frame to frame, how to deal with occlusions, and how to cope with the noise and artifacts that corrupt images recorded with ordinary equipment. We test the entire system with a series of experiments on real images taken both in the lab, for an accurate performance evaluation, and outdoors, to demonstrate the applicability of the method in real-life situations.

Simulating the grassfire transform using an active contour model

Abstract: A method for shape description of planar objects that integrates both region and boundary features is presented. The method is an implementation of a 2D dynamic grassfire that relies on a distance surface on which elastic contours minimize an energy function. The method is based on an active contour model. Numerous implementation aspects of the shape description method were optimized. A Euclidean metric was used for optimal accuracy, and the active contour model permits bypassing some of the discretization limitations inherent in using a digital grid. Noise filtering was performed on the basis of both contour feature measures and region measures, that is, curvature extremum significance and ridge support, respectively, to obtain robust shape descriptors. Other improvements and variations of the algorithmic implementation are proposed. >

A computational vision approach to image registration

Abstract: A computational vision approach is presented for the estimation of 2-D translation, rotation, and scale from two partially overlapping images. The approach results in a fast method that produces good results even when large rotation and translation have occurred between the two frames and the images are devoid of significant features. An illuminant direction estimation method is first used to obtain an initial estimation of camera rotation. A small number of feature points are then located, using a Gabor wavelet model for detecting local curvature discontinuities. An initial estimate of scale and translation is obtained by pairwise matching of the feature points detected from both frames. Finally, hierarchical feature matching is performed to obtain an accurate estimate of translation, rotation and scale. A method for error analysis of matching results is also presented. Experiments with synthetic and real images show that this algorithm yields accurate results when the scale of the images differ by up to 10%, the overlap between the two frames is as small as 23%, and the camera rotation between the two frames is significant. Experimental results and applications are presented. >

Fast vision-guided mobile robot navigation using model-based reasoning and prediction of uncertainties

Abstract: The model-based vision system described in this paper allows a mobile robot to navigate indoors at an average speed of 8 to 10 m/min using ordinary laboratory computing hardware of approximately 16 MIPS power. The navigation capabilities of the robot are not impaired by the presence of stationary or moving obstacles. The vision system maintains a model of uncertainty and keeps track of the growth of uncertainty as the robot travels toward the goal position. The estimates of uncertainty are then used to predict bounds on the locations and orientations of landmarks expected to be seen in a monocular image. This greatly reduces the search for establishing correspondence between the features visible in the image and the landmarks. Given a sequence of image features and a sequence of landmarks derived from a geometric model of the environment, a special aspect of our vision system is the sequential reduction in the uncertainty as each image feature is matched successfully with a landmark, allowing subsequent features to be matched more easily; this is a natural by-product of the manner in which we use Kalman filter-based updating.

Model-Based Object Pose in 25 Lines of Code

Abstract: We find the pose of an object from a single image when the relative geometry of four or more noncoplanar visible feature points is known We first describe an algorithm, POS (Pose from Orthography and Scaling), that solves for the rotation matrix and the translation vector of the object by a linear algebra technique under the scaled orthographic projection approximation We then describe an iterative algorithm, POSIT (POS with ITerations), that uses the pose found by POS to remove the “perspective distortions” from the image, then applies POS to the corrected image instead of the original image POSIT generally converges to accurate pose measurements in a few iterations Mathematica code is provided in an Appendix

Parametric query optimization

Abstract: In most database systems, the values of many important run-time parameters of the system, the data, or the query are unknown at query optimization time. Parametric query optimization attempts to identify at compile time several execution plans, each one of which is optimal for a subset of all possible values of the run-time parameters. The goal is that at run time, when the actual parameter values are known, the appropriate plan should be identifiable with essentially no overhead. We present a general formulation of this problem and study it primarily for the buffer size parameter. We adopt randomized algorithms as the main approach to this style of optimization and enhance them with a sideways information passing feature that increases their effectiveness in the new task. Experimental results of these enhanced algorithms show that they optimize queries for large numbers of buffer sizes in the same time needed by their conventional versions for a single buffer size, without much sacrifice in the output quality and with essentially zero run-time overhead.

Fast Vision-guided Mobile Robot Navigation Using Model-based Reasoning And Prediction Of Uncertainties

Abstract: The model-based vision system described in this thesis allows a mobile robot to navigate indoors at an average speed of 8 meters/minute using ordinary laboratory computing hardware of approximately 16 MIPS power. The navigation capabilities of the robot are not impaired by the presence of the stationary or moving obstacles. The vision system maintains a model of uncertainty and keeps track of the growth of uncertainty as the robot travels towards the goal position. The estimates of uncertainty are then used to predict bounds on the locations and orientations of landmarks expected to be seen in a monocular image. This greatly reduces the search for establishing correspondence between the features visible in the image and the landmarks. Given a sequence of image features and a sequence of landmarks derived from a geometric model of the environment, a special aspect of our vision system is the sequential reduction in the uncertainty as each image feature is matched successfully with a landmark, allowing subsequent features to be matched more easily, this being a natural byproduct of the manner in which we use Kalman-filter based updating. Strategies for path planning, path replanning and perception planning are introduced for the robot to navigate in the presence of obstacles. Finally, experimental results are presented.

Model-Based Object Tracking in Traffic Scenes

Abstract: This contribution addresses the problem of detection and tracking of moving vehicles in image sequences from traffic scenes recorded by a stationary camera. In order to exploit the a priori knowledge about the shape and the physical motion of vehicles in traffic scenes, a parameterized vehicle model is used for an intraframe matching process and a recursive estimator based on a motion model is used for motion estimation. The initial guess about the position and orientation for the models are computed with the help of a clustering approach of moving image features. Shadow edges of the models are taken into account in the matching process. This enables tracking of vehicles under complex illumination conditions and within a small effective field of view. Results on real world traffic scenes are presented and open problems are outlined.

Knowledge-guided visual perception of 3-D human gait from a single image sequence

Abstract: A computer vision method is presented to determine the 3-D spatial locations of joints or feature points of human body from a film recording the human motion during walking. The proposed method first applies the geometric projection theory to obtain a set of feasible postures from a single image, then it makes use of the given dimensions of the human stick figure, physiological and motion-specific knowledge to constrain the feasible postures in both the single-frame analysis and the multi-frame analysis. Finally a unique gait interpretation is selected by an optimization algorithm. Computer simulations are used to illustrate the ideas presented. >

A face recognition method using higher order local autocorrelation and multivariate analysis

Abstract: Proposes a face recognition method which is characterized by structural simplicity, trainability and high speed. The method consists of two stages of feature extractions: first, higher order local autocorrelation features which are shift-invariant and additive are extracted from an input image; then those features are linearly combined on the basis of multivariate analysis methods so as to provide new effective features for face recognition in learning from examples. >

A compositer interface for arranging the components of special effects for a motion picture production

Abstract: A user interface is described for an image computing workstation for electronically arranging the components of a special effects job, such as image-compositing, from a plurality of image sequences obtained by the scanning of motion picture film The interface controls the ordering of a plurality of image sequences into a hierarchy of background and foreground image sequences, with each sequence being composed of frames whose appearance imitates the frames of a motion picture film The hierarchical image sequences are displayed adjacent to each other in a windowing environment so that the frames thereof visually align on a frame-to-frame basis The interface includes means for varying the hierarchical order and the adjacency of the image sequences so that different frames thereof are brought into visual alignment with each other, whereby the image sequences are correctly ordered as to hierarchy and adjacency for a special effect As an additional feature, the interface provides a flow diagram for specifying the type and order of special effect operations applied to each frame

Navigation system for a mobile robot

Abstract: A navigation system for a mobile autonomous robot that includes apparatus for creating and maintaining a map of an environment the mobile autonomous robot is to traverse including provision for storing in a map at an assigned location features representative of geometric beacons located in the environment. Because of the uncertainty in its sensor's operating conditions and changes in the environment, a credibility measure is associated with each map feature stored. This credibility measure is increased or decreased whenever the map feature assigned to a location matches or does not match, respectively, a geometric beacon corresponding to such location. Whenever a geometric beacon is observed for a location that does into match a previously stored map features, an appropriate map feature is added for such location.

Performance evaluation of scene registration and stereo matching for cartographic feature extraction

Abstract: Three major areas in the development of competent 3-D scene interpretation system are discussed. First, the importance of accurate automatic scene registration and the difficulty in automated extraction and matching of scene reference points are described. Second, the authors describe two stereo matching algorithms, S1, which is an area-based matcher previously used in the SPAM system, and S2, which is a feature-based matching algorithm based on hierarchical waveform matching. Third, the authors introduce several performance evaluation metrics that made it possible to measure the quality of the overall scene recovery, the building disparity estimate, and the quality and sharpness of the building delineations. Such manually generated scene reference models are critical for understanding strengths and weaknesses of various matching algorithms and in the incremental development of improvements to existing algorithms. Experiments were performed on difficult examples of aerial imagery. >

Self–organization with partial data

Abstract: We show how the kohonen self-organizing feature map model can be extended so that partial training data can be utilized. Given input stimuli in which values for some elements or features are absent, the match computation and the weight updates are performed in the input subspace defined by the available values. Three examples, including an application to student modelling for intelligent tutoring systems in which data is inherently incomplete, demonstrate the effectiveness of the extension.

Feature-based detection of the K-complex wave in the human electroencephalogram using neural networks

Abstract: The main difficulties in reliable automated detection of the K-complex wave in EEG are its close similarity to other waves and the lack of specific characterization criteria. The authors present a feature-based detection approach using neural networks that provides good agreement with visual K-complex recognition: a sensitivity of 90% is obtained with about 8% false positives. The respective contribution of the features and that of the neural network is demonstrated by comparing the results to those obtained with (i) raw EEG data presented to neural networks, and (ii) features presented to Fisher's linear discriminant. >

Model-based multi-sensor data fusion

Abstract: The authors describe an algorithm for implementing a multisensor system in a model-based environment with consideration of the constraints. Based on an environment model, geometric features and constraints are generated from a CAD model database. Sensor models are used to predict sensor response to certain features and to interpret raw sensor data. A constrained MMS (minimum mean squared) estimator is used to recursively predict, match, and update feature location. The effects of applying various constraints in estimation were shown by simulation system mounted on a robot arm for localization of known object features. >

Feature predictive vector quantization of multispectral images

Abstract: A compression method for multispectral data sets is proposed where a small subset of image bands is initially vector quantized. The remaining bands are predicted from the quantized images. Two different types of predictors are examined, an affine predictor and a new nonlinear predictor. The residual (error) images are encoded at a second stage based on the magnitude of the errors. This scheme simultaneously exploits both spatial and spectral correlation inherent in multispectral images. Simulation results on an image set from the Thematic Mapper with seven spectral bands provide a comparison of the affine predictor with the nonlinear predictor. It is shown that the nonlinear predictor provides significantly improved performance compared to the affine predictor. Image compression ratios between 15 and 25 are achieved with remarkably good image quality. >