Showing papers on "Feature (computer vision) published in 1996"

Toward optimal feature selection

Abstract: In this paper, we examine a method for feature subset selection based on Information Theory. Initially, a framework for defining the theoretically optimal, but computationally intractable, method for feature subset selection is presented. We show that our goal should be to eliminate a feature if it gives us little or no additional information beyond that subsumed by the remaining features. In particular, this will be the case for both irrelevant and redundant features. We then give an efficient algorithm for feature selection which computes an approximation to the optimal feature selection criterion. The conditions under which the approximate algorithm is successful are examined. Empirical results are given on a number of data sets, showing that the algorithm effectively handles datasets with a very large number of features.

A space-sweep approach to true multi-image matching

Abstract: The problem of determining feature correspondences across multiple views is considered. The term "true multi-image" matching is introduced to describe techniques that make full and efficient use of the geometric relationships between multiple images and the scene. A true multi-image technique must generalize to any number of images, be of linear algorithmic complexity in the number of images, and use all the images in an equal manner. A new space-sweep approach to true multi-image matching is presented that simultaneously determines 2D feature correspondences and the 3D positions of feature points in the scene. The method is illustrated on a seven-image matching example from the aerial image domain.

Feature-based methods for large scale dynamic programming

Abstract: We develop a methodological framework and present a few different ways in which dynamic programming and compact representations can be combined to solve large scale stochastic control problems. In particular, we develop algorithms that employ two types of feature-based compact representations; that is, representations that involve feature extraction and a relatively simple approximation architecture. We prove the convergence of these algorithms and provide bounds on the approximation error. As an example, one of these algorithms is used to generate a strategy for the game of Tetris. Furthermore, we provide a counter-example illustrating the difficulties of integrating compact representations with dynamic programming, which exemplifies the shortcomings of certain simple approaches.

Conformal curvature flows: From phase transitions to active vision

Abstract: In this paper, we analyze geometric active contour models from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. This leads to a novel edge-detection paradigm in which the feature of interest may be considered to lie at the bottom of a potential well. Thus an edge-seeking curve is attracted very naturally and efficiently to the desired feature. Comparison with the Allen-Cahn model clarifies some of the choices made in these models, and suggests inhomogeneous models which may in return be useful in phase transitions. We also consider some 3-dimensional active surface models based on these ideas. The justification of this model rests on the careful study of the viscosity solutions of evolution equations derived from a level-set approach.

Automated infusion system with dose rate calculator

Abstract: This invention is a medication infusion system (10) having an integrated dose rate calculation feature for selectively assigning values to a plurality of infusion parameters and automatically calculating an infusion rate from the selected parameters.

Performing optical proximity correction with the aid of design rule checkers

Abstract: A method is disclosed for identifying regions of an integrated circuit layout design where optical proximity correction will be most useful and then performing optical proximity correction on those regions only. More specifically, the method includes the following steps: (a) analyzing an integrated circuit layout design with a design rule checker to locate features of the integrated circuit layout design meeting predefined criteria; and (b) performing optical proximity correction on the features meeting the criteria in order to generate a reticle design. The criteria employed by the design rule checker to select features include outside corners on patterns, inside corners on features, feature size, feature shape, and feature angles.

Image representations for visual learning.

Abstract: Computer vision researchers are developing new approaches to object recognition and detection that are based almost directly on images and avoid the use of intermediate three-dimensional models. Many of these techniques depend on a representation of images that induce a linear vector space structure and in principle requires dense feature correspondence. This image representation allows the use of learning techniques for the analysis of images (for computer vision) as well as for the synthesis of images (for computer graphics).

Texture features and learning similarity

Abstract: This paper addresses two important issues related to texture pattern retrieval: feature extraction and similarity search. A Gabor feature representation for textured images is proposed, and its performance in pattern retrieval is evaluated on a large texture image database. These features compare favorably with other existing texture representations. A simple hybrid neural network algorithm is used to learn the similarity by simple clustering in the texture feature space. With learning similarity the performance of similar pattern retrieval improves significantly. An important aspect of this work is its application to real image data. Texture feature extraction with similarity learning is used to search through large aerial photographs. Feature clustering enables efficient search of the database as our experimental results indicate.

Learning trees and rules with set-valued features

Abstract: In most learning systems examples are represented as fixed-length "feature vectors", the components of which are either real numbers or nominal values. We propose an extension of the feature-vector representation that allows the value of a feature to be a set of strings; for instance, to represent a small white and black dog with the nominal features size and species and the set-valued feature color, one might use a feature vector with size=small, species=canis-familiaris and color-{white, black}. Since we make no assumptions about the number of possible set elements, this extension of the traditional feature-vector representation is closely connected to Blum's "infinite attribute" representation. We argue that many decision tree and rule learning algorithms can be easily extended to set-valued features. We also show by example that many real-world learning problems can be efficiently and naturally represented with set-valued features; in particular, text categorization problems and problems that arise in propositionalizing first-order representations lend themselves to set-valued features.

The Effect of New Product Features on Brand Choice

Abstract: Companies often introduce new product features to differentiate their brands and gain a competitive advantage. The authors investigate factors that moderate the impact of a new feature on brand cho...

Real-estate method and apparatus for searching for homes in a search pool for exact and close matches according to primary and non-primary selection criteria

Abstract: A method and apparatus is provided for a search system based in software running on a personal computer. The personal computer is housed in a kiosk having a touch monitor and a printer. With the search system, selection features are selected and a search based upon these search features is performed. Each item in a database is examined to determine if an item has a given search feature. These search features are categorized into primary and non-primary search features. Items neither satisfying nor closely satisfying a given primary search feature are eliminated from the search. In contrast, items not satisfying a given non-primary feature may remain in a search pool. For both primary and non-primary features, if an item in a database is an exact match to a given search feature, then that item is assigned full points. If an item closely satisfies the search feature then that item is assigned full or partial points. After completion of comparing each primary and non-primary search features with each item in the search pool, predetermined number of items remaining in the search pool with the highest total points are displayed to the user of the search system.

PicHunter: Bayesian relevance feedback for image retrieval

Abstract: This paper describes PicHunter, an image retrieval system that implements a novel approach to relevance feedback, such that the entire history of user selections contributes to the system's estimate of the user's goal image. To accomplish this, PicHunter uses Bayesian learning based on a probabilistic model of a user's behavior. The predictions of this model are combined with the selections made during a search to estimate the probability associated with each image. These probabilities are then used to select images for display. Details of our model of a user's behavior were tuned using an off-line leaning algorithm. For clarity, our studies were done with the simplest possible user interface but the algorithm can easily be incorporated into systems which support complex queries, including most previously proposed systems. However, even with this constraint and simple image features, PicHunter is able to locate randomly selected targets in a database of 4522 images after displaying an average of only 55 groups of 4 images which is over 10 times better than chance. We therefore expect that the performance of current image database retrieval systems can be improved by incorporation of the techniques described here.

Automated binary texture feature sets for image retrieval

Abstract: Digital image and video libraries require new algorithms for the automated extraction and indexing of salient image features. Texture features provide one important cue for the visual perception and discrimination of image content. We propose a new approach for automated content extraction that allows for efficient database searching using texture features. The algorithm automatically extracts texture regions from image spatial-frequency data which are represented by binary texture feature vectors. We demonstrate that the binary texture features provide excellent performance in image query response time while providing highly effective texture discriminability, accuracy in spatial localization and capability for extraction from compressed data representations. We present the binary texture feature extraction and indexing technique and examine searching by texture on a database of 500 images.

An adaptive density-weighted contrast enhancement filter for mammographic breast mass detection

Abstract: Presents a novel approach for segmentation of suspicious mass regions in digitized mammograms using a new adaptive density-weighted contrast enhancement (DWCE) filter in conjunction with Laplacian-Gaussian (LG) edge detection. The DWCE enhances structures within the digitized mammogram so that a simple edge detection algorithm can be used to define the boundaries of the objects. Once the object boundaries are known, morphological features are extracted and used by a classification algorithm to differentiate regions within the image. This paper introduces the DWCE algorithm and presents results of a preliminary study based on 25 digitized mammograms with biopsy proven masses. It also compares morphological feature classification based on sequential thresholding, linear discriminant analysis, and neural network classifiers for reduction of false-positive detections.

Quantitative measures of change based on feature organization: eigenvalues and eigenvectors

Abstract: We propose four measures of image organizational change which can be used to monitor construction activity The measures are based on the thesis that the progress of construction will see a change in the individual image feature attributes as well as an evolution in the relationships among these features This change in the relationship is captured by the eigenvalues and eigenvectors of the relation graph embodying the organization among the image features We demonstrate the ability of the measures to differentiate between no development, the onset of construction, and full development, on the available real test image set

High-speed visual estimation using preattentive processing

Abstract: A new method is presented for performing rapid and accurate numerical estimation. The method is derived from an area of human cognitive psychology called preattentive processing. Preattentive processing refers to an initial organization of the visual field based on cognitive operations believed to be rapid, automatic, and spatially parallel. Examples of visual features that can be detected in this way include hue, intensity, orientation, size, and motion. We beleive that studies from preattentive vision should be used to assist in the design of visualization tools, especially those for which high-speed target detection, boundary identification, and region detection are important. In our present study, we investigated two known preattentive features (hue and orientation) in the context of a new task (numerical estimation) in order to see whether preattentive estimation was possible. Our experiments tested displays that were designed to visualize data from salmon migration simulations. The results showed that rapid and accurate estimation was indeed possible using either hue or orientation. Furthermore, random variation in one of these features resulted in no interference when subjects estimated the percentage of the other. To test the generality of our results, we varied two important display parameters—display duration and feature difference—and found boundary conditions for each. Implications of our results for application to real-world data and tasks are discussed.

Driver control interface system

Abstract: A driver control interface controls the values of a plurality of features in a vehicle and displays information from the vehicle to the driver. A plurality of feature group switches are located on the steering wheel of the vehicle. Each of the vehicle features is associated with a feature group. Each of the feature group switches activates an associated feature group. A plurality of selection switches is also preferably located on the steering wheel for adjusting the values of the features associated with the activated feature group. An eyes-front display indicates the current value of a feature in an activated feature group.

Restrictive package for expandable or shape memory medical devices and method of preventing premature change of same

Abstract: A package for a medical device made of an expandable or shape memory material is disclosed. The package is a sheath which surrounds and contains the medical device, and is of sufficient strength that upon exposure to conditions which would cause the medical device to expand or change its shape it is restrained from such shape change or expansion. The package has a tear-away or peel-away feature which provides easy access to the medical device when needed.

The relationship between the locations of spatial features and those of fixations made during visual examination of briefly presented images

Abstract: The locations of features such as extremes of contrast or luminance, high spatial frequency content and edge density in a set of images have been determined, and the locations of fixations made by a group of eighteen human observers who examined the images during brief (3 s) presentations were also measured. The similarity between the locations of the eye movements and those of each stimulus feature was determined by means of a least squares index IS. For averages taken over data for all observers, the similarity determined in this way is much lower than values for pairs of fixation locations made by different observers. It is concluded that the pattern of fixations made to a given image which is highly conserved between different observers, cannot be associated with any one of the local features examined by us. It is shown further that the distribution of fixation locations over the images is non-uniform, with a marked bias to central areas, whereas the image features are more uniformly distributed. Weighting the distributions of feature locations to take account of the non-uniform distribution of fixations produces much higher IS values, but the dominant contribution to these high values is the weighting function itself. Only in the case of edge density is there significant similarity between the locations of eye movements and those of the image features.

Apparatus for processing an image of a face

Abstract: The invention provides an apparatus for processing an image of a face, capable of quickly and correctly detecting eyes not only under artificial illumination but also under sunlight regardless of the direction or altitude of the sun and regardless of circumstance conditions such as sunlight filtering down through trees, and still regardless of the variation in the face shape from person to person. An image of the face of a car driver is taken by a camera, and input to image signal input means. Gray level conversion means performs signal level conversion of picture elements of the face image received via the image signal input means in such a manner as to extract black-level areas smaller at least in the dimension along one image axis parallel or nearly parallel to the vertical direction of a face than a predefined length corresponding to the up-to-down width of an eye, thereby extracting black level areas having a size nearly equal to or less than the up-to-down width of the eye and thus extracting characteristic feature areas such as eyes, eyebrows, nares, and line between lips from the input face image. Variable binarization means converts the characteristic feature image into a binary image. Eye searching area setting means sets eye searching areas in the binary image. Candidate area setting means sets eye candidate areas in the eye searching areas. Eye area detection means detects eye areas from the eye candidate areas.

Face recognition using DCT-based feature vectors

Abstract: Face recognition has many applications ranging from security access to video indexing by content. We describe an automatic face recognition system which is VQ-based and examine the effects of feature selection, feature dimensionality and codebook size on recognition performance in the VQ framework. In particular, we examine DCT-based feature vectors in such a system. DCT-based feature vectors have the additional appeal that the recognition can be performed directly on the bitstream of compressed images which are DCT-based. The system described consists of three parts: a preprocessing step to segment the face, the feature selection process and the classification. Recognition rates for a database of 500 images shows promising results.

Fidelity enhancement of lithographic and reactive-ion-etched images by optical proximity correction

Abstract: A method for performing optical proximity correction is disclosed that not only limits the optical proximity correction to electrically relevant structures, but also improves the accuracy of the corrections by processing individual feature edges, and minimizes the mask manufacturing impacts by avoiding the introduction of jogs into the design. Critical edge regions of the relevant electrical structures are analyzed, sorted and manipulated to receive optical proximity corrections.

A camera-based system for tracking people in real time

Abstract: This paper describes a system for real-time tracking of people in video sequences. The input to the system is live or recorded video data acquired by a stationary camera in an environment where the primary moving objects are people. The output consists of trajectories which give the spatio-temporal coordinates of individual persons as they move in the environment. The system uses a new model-based approach to object tracking. It identifies feature points in each video frame, matches feature points across frames to produce feature "paths", then groups short-lived and partially overlapping feature paths into longer living trajectories representing motion of individual persons. The path grouping is based on a novel model-based algorithm for motion clustering. The system runs on an SGI Indy workstation at an average rate of 14 frames a second. The system has numerous applications since various statistics and indicators of human activity can be derived from the motion trajectories. Examples of these indicators described in the paper include people counts, presence and time spent in a region, traffic density maps and directional traffic statistics.

Epipolar line estimation and rectification for stereo image pairs

Abstract: The assumption that epipolar lines are parallel to image scan lines is made in many algorithms for stereo analysis. If valid, it enables the search for corresponding image features to be confined to one dimension and, hence, simplified. An algorithm that generates a vertically aligned stereo pair by warped resampling is described. The method uses grey scale image matching between the components of the stereo pair but confined to feature points.