Showing papers on "Feature (computer vision) published in 1985"

Preattentive processing in vision

Abstract: Visual analysis appears to be functionally divided between an early preattentive level of processing at which simple features are coded spatially in parallel and a later stage at which focused attention is required to conjoin the separate features into coherent objects. Evidence supporting this dichotomy comes from behavioral studies of visual search, from differences in the ease of texture segregation, from reports of illusory conjunctions when attention is overloaded, from subjects' ability to identify simple features correctly even when they mislocate them, and from the substantial benefit of pre-cuing the location of a relevant item when the task requires that features be conjoined but not when simple features are sufficient. Some further studies of search have revealed a striking asymmetry between several pairs of stimuli which differ in the presence or absence of a single part or property. The asymmetry depends solely on which of the pair is allocated the role of target and which is replicated to form the background items. It suggests that search for the presence of a visual primitive is automatic and parallel, whereas search for the absence of the same feature is serial and requires focused attention. The search asymmetry can be used as an additional diagnostic to help define the functional features extracted by the visual system.

Computational Experiments with a Feature Based Stereo Algorithm

Abstract: Computational models of the human stereo system can provide insight into general information processing constraints that apply to any stereo system, either artificial or biological. In 1977 Marr and Poggio proposed one such computational model, which was characterized as matching certain feature points in difference-of-Gaussian filtered images and using the information obtained by matching coarser resolution representations to restrict the search space for matching finer resolution representations. An implementation of the algorithm and its testing on a range of images was reported in 1980. Since then a number of psychophysical experiments have suggested possible refinements to the model and modifications to the algorithm. As well, recent computational experiments applying the algorithm to a variety of natural images, especially aerial photographs, have led to a number of modifications. In this paper, we present a version of the Marr-Poggio-Grimson algorithm that embodies these modifications, and we illustrate its performance on a series of natural images.

Classification of textures using Gaussian Markov random fields

Abstract: The problem of texture classification arises in several disciplines such as remote sensing, computer vision, and image analysis. In this paper we present two feature extraction methods for the classification of textures using two-dimensional (2-D) Markov random field (MRF) models. It is assumed that the given M × M texture is generated by a Gaussian MRF model. In the first method, the least square (LS) estimates of model parameters are used as features. In the second method, using the notion of sufficient statistics, it is shown that the sample correlations over a symmetric window including the origin are optimal features for classification. Simple minimum distance classifiers using these two feature sets yield good classification accuracies for a seven class problem.

Elite: A Digital Dedicated Hardware System for Movement Analysis Via Real-Time TV Signal Processing

Abstract: The system illustrated in this paper has been designed and developed particularly for automatic and reliable analysis of body movement in various conditions and environments. It is based on real-time processing of the TV images to recognize multiple passive markers and compute their coordinates. This performance is achieved by using a special algorithm allowing the recognition of markers only if their shape matches a predetermined "mask." The main feature of the system is a two-level processing architecture, the first of which includes a dedicated peripheral fast processor for shape recognition (FPSR), designed and implemented by using fast VLSI chips. The second level consists of a general purpose computer and provides the overall system with high flexibility. The main characteristics are: no restriction on the number of markers, resolution of one part in 2500, and a 50 Hz sampling rate independent of the number of markers detected. The prototype has been fully developed, and preliminary results obtained from the analysis of several movements are illustrated.

Determination of 3D human body postures from a single view

Abstract: In this paper a method is proposed to recover and interpret the 3D body structures of a person from a single view, provided that (1) at least six feature points on the head and a set of body joints are available on the image plane, and (2) the geometry of head and lengths of body segments formed by joints are known. First of all, the feature points on the head in the head-centered coordinate system and their image projections are used to determine a transformation matrix. Then, the camera position and orientations are extracted from the matrix. Finally, the 3D coordinates of the head points expressed in the camera-centered coordinate system are obtained. Starting from the coordinates of the neck, which is a head feature point, the 3D coordinates of other joints one-by-one are determined under the assumption of the fixed lengths of the body segments. A binary interpretation tree is used to represent the 2n − 1 possible body structures, if a human body has n joints. To determine the final feasible body structures, physical and motion constraints are used to prune the interpretation tree. Formulas and rules required for the tree pruning are formulated. Experiments are used to illustrate the pruning powers of these constraints. In the two cases of input data chosen, a unique or nearly unique solution of the body structure is obtained.

Model-Based Image Matching Using Location

Abstract: This work deals with the computer vision problem of recognizing and locating rigid shapes in the plane which have been subjected to unknown rotation, scaling, and noise. The recognition task includes both locating the overall pattern and identifying each of its features. Location is achieved by finding a geometric registration function that does a good job of superimposing the instance and the model. Identifying the features requires matching each model feature with the corresponding instance feature.A pruned tree-search algorithm is developed which makes effective use of the Soviet ellipsoid algorithm for feasibility of linear constraints. An interesting blend of theoretical analysis and practical implementation shows that the resulting algorithm has an expected runtime that is theoretically asymptotically quadratic in the number of feature points, but practically linear in n for patterns with fewer than 100 points.Contents: Introduction; Task Abstraction; Prior Approaches; A Linear Programming Approach; Geometry of Registrations and Ellipsoids; Worst-Case Number of Feasible Matchings; Random Patterns; Expected Cost of Feasibility Testing; Expected Size of Search Tree; Monte Carlo Trials; Conclusions.Henry S. Baird received his doctorate from Princeton University. He is currently a technical staff member et AT & T Bell Laboratories. "Model-Based Image Matching Using Location "is a 1984 ACM Distinguished Dissertation.

Applications of Tensor Theory to Object Recognition and Orientation Determination

Abstract: A method is developed by which images resulting from orthogonal projection of rigid planar-patch objects arbitrarily oriented in three-dimensional (3-D) space may be used to form systems of linear equations which are solved for the affine transform relating the images. The technique is applicable to complete images and to unlabeled feature sets derived from images, and with small modification may be used to transform images of unknown objects such that they represent images of those objects from a known orientation, for use in object identification. No knowledge of point correspondence between images is required. Theoretical development of the method and experimental results are presented. The method is shown to be computationally efficient, requiring O(N) multiplications and additions where, depending on the computation algorithm, N may equal the number of object or edge picture elements.

Electronic facial tracking and detection system and method and apparatus for automated speech recognition

Abstract: The apparatus includes circuitry for obtaining a video image of an individual's face, circuitry for electronically locating and tracking a first feature, such as the nostrils, of the facial image for use as reference coordinates and circuitry responsive to the reference coordinates for locating and tracking a second facial feature, such as the mouth, of the facial image with respect to the first feature. By tracking the location of the nostrils, the apparatus can follow the movement of the mouth, and thereby automatically recognize speech. In a preferred embodiment, the video image is grayscale encoded and the raster lines are smoothed to eliminate noise. The transitions between gray levels of the smoothed image are encoded and the resulting transition code is used to form a contour map of the image from which region parameters are computed which can be compared against stored speech templates to recognize speech. In the preferred embodiment, acoustic speech recognition is combined with visual speech recognition to improve accuracy.

Eye Spacing Measurement for Facial Recognition

Abstract: Few approaches to automated facial recognition have employed geometric measurement of characteristic features of a human face. Eye spacing measurement has been identified as an important step in achieving this goal. Measurement of spacing has been made by application of the Hough transform technique to detect the instance of a circular shape and of an ellipsoidal shape which approximate the perimeter of the iris and both the perimeter of the sclera and the shape of the region below the eyebrows respectively. Both gradient magnitude and gradient direction were used to handle the noise contaminating the feature space. Results of this application indicate that measurement of the spacing by detection of the iris is the most accurate of these three methods with measurement by detection of the position of the eyebrows the least accurate. However, measurement by detection of the eyebrows' position is the least constrained method. Application of these techniques has led to measurement of a characteristic feature of the human face with sufficient accuracy to merit later inclusion in a full package for automated facial recognition.

Experiments in Intensity Guided Range Sensing Recognition of Three-Dimensional Objects

Abstract: With the advent of devices that can directly sense and determine the coordinates of points in space, the goal of constructing and recognizing descriptors of three-dimensional (3-D) objects is attracting the attention of many researchers in the image processing community. Unfortunately, the time required to fully sense a range image is large relative to the time required to sense an intensity image. Conversely, a single intensity image lacks the depth information required to construct 3-D object descriptors. This paper presents a method of combining the two sensory sources, intensity and range, such that the time required for range sensing is considerably reduced. The approach is to extract potential points of interest from the intensity image and then selectively sense range at these feature points. After the range information is known at these points, a graph structure representing the object in the scene is constructed. This structure is compared to the stored graph models using an algorithm for partial matching. The results of applying the method to both synthetic data and real intensity/range images are presented.

Pica as a feature of autism.

Abstract: Pica—the ingestion of non-food substances—is found in many animal species, where it is usually attributed to dietary deficiencies (e.g. osteophagia (Theiler eta!, 1924) and salt licking (Bott eta!, 1964) in areas of phosphorus and sodium depletion) or physical (especially gastrointestinal) (Mitchell et a!, 1976) illness (e.g. cats and dogs will instinctively eat grass). Experiments with animals (Snowdon, 1977) also suggest a nutritional basis for pica. However, geophagia has been found as a generalised stress in response in rats, (Burchfield, eta! 1977), and cattle whose phosphorus deficiency has been cured may continue to eat bones (Green, 1925). In the human literature there has also been an emphasis on mineral (e.g. iron, Lanzkowsky, 1959; Jolly, 1963; Gleditsch, 1959; Catzel, 1963; Mc Donald & Marshall 1964; Crosby, 1976; Perry, 1977; zinc, Cavdar et a!, 1974; Hambidge, 1973; calcium, Snowdon & Sanderson 1974; deficiency, the majority of reports being of children, pregnant women, (Vermeer, 1966) and socially deprived groups, who might all be expected to be susceptible to such deficiencies. Ingestion of starch (Roselle, 1970) and ice (pagophagia) (Reynolds, et al, 1968) have been found in association with iron deficiency. However, it has been shown (Bicknell, 1975) that iron-deficiency anaemia is coincidental rather than causal in the condition, (social deprivation was also found to be correlated, but not causative). Like wise, children whose lead-poisoning has been cured, and pregnant women who have delivered, (Lourie & Layman 1963) may continue to indulge in pica. No demonstrable nutritional deficiency occurs in many instances of pica (Gutelius eta!, 1962). Pica as a manifestation of severe psychopatho logy was clearly described by the early psychiatric pioneers (Kraepelin, 1913; Krafft-Ebing, 1905). Thus Kraepelin (1913) considered the behaviour a †̃¿ vegetative' sign of psychosis. Indeed, the preferred definition of pica implies pathology: †̃¿ the perverted craving of substances unfit for food' (Hochstein, 1968). But pica has received little attention in recent psychiatric literature. Where it has, (Arieti, 1974) it is argued that pica is seen only in the †̃¿ terminalstage of long-standing schizophrenia, where the behaviour represents a compulsory undifferentiated oral response to external stimuli'. It is of interest that an African tribal group has a category for madness designated by earth eating (Beiser et a!, 1972). Psychotic pica has been reported more frequently in the non-psychiatric literature, and with preferential attention to phys ical complications. Pica in relation to autism has been described, (Cohen et a!, 1976) but does not feature in the standard autism literature. Aim: The aim of the present study was to determine the frequency of pica in subjects with autistic tendencies.

Substantial constructive induction using layered information compression: tractable feature formation in search

Abstract: This paper addresses a problem of induction (generalization learning) which is more difficult than any comparable work in AI. The subject of the present research is a hard problem of new terms, a task of realistic constructive induction. While the approach is quite general, the system is analyzed and tested in an environment of heuristic search where noise management and incremental learning are necessary. Here constructive induction becomes feature formation from data represented in elementary form. A high-level attribute or feature such as "piece advantage" in checkers is much more abstract than an elementary descriptor or primitive such as contents of a checkerboard square. Features have often been used in evaluation functions; primitives are usually too detailed for this. To create abstract features from primitives (i.e. to restructure data descriptions), a new form of clustering is used which involves layering of knowledge and invariance of utility relationships related to data primitives and task goals. The scheme, which is both model- and data-driven, requires little background, domain-specific knowledge, but rather constructs it. The method achieves considerable generality with superior noise management and low computational complexity. Although the domains addressed are difficult, initial experimental results are encouraging.

The Recovery of Three-Dimensional Structure from Image Curves

Abstract: A class of inferences is described which allows the recovery of three-dimensional structures from the two-dimensional curves in an image. Unlike most previous methods, these inferences do not require restrictive assumptions or prior knowledge regarding the scene. They are based on the assumption that the camera viewpoint and the positions of the illumination sources are independent of the objects in the scene. From these independence assumptions, it can be shown that many potential interpretations of image curves are highly improbable. By eliminating these improbable interpretations it is possible to segment the image into sets of related image features and derive many three-space relations.

Multi-function rotary dial system including timer setting feature

Abstract: In a multi-function video tape recorder system, a manually operable rotary dial can be used in place of a large number of dedicated manual switches, and so forth to make selections from multiple-choice lists and to assign numerical values for timing, and so forth. The rotary dial is journalled on a fold-down section of the video tape recorder's front console and its manually-actuated rotation is monitored by optical sensors. A microprocessor receives the output of the sensors and so can derive the angular position and speed and direction of rotation of the rotary dial, which may all serve as input parameters. In addition, a ring may be included in the rotary dial assembly, the ring being pivotably slightly relative to the rotary dial itself to provide an addition dimension of information input. The rotary dial can be used to input date and time information for both clock setting and timer setting operations, to select a television channel for recording or direct reception, to select the speed and mode of video playback and/or to control the rate and direction of frame advance.

Lipoid proteinosis presenting with neuropsychiatric manifestations.

Abstract: Two patients with lipoid proteinosis are reported in whom paranoid symptoms were the presenting feature. Both had a long standing impairment of memory and bilateral medial temporal lobe calcification demonstrated by CT scan. Possible associations between the anatomical site of these lesions and the neuropsychiatric manifestations are discussed.

Rotation-invariant pattern recognition using optimum feature extraction

Abstract: In this paper we consider the problem of detecting a target regardless of its orientation when it is known that the target must be from one of two classes. We assume significant random intraclass variability, a complication which requires techniques from statistical pattern recognition for amelioration. The Foley-Sammon transformation for selecting optimum features from random training samples is used to solve the problem.

Modal analysis method for optical fibers with symmetrically distributed multiple cores

Abstract: The purpose of this paper is to present an effective modal analysis method for a class of recently developed optical fibers with multiple cores. The main feature of the method is to combine the point-matching procedure with group theory to solve such complicated boundary value problems. The results of the numerical computations are compared with those of microwave simulation experiments.

Signal processing disparity resolution

Abstract: A process for signal matching. The process is general and can be applied to matching signals of arbitrary dimension. To implement the process, a suitable discretized description of the two signals to be matched is defined. Such descriptions can be the local signal extrema or any other qualitative signal significant points of interest or features. Allowable feature matches and values for matches are defined, and determined for all potential matches. Matches are confined to the features within defined matching windows and are mapped for each significant point. Within a defined similarity disparity window, a neighborhood of potentially interacting matches are evaluated. Matches within a neighborhood contribute to the decision about the appropriate match for each significant point to determine a composite similarity weighted best value match for each point. Mapping is piecewise continuous. The two signals are matched with disparities therebetween resolved and removed responsive to the best match values. Following the coherence process, the overall process of the present invention provides a superposition of several such piecewise transformations. In an illustrated application domain, a stereo correspondence technique provides for matching of figurally similar three dimensional images, according to a simple no iterative, parallel and local process that can successfully detect disparities of opaque as well as transparent surfaces.

Device for measuring distance, particularly for motor vehicles

Abstract: In this device, a number of transducers for sending out and receiving ultrasonic signals are activated deferred and the corresponding echo signals are then evaluated. The essential feature of the present invention is the manner in which these transducers are controlled and the echo signals are evaluated in such a manner that the driver is provided with an optimum warning function.

Computing Visible-Surface Representations

Abstract: : The computational framework offered in this paper addresses, in a unified way, certain visual information processing tasks involved in the representation of visible surfaces. Particular emphasis is placed on utilizing highly parallel, cooperative processing to integrate surface shape information over multiple visual sources, to fuse it across a multiplicity of spatial resolutions, and to maintain the global consistency of the resulting distributed shape representations. The issues are first investigated in terms of a surface reconstruction model rooted in mathematical physics. This formal analysis is augmented by an empirical study of the resulting algorithms, which feature multiresolution iterative processing within hierarchical surface shape representations. The approach is guided by current knowledge of how humans perceive visible surfaces, while applications in machine vision provide a testbed for the algorithms. Keywords: vision; finite elemeent analysis; discontinuities; variational principles; splines.

Feature extraction technique for use in a pattern recognition system

Abstract: A method is provided for forming feature vectors representing the pixels contained in a pattern desired to be recognized, and reference patterns. One part of the feature vector is representative of the pixels contained in the pattern itself, while not requiring a very large feature vector which exactly defines each pixel of the pattern. One embodiment of this invention provides that another part of the feature vector, consisting of one or more bytes of the feature vector, defines the aspect ratio of the pattern. In one embodiment, each byte of the feature vector representing the pixels contained in the character represents the relative ratio of black pixels to total pixels in a specific area of the character; other functions relating input matrix and output feature vector information can be used. In one embodiment of this invention, those areas of the character which are defined by the feature vector together cover the entire character, providing a feature vector describing what might loosely be thought as a "blurred" version of the pattern.

Object recognition using multiple views

Abstract: A new approach to model based object recognition employing multiple views is described. The emphasis is given on the determination of camera viewpoints for succesive views looking for distinguishing features of objects. The distance and direction of the camera are determined separately. The distance is determined by the size of the object and the feature, while the direction is determined by the shape of the feature and the presence of the occluding objects.

Video recognition system

Abstract: An image recognition system uses feature or attribute matching for fast coarse selection of a group of reference images which closely resemble an unknown image and thereafter selects the best reference image match from that group using 2-dimensional intensity correlation or template matching. The system provides highly accurate image recognition without resorting to time consuming exhaustive search by template matching.

Three new cases of oculodentodigital (ODD) syndrome: development of the facial phenotype.

Abstract: Three new cases of oculodentodigital (ODD) syndrome are reported. The clinical features are discussed and the development of the characteristic facial appearance is illustrated. Conductive deafness is reported in one of our cases and has been reported in six previous cases. It is suggested that it is a feature of the syndrome which is amenable to treatment.

Phoneme Feature Perception in Noise by Normal-Hearing and Hearing-Impaired Subjects

Abstract: The purpose of this investigation was to determine whether normal-hearing and hearing-impaired listeners perceive phoneme features differently in noise and to determine whether phoneme perception c...

Auxiliary dumping apparatus for vehicles

Abstract: A dumper of the type that attaches to the bed of a pick-up, trailer or the like, and adds the dumping feature to the fixed-bed locomotive, and comprises a bin riding over a set of rollers secured to a framework affixed to the bottom of the pick-up bed.