Showing papers on "Orientation (computer vision) published in 1990"

Multichannel texture analysis using localized spatial filters

Abstract: A computational approach for analyzing visible textures is described. Textures are modeled as irradiance patterns containing a limited range of spatial frequencies, where mutually distinct textures differ significantly in their dominant characterizing frequencies. By encoding images into multiple narrow spatial frequency and orientation channels, the slowly varying channel envelopes (amplitude and phase) are used to segregate textural regions of different spatial frequency, orientation, or phase characteristics. Thus, an interpretation of image texture as a region code, or carrier of region information, is emphasized. The channel filters used, known as the two-dimensional Gabor functions, are useful for these purposes in several senses: they have tunable orientation and radial frequency bandwidths and tunable center frequencies, and they optimally achieve joint resolution in space and in spatial frequency. By comparing the channel amplitude responses, one can detect boundaries between textures. Locating large variations in the channel phase responses allows discontinuities in the texture phase to be detected. Examples are given of both types of texture processing using a variety of real and synthetic textures. >

Paint by numbers: abstract image representations

Abstract: Computer graphics research has concentrated on creating photo-realistic images of synthetic objects. These images communicate surface shading and curvature, as well as the depth relationships of objects in a scene. These renderings are traditionally represented by a rectangular array of pixels that tile the image plane.As an alternative to photo-realism, it is possible to create abstract images using an ordered collection of brush strokes. These abstract images filter and refine visual information before it is presented to the viewer. By controlling the color, shape, size, and orientation of individual brush strokes, impressionistic paintings of computer generated or photographic images can easily be created.

Error modeling in stereo navigation

Abstract: In stereo navigation, a mobile robot estimates its position by tracking landmarks with on-board cameras. Previous systems for stereo navigation have suffered from poor accuracy, in part because they relied on scalar models of measurement error in triangulation. Using three-dimensional (3D) Gaussian distributions to model triangulation error is shown to lead to much better performance. How to compute the error model from image correspondences, estimate robot motion between frames, and update the global positions of the robot and the landmarks over time are discussed. Simulations show that, compared to scalar error models, the 3D Gaussian reduces the variance in robot position estimates and better distinguishes rotational from translational motion. A short indoor run with real images supported these conclusions and computed the final robot position to within two percent of distance and one degree of orientation. These results illustrate the importance of error modeling in stereo vision for this and other applications.

Differentiating sonar reflections from corners and planes by employing an intelligent sensor

Abstract: A multitransducer, pulse/echo-ranging system is described that differentiates corner and plane reflectors by exploiting the physical properties of sound propagation. The amplitudes and ranges of reflected signals for the different transmitter and receiver pairs are processed to determine whether the reflecting object is a plane or a right-angle corner. In addition, the angle of inclination of the reflector with respect to the transducer orientation can be measured. Reflected signal amplitude and range values, as functions of inclination angle, provide the motivation for the differentiation algorithm. A system using two Polaroid transducers is described that correctly discriminates between corners and planes for inclination angles within +or-10 degrees of the transducer orientation. The two-transducer system is extended to a multitransducer array, allowing the system to operate over an extended range. An analysis comparing processing effort to estimation accuracy is performed. >

A document skew detection method using run-length encoding and the Hough transform

Abstract: As part of the development of a document image analysis system, a method, based on the Hough transform, was devised for the detection of document skew and interline spacing-necessary parameters for the automatic segmentation of text from graphics. Because the Hough transform is computationally expensive, the amount of data within a document image is reduced through the computation of its horizontal and vertical black runlengths. Histograms of these runlengths are used to determine whether the document is in portrait or landscape orientation. A gray scale burst image is created from the black runlengths that are perpendicular to the text lines by placing the length of the run in the run's bottom-most pixel. By creating a burst image from the original document image, the processing time of the Hough transform can be reduced by a factor of as much as 7.4 for documents with gray-scale images. Because only small runlengths are input to the Hough transform and because the accumulator array is incremented by the runlength associated with a pixel rather than by a factor of 1, the negative effects of noise, black margins, and figures are avoided. Consequently, interline spacing can be determined more accurately. >

Detecting and localizing edges composed of steps, peaks and roofs

Abstract: The projection of depth or orientation discontinuities in a physical scene results in image intensity edges which are not ideal step edges but are more typically a combination of step, peak and roof profiles. Most edge detection schemes ignore the composite nature of these edges, resulting in systematic errors in detection and localization. The problem of detecting and localizing these edges is addressed, along with the problem of false responses in smoothly shaded regions with constant gradient of the image brightness. A class of nonlinear filters, known as quadratic filters, is appropriate for this task, while linear filters are not. Performance criteria are derived for characterizing the SNR, localization and multiple responses of these filters in a manner analogous to Canny's criteria for linear filters. A two-dimensional version of the approach is developed which has the property of being able to represent multiple edges at the same location and determine the orientation of each to any desired precision. This permits junctions to be localized without rounding. Experimental results are presented. >

A technique for object orientation detection using a feed-forward neural network

Abstract: The present invention relates to a technique in the form of an exemplary computer vision system for detecting the orientation of text or features on an object of manufacture. In the present system, an image of the features or text (10) is used to extract lines using horizontal bitmap sums, and then individual symbols (12) using vertical bitmap sums while using thresholds with each of the sums. The separated symbols are then appropriately trimmed and scaled to provide individual normalized symbols (14). A Decision Module (15) comprising a Feed-Forward Neural network (21) and a sequential decision arrangement (23) determines the "up", "down" or "indeterminate" orientation of the text after a variable number of symbols have been processed. The system can then compare (24) the determined orientation with a database to further determine if the object is in the "right-side up" "upside-down" or "indeterminate" orientation.

Three-dimensional alignment of functional and morphological tomograms.

Abstract: A method has been developed to create corresponding brain slices from morphological [CT, magnetic resonance (MR)] and functional [positron emission tomography (PET), single photon emission computed tomography] tomographic studies in individual patients It does not require special headholders or definition of specific landmarks and is fully retrospective Three-dimensional image registration in corresponding orientation is achieved by linear interpolation of original slices and a variety of interactively controlled video display options These include simultaneous display of multiple slices and brain cuts in all three dimensions for comparison of positioning Brain contours in one imaging modality may be enhanced by appropriate filtering and superimposed onto reference images of another modality Matching accuracy depends on image resolution; misalignment of 4 mm was detected unambiguously in sample studies (fluoro-2-deoxy-D-glucose PET matched with MR) The technique is equally well applicable to normals and to patients with structural brain lesions Additional options for shaded surface display enhance the power to identify neuroanatomical structures in functional image analysis As demonstrated in the example of MR-guided PET, this modeling procedure can be successfully used for identification of brain structures on functional images, even in patients with pathologically altered brain morphology

Probe-correlated viewing of anatomical image data

Abstract: A computerized system for viewing of internal anatomical regions of a patient based on previously acquired image data of the patient. The anatomical regions are viewed in direct relationship to amoving probe which can be hand-held. The location of the probe relative to the patient is reported to computer. The computer then uses the previously acquired image data to generate a desired view of the patient's anatomy in relationship to the position or orientation of the probe. An operator is able to visualize normally invisible anatomical features before commencing, and during, procedure. The correspondence between positions of the patient's anatomy to locations on the stored data images is determined through an initialization procedure which can be repeated or refined between viewing operations. The system may be employed during diagnostic, therapeutic, or surgical procedures.

Three-dimensional spatial registration and interactive display of position and orientation of real-time ultrasound images.

Abstract: Ultrasound images may be difficult to interpret because of the lack of an image orientation display. To resolve this problem, a three-dimensional (3-D) ultrasound scanner has been constructed that provides spatial registration and display of position and orientation of real-time images while allowing unconstrained movement of the scanning transducer. It consists of a conventional sector scanner, a 3-D acoustical spatial locater, and a personal computer. It displays within each image the line of intersection of two image planes, a reference image, and a live image. This display guides and documents image positioning. The scanner's 3-D data also provide the potential for computergraphic modeling of organs, the ability to calculate volumes using nonparallel, nonintersecting image planes, and the capability for 3-D color flow mapping and measurement of Doppler angle.

A fast line finder for vision-guided robot navigation

Abstract: There are two basic ways to improve the speed of a low-level vision algorithm: careful code optimization and selective processing. Reducing the computational effort expended on each pixel reduces the time required to process an image by a constant factor. Selective processing on a limited portion of an image using a focus of attention can decrease overall computation by orders of magnitude. A fast pixel-based algorithm is developed that uses these principles to achieve fast extraction of lines for use in vision-guided mobile robot navigation. It builds upon an algorithm for extracting lines by grouping pixels with similar gradient orientation. It allows parametric control of computational resources required to extract lines with particular characteristics. >

Sensitivity to Three-Dimensional Orientation in Visual Search

Abstract: Previous theories of early vision have assumed that visual search is based on simple two-dimensional aspects of an image, such as the orientation of edges and lines. It is shown here that search can also be based on three-dimensi onal orientation of objects in the corresponding scene, provided that these objects are simple convex blocks. Direct comparison shows that image-based and scene-based orientation are similar in their ability to facilitate search. These findings support the hypothesis that scene-based properties are represented at preattentive levels in early vision. Visual search is a powerful tool for investigating the representations and processes at the earliest stages of human vision. In this task, observers try to determine as rapidly as possible whether a given target item is present or absent in a display. If the time to detect the target is relatively independent of the number of other items present, the display is considered to contain a distinctive visual feature. Features found in this way (e.g. orientation, color, motion) are taken to be the primitive elements of the visual systems. The most comprehensive theories of visual search (Beck, 1982; Julesz, 1984; Treisman, 1986) hypothesize the existence of two visual subsystems. A preattentive system detects features in parallel across the visual field. Spatial relations between features are not registered at this stage. These can only be determined by an attentive system that inspects serially each collection of features in the image. Recent findings, however, have argued for more sophisticated pre- attentive processes. For example, numerous reports show features to be context-sensi tive (Callaghan, 1989; Enns, 1986; Nothdurft, 1985). Others show that spatial conjunctions of features permit rapid search under some conditions (McLeod, Driver, & Crisp, 1988; Treisman, 1988; Wolfe, Franzel, & Cave, 1988). These findings suggest that spatial information can be used at the preattentive stage. Recent studies also suggest that the features are more complex than previously thought. For example, rapid search is possible for items defined by differences in binocular disparity (Nakayama & Silverman, 1986), raising the possibility that stereoscopic depth may be deter- mined preattentively. Indeed, it appears that the features do not simply describe two-dimensional aspects of the image, but also describe attributes of the three-dimensional scene that gave rise to the image. Ramachandran (1988) has shown that the convexity/concavity of surfaces permits spontaneous texture segregation, and Enns and Rensink (1990) have found that search for shaded polygons is rapid when these items can be interpreted as three-dimensi onal blocks. Although the relevant scene-based properties present at preattentive levels have not yet been completely mapped out, likely candidates include lighting direction, surface reflectance, and three-dimensional orientation.

Specular surface inspection using structured highlight and Gaussian images

Abstract: The structured highlight inspection method uses an array of point sources to illuminate a specular object surface. The point sources are scanned, and highlights on the object surface resulting from each source are used to derive local surface orientation information. The extended Gaussian image (EGI) is obtained by placing at each point on a Gaussian sphere a mass proportional to the area of elements on the object surface that have a specific orientation. The EGI summarizes shape properties of the object surface and can be efficiently calculated from structured highlight data without surface reconstruction. Features of the estimated EGI including areas, moments, principal axes, homogeneity measures, and polygonality can be used as the basis for classification and inspection. The structured highlight inspection system (SHINY) has been implemented using a hemisphere of 127 point sources. The SHINY system uses a binary coding scheme to make the scanning of point sources efficient. Experiments have used the SHINY system and EGI features for the inspection and classification of surface-mounted-solder joints. >

Omnidirectional bar code reader with method and apparatus for detecting and scanning a bar code symbol

Abstract: A bar code reader includes an optical system for storing a two dimensional image in memory, which stored two dimensional image contains a bar code symbol A method and apparatus is disclosed for detecting the location of said bar code image by computing the accumulated sum of the products of the derivatives of respective first and second scan lines as a location score for the image under consideration The higher the location score, the higher the probability that the area under consideration contains a bar code image Also, a method and apparatus is disclosed for determining the fine orientation of a located bar code image by the cross-correlation of interpolated scan line data The bar code image is filtered by shifting interpolated scan line data in accordance with the detected peak of the cross-correlation and combining the shifted scan line data

Effect of surface medium on visual search for orientation and size features

Abstract: By using a visual search task, this study examined the encoding of orientation and size for stimuli defined in five different surface media: luminance, color, texture, relative motion, and binocular disparity. Results indicated a spatially parallel analysis of size and orientation features for all surface media, with the possible exception of binocular disparity. The data also revealed a search rate asymmetry in the orientation task for all media: Parallel or shallow search functions were obtained for oblique targets in vertical distractors, whereas steeper serial search functions were obtained for vertical targets in oblique distractors. No consistent asymmetry was found for the large and small targets in the size task. There seemed to be common principles of coding in all these different media, suggesting either a single analysis of shape features applied to a common representation or multiple analyses, one for each surface medium, with each extracting a similar set of features. The shared coding principles may facilitate the use of redundancy across media to reduce ambiguities in the locations and shapes of contours in the visual scene.

A computational model for face location

Abstract: The authors adopted a model-based approach, where the shape of the object is defined in terms of several mini-templates. The mini-templates are abstract descriptions of simple geometric features like arcs and corners. Relationships between mini-templates are not rigid. Rather, they are represented by springs that allow deformation of a template in terms of its size and orientation. Cost functionals are determined empirically. The authors expect their system to generate candidate regions in a given photograph associated with a rank of its goodness. >

Detection of barcodes in binary images with arbitrary orientation

Abstract: The location and orientation of a barcode block is determined by first producing an image of the document that excludes the barcode block and producing a second image wherein the spaces in the barcode block have been deleted thereby providing a solid rectangular block. The two images are subtracted to reject large background clutter while displaying with certainty the full image of the barcode block. Thereafter, down-sampling occurs to remove small clutter and other non-barcode objects while locating the centroid of each barcode block. The image containing the centroid is up-scaled and used to calculate the position of the barcode block in the original document for use by a barcode reader.

Range image segmentation combining edge-detection and region-growing techniques with applications sto robot bin-picking using vacuum gripper

Abstract: A new segmentation algorithm that can be used for robot applications is presented. The input images are dense range data of industrial parts. The image is segmented into a number of surfaces. The segmentation algorithm uses residual analysis to detect edges, then a region-growing technique is used to obtain the final segmented image. The use of the segmentation output for determining the best holdsite position and orientation of objects is studied. As compared to techniques based on intensity images, the use of range images simplifies the holdsite determination. This information can then be used to instruct the robot to grip the object and move it to the required position. The performance of the algorithm on a number of range images is presented. >

Auto-indexing of Oscillation Images

Abstract: A method is presented which indexes spots recorded on single oscillation images without any a priori knowledge of cell parameters. The strategy is similar to that used in four-circle diffractometry and the method works in a fully automatic manner. It is applicable to multiple oscillation images or multiple stills. A complementary method is also described to obtain orientation angles for the case where cell parameters have already been determined.

Surface orientation from projective foreshortening of isotropic texture autocorrelation

Abstract: A method for determining local surface orientation from the autocorrelation function of statistically isotropic textures is introduced. It relies on the foreshortening that occurs in the image of an oriented surface, and the analogous foreshortening produced in the texture-autocorrelation function. This method assumes textural isotropy, but does not require the texture to be composed of texels or assume other texture regularities. The technique was applied to natural images of planar-textured surfaces and found to give good results. The simplicity of the method and its use of information from all parts of the image are emphasized. >

Method and apparatus for calibrating a vision guided robot

Abstract: A method and apparatus for calibrating a vision-guided robot of the type having a slit light unit for illuminating a workpiece with a target image, a camera for detecting the target image, a tool for working upon the workpiece and a controller for positioning the tool in response to image signals from the camera so that the camera signals correspond to stored image signals The method includes the steps of displacing the robot from a home position to a calibration position wherein the camera is oriented toward a target, determining a camera correction value between a desired camera position and the actual camera position by comparing a perceived target image with a stored target image and incorporating the camera correction value for robot positioning during a subsequent operational movement The method also includes a slit light calibration sequence in which the robot is displaced to a second calibration position where the slit light unit directs a light beam on a second target, the camera perceives a second target image and a light correction value between a desired slit light image and an actual slit light image is determined and incorporated for robot positioning during the subsequent operational movement The calibration unit comprises topmost, intermediate and lower plates arranged in stairstep fashion, the topmost plate having a first pattern perceivable by the camera to enable the controller to determine spatial orientation of the plate and the intermediate and lower plates include a second pattern perceivable by the camera which enables the controller to determine the position of the slit light unit

Storage and playback of digitized images in digital database together with presentation control file to define image orientation/aspect ratio

Abstract: A digital image processing system digitizes and stores photographic film images in their captured orientation on film, in order to obviate the need to physically rotate the film scanner relative to the film for vertical images, thereby significantly reducing the complexity and cost of the scanner. Instead, each stored image file has an associated presentation control file, which contains orientation and aspect ratio information, so that the image playback device will know how each image has been stored on the digital image database, such as a compact disc. When the disc is inserted into a playback device for driving an output display such as a color TV monitor, the playback device is readily able to decode the playback control information in the course of reading out the digitized image, so that the image will be displayed in an upright orientation and at the correct aspect ratio for the display.

Steerable Filters for Early Vision, Image Analysis, and

Abstract: Oriented filters are useful in many early vision tasks. One often needs to apply the same filter, rotated to different angles under adaptive con- trol, or wishes to calculate the filter response at various orientations. We present an efficient ar- chitecture to synthesize filters of arbitrary orien- tations from linear combinations of basis filters, allowing one to adaptively "steer" a filter to any orientation, and to determine analytically the fil- ter output as a function of orientation. Steerable filters may be designed in quadrature pairs to allow adaptive control over phase as well as orientation. We show how to design and steer the filters, and present examples of their use in several tasks: the analysis of orientation and phase, angularly adaptive filtering, edge de- tection, and shape-from-shading. One can also build a self-similar steerable pyramid represen- tation which may be considered to be a steerable wavelet transform. The same concepts can be generalized to the design of 3-D steerable filters, which should be useful in the analysis of image sequences and volumetric data.

Steerable filters for early vision, image analysis, and wavelet decomposition

Abstract: An efficient architecture is presented to synthesize filters of arbitrary orientations from linear combinations of basis filters, allowing one to adaptively 'steer' a filter to any orientation, and to determine analytically the filter output as a function of orientation. The authors show how to design and steer filters, and present examples of their use in several tasks: the analysis of orientation and phase, angularly adaptive filtering, edge detection, and shape-from-shading. It is also possible to build a self-similar steerable pyramid representation which may be considered to be a steerable wavelet transform. The same concepts can be generalized to the design of 3-D steerable filters, which should be useful in the analysis of image sequences and volumetric data. >

Maneuver estimation using measurements of orientation

Abstract: An image-based algorithm which provides an estimate of the current radial acceleration of a target is studied. Since the data in a single image frame provide information only on the orientation of the target, a sequence of frames must be processed to detect maneuvers. The estimation problem is parameterized in terms of natural groupings of measurement errors, and the influence of these errors on estimator fidelity is studied. >

Apparatus for visual recognition

Abstract: A basic image of objects is extracted from a two-dimensional image of objects. Geometrical elements of the objects are extracted from the extracted basic image. The objects to be recognized are identified by searching a combination of the geometrical elements which match a geometrical model and then utilizing candidate position/orientation of the objects to be recognized, said candidate position/orientation being determined from a relationship in relative position between the combination of geometrical elements and the geometrical model. Mesh cells fixed to the geometrical model are mapped on the basic image based on the candidate position/orientation. In addition, verification is made as to whether an image of the geometrical model mapped by the candidate position/orientation is accurately matched with an image of one of the objects to be recognized, through a neural network to which values got from the basic image included in the individual mesh cells are to be applied as input values. Combination weight factors employed in the neural network are learned according to the verified results. It is also possible to recognize the multi-purpose objects according to how to learn the combination weight factors.

Dual image video inspection apparatus

Abstract: A video inspection system includes first and second video cameras (36 and 48) mounted along a parallel axes. A lighting array (16) is pulsed, and resultant light is reflected from a specimen to both cameras. Orientation of the specimen is determined in accordance with an image generated from a first camera (36). This data is used to isolate a selected portion of the specimen for analysis by an image generated from the second camera (48).