Showing papers on "Orientation (computer vision) published in 1993"

Improved localizadon of cortical activity by combining eeg and meg with mri cortical surface reconstruction: A linear approach

Abstract: We describe a comprehensive linear approach to the problem of imaging brain activity with high temporal as well as spatial resolution based on combining EEG and MEG data with anatomical constraints derived from MRI images. The "inverse problem" of estimating the distribution of dipole strengths over the cortical surface is highly underdetermined, even given closely spaced EEG and MEG recordings. We have obtained much better solutions to this problem by explicitly incorporating both local cortical orientation as well as spatial covariance of sources and sensors into our formulation. An explicit polygonal model of the cortical manifold is first constructed as follows: (1) slice data in three orthogonal planes of section (needle-shaped voxels) are combined with a linear deblurring technique to make a single high-resolution 3-D image (cubic voxels), (2) the image is recursively flood-filled to determine the topology of the gray-white matter border, and (3) the resulting continuous surface is refined by relaxing it against the original 3-D gray-scale image using a deformable template method, which is also used to computationally flatten the cortex for easier viewing. The explicit solution to an error minimization formulation of an optimal inverse linear operator (for a particular cortical manifold, sensor placement, noise and prior source covariance) gives rise to a compact expression that is practically computable for hundreds of sensors and thousands of sources. The inverse solution can then be weighted for a particular (averaged) event using the sensor covariance for that event. Model studies suggest that we may be able to localize multiple cortical sources with spatial resolution as good as PET with this technique, while retaining a much finer grained picture of activity over time.

Dynamic and static hand gesture recognition through low-level image analysis

Abstract: A low-level model-free dynamic and static hand gesture recognition system utilizes either a 1-D histogram of frequency of occurrence vs. spatial orientation angle for static gestures or a 2-D histogram of frequency of occurrence vs. space-time orientation for dynamic gestures. In each case the histogram constitutes the signature of the gesture which is used for gesture recognition. For moving gesture detection, a 3-D space-time orientation map is merged or converted into the 2-D space-time orientation histogram which graphs frequency of occurrence vs. both orientation and movement. It is against this representation or template that an incoming moving gesture is matched.

Apparatus and method for adaptively interpolating a full color image utilizing chrominance gradients

Abstract: Adaptive interpolation is performed by apparatus operating upon a digitized image signal obtained from an image sensor having color photosites that generate a plurality of color values, but only one color per photosite. A digital processor obtains gradient values from the differences between chrominance values in vertical and horizontal image directions. The gradient values are compared with each other in order to select one of the directions as the preferred orientation for the interpolation of additional luminance values. The interpolation is then performed upon values selected to agree with the preferred orientation.

Automatic detection of brain contours in MRI data sets

Abstract: A software procedure is presented for fully automated detection of brain contours from single-echo 3-D MRI data, developed initially for scans with coronal orientation. The procedure detects structures in a head data volume in a hierarchical fashion. Automatic detection starts with a histogram-based thresholding step, whenever necessary preceded by an image intensity correction procedure. This step is followed by a morphological procedure which refines the binary threshold mask images. Anatomical knowledge, essential for the discrimination between desired and undesired structures, is implemented in this step through a sequence of conventional and novel morphological operations, using 2-D and 3-D operations. A final step of the procedure performs overlap tests on candidate brain regions of interest in neighboring slice images to propagate coherent 2-D brain masks through the third dimension. Results are presented for test runs of the procedure on 23 coronal whole-brain data sets, and one sagittal whole-brain data set. Finally, the potential of the technique for generalization to other problems is discussed, as well as limitations of the technique. >

Omniview motionless camera endoscopy system

Abstract: A endoscopic-type device for omnidirectional image viewing providing electronic pan-and-tilt orientation, rotation, and magnification within a selected field-of-view for use in applications in various environments such as in internal medicine inspection, monitoring, and surgery. The imaging device (using optical or infrared images) is based on the effect that the image from a wide angle lens, which produces a circular image of an entire field-of-view, can be mathematically corrected using high speed electronic circuitry. More specifically, an incoming image from a endoscope image acquisition source, including a wide angle lens, is transmitted through an image conduit and captured by a camera that produces output signals according to that image. A transformation of these output signals is performed for the viewing region of interest and viewing direction, and a corrected image is output as a video image signal for viewing, recording, or analysis. Multiple simultaneous images can be output from a single input image.

Locating 2-D bar codes

Abstract: After a two-dimensional bar code is scanned to provide a stored image, the location (i.e., bounds, including orientation) of the bar code image within the scanned area image must be determined to enable decoding. Methods for locating the bar code image include the steps of sampling the stored image, identifying sampling traversals of bar code start and stop patterns, and correlating the identified start and stop pattern traversals to a common bar code image. The correlating data is then used to identify a nominally rectangular area bounding the bar code image. A bounding box may be identified as the smallest area capable of encompassing all of the start and stop pattern traversals related to a common bar code image. Output location data may specify the coordinates of the four corners of a bounding box for use in subsequent decoding. Related systems are described.

Apparatus and method for adaptively interpolating a full color image utilizing luminance gradients

Abstract: Adaptive interpolation is performed by apparatus operating upon a digitized image signal obtained from an image sensor having color photosites that generate a plurality of color values, but only one color per photosite. A digital processor obtains gradient values from the differences between luminance values in vertical and horizontal image directions. The gradient values are compared to a programmable threshold in order to select one of the directions as the preferred orientation for the interpolation of additional luminance values. The interpolation is then performed upon values selected to agree with the preferred orientation.

Promising directions in active vision

Abstract: Active vision systems have mechanisms that can actively control camera parameters such as position, orientation, focus, zoom, aperture, and vergence (in a two-camera system) in response to the requirements of the task and external stimuli. They may also have features such as spatially variant (foveal) sensors. More broadly, active vision encompassesattention, selective sensing in space, resolution, and time, whether it is achieved by modifying physical camera parameters or the way data is processed after leaving the camera. In the active-vision paradigm, the basic components of the visual system are visual behaviors tightly integrated with the actions they support; these behaviors may not require elaborate categorical representations of the 3-D world. Because the cost of generating and updating a complete, detailed model of most environments is too high, this approach to vision is vital for achieving robust, real-time perception in the real world. In addition, active control of imaging parameters has been shown to simplify scene interpretation by eliminating the ambiguity present in single images. Important research areas in active vision include attention, foveal sensing, gaze control, eye-hand coordination, and integration with robot architectures.

Intensity and edge-based symmetry detection with an application to car-following

Abstract: We present two methods for detecting mirror symmetry in images, one based directly on the intensity values and another one based on a discrete representation of local orientation. A symmetry finder has been developed which uses the intensity-based method to search an image for compact regions which display some degree of mirror symmetry due to intensity similarities across a straight axis. In a different approach, we look at symmetry as a bilateral relationship between local orientations. A symmetry-enhancing edge detector is presented which indicates edges dependent on the orientations at two different image positions. SEED, as we call it, is a detector element implemented by a feedforward network that holds the symmetry conditions. We use SEED to find the contours of symmetric objects of which we know the axis of symmetry from the intensity-based symmetry finder. The methods described in this paper have been developed and tested for the recognition and tracking of cars in a real-time system for automatic car-following and headway control on normal roads.

Image compression using the spatial-orientation tree

Abstract: The zero-tree method for image compression, proposed by J. Shapiro (1992), is studied. The method is presented in a more general perspective, so that its characteristics can be better understood. From this analysis, an improved method is proposed, and it is shown that the new method can increase the PSNR up to 1.3 dB over the original method. >

Three dimensional pointing device monitored by computer vision

Abstract: A pointing device (28), comprising light sources (30) and monitored by a computer vision task running in a microcontroller (108) and a computer (24). The computer vision task computes the spatial position and orientation of the pointing device, and enables an operator to control virtual three dimensional objects (73) on the display (22) of the computer. Images (78) are captured by a video camera (20) and digitized, and only image rows that contain bright pixels (80) from the light sources are processed. The light sources are the tips of optic fibers (30) guiding light from a laser diode (32), and an optical filter (46) on the camera is matched to the wavelength of the laser diode.

A unified approach to boundary perception: edges, textures, and illusory contours

Abstract: A model consisting of a multistage system which extracts and groups salient features in the image at different spatial scales (or frequencies) is used. In the first stage, a Gabor wavelet decomposition provides a representation of the image which is orientation selective and has optimal localization properties in space and frequency. This decomposition is useful in detecting significant features such as step and line edges at different scales and orientations in the image. Following the wavelet transformation, local competitive interactions are introduced to reduce the effects of noise and changes in illumination. Interscale interactions help in localizing the line ends and corners, and play a crucial role in boundary perception. The final stage groups similar features, aiding in boundary completion. The different stages can be identified with processing by simple, complex, and hypercomplex cells in the visual cortex of mammals. Experimental results demonstrate the performance of this model in detecting boundaries (both real and illusory) in real and synthetic images. >

2-D bar code scanner/decoder having a redundancy canceller

Abstract: Hand-held devices are provided for both scanning and decoding coded images such as two-dimensional bar codes. A linear scanning array of image sensing elements in the scanner/decoder provides image data with pixel-to-pixel synchronism, but lacking scan-to-scan synchronism as the scanning array is moved transversely across the bar code image. No tracking ball or roller is included to provide data enabling scan-to-scan synchronism. Redundant scan cancellation is employed to delete redundant image data from the stored image, with the adequate representation of coded information taking precedence over storage of a high resolution image. The stored image is sampled to correlate bar code edge pattern elements in order to identify the bounds and orientation of scanned bar code images. The redundancy-reduced stored bar code image is decoded within the hand-held unit, with use of data on bar code bounds and orientation, to provide decoded information for further use. Scanner/decoder devices and methods, and data redundancy reduction methods are described.

Shape from texture from a multi-scale perspective

Abstract: The problem of scale in shape from texture is addressed. The need for two scale parameters is emphasized: a local scale, for describing the amount of smoothing used for suppressing noise and irrelevant details when computing primitive texture descriptors from image data; and an integration scale, for describing the size of the region in space over which the statistics of the local descriptors is accummulated. The proposed computational model is expressed completely in terms of different invariants defined from Gaussian derivatives at multiple scales in scale-space. The resulting texture description can be combined with various assumptions about surface texture to estimate local surface orientation. Two specific assumptions, weak isotropy and constant area, are explored in more detail. Results from experiments on real and synthetic reference data with known geometry that demonstrate the viability of the approach are presented. >

Method and apparatus for flash correlation.

Abstract: Flash correlation instantaneously compares (52) two or more patterns (20, 50) to determine whether they are the same or essentially the same regardless of the complexity of the images, and in spite of the addition of noise, local changes, and variations in resolution and focus. Flash correlation artifacts (58) also provide cues to quantitative assessment of relative movement, stretching, blurring, and warping of one image with respect to the other. Presence of a flash correlation artifact between two stacks of patterns (58) is sufficient to identify the stacks as containing at least one pair of massively correlated patterns (62). Precise control of registration, image size and orientation is not required. An image may be combined with other images, either by overlays or concatenation, and still be identified. A flash correlation engine may utilize optical, analog or digital processing to provide rapid sorting, classification, and identification functions with minimal computational complexity.

Point-of-gaze tracker

Abstract: The tracker determines a vision vector for an eye of an operator. The device generally comprises: a video camera oriented so as to observe an eye of an operator for obtaining an image of the eye; camera interface electronics and image processor for digitizing the image of the operator's eye and for analyzing the digitized image for determining therefrom a plurality of points determinative of the iridal ellipse, the points being on the boundary between the eye's sclera and iris as represented by different light intensities; and a processor for utilizing said information and an estimate of the diameter of the iris in formulating an estimated optical axis vector for the eye. If the position and orientation of the camera is known relative to the operator's eye, then the pupillary ellipse can be used instead of the iridal ellipse. The tracker of the invention can be used as a mouse emulator attached to a mouse port of a personal computer system.

Omnidirectional scanning method and apparatus

Abstract: A method and apparatus for reading encoded symbols such as bar code labels at any orientation to a raster scanning device. A pattern of virtual scan lines is selected over the two-dimensional imaging region according to the specifications of the images to be read. The pattern is generated by defining a family of parallel lines of a certain spacing and rotating the family by a specified angle until the two-dimensional imaging region is covered. Only the data at selected raster locations on the virtual scan lines is stored and processed. One-dimensional signal processing methods are used to detect edges and decode the encoded symbols.

Document skew detection based on local region complexity

Abstract: A new method is proposed for detecting skew in document images which contain a mixture of text areas, photographs, figures, charts, and tables. Two basic ideas are introduced in the method. One idea is that a new parameter is used for skew detection to discern the orientation of text lines in document images. This parameter is based on the document image complexity and is obtained from the number of transitions from white to black pixels or vice versa. The other idea is that skew is detected in local regions in which only text lines are expected. Such local regions are extracted from a document image automatically and the obtained skew angle is defined as the overall document skew. Document skew has been measured in experiments with an error of 0.12 degrees on the average for all test documents. >

Semi-automatic segmentation of vascular network images using a rotating structuring element (ROSE) with mathematical morphology and dual feature thresholding

Abstract: A method for measuring the spatial concentration of specific categories of vessels in a vascular network consisting of vessels of several diameters, lengths, and orientations is demonstrated. It is shown that a combination of the mathematical morphology operation, opening, with a linear rotating structuring element (ROSE) and dual feature thresholding can semi-automatically segment categories of vessels in a vascular network. Capillaries and larger vessels (arterioles and venules) are segmented here in order to assess their spatial concentrations. The ROSE algorithm generates the initial segmentation, and dual feature thresholding provides a means of eliminating the nonedge artifact pixels. The subsequent gray-scale histogram of only the edge pixels yields the correct segmentation threshold value. This image processing strategy is demonstrated on micrographs of vascular casts. By adjusting the structuring element and rotation angles, it could be applied to other network structures where a segmentation by network component categories is advantageous, but where the objects can have any orientation. >

A noise-tolerant algorithm for robotic hand-eye calibration with or without sensor orientation measurement

Abstract: An iterative algorithm for calibration of a robotic hand-eye relationship is presented. The hand-eye calibration can be performed by solving a system of homogeneous transformation equations of the form A/sub i/X=XB/sub i/, where X is the unknown sensor position relative to the robot wrist, A/sub i/ is the ith robot motion, and B/sub i/ is the ith sensor motion. Unlike existing approaches, the algorithm presented solves the kinematic parameters of X in one stage, thus eliminating error propagation and improving noise sensitivity. Furthermore, with the iterative algorithm, the parameters of X can be computed even when the rotational part of B/sub i/ is unknown. This is important since position is easier to measure than orientation. Comparative simulation studies show that the performance of the iterative algorithm is usually better than that of noniterative two-stage algorithms, regardless of whether the orientation part of B/sub i/ is used or not. This paper also discusses the application of the proposed method to calibration of a tool mounted on a robot manipulator. >

Is pattern vision in insects mediated by 'cortical' processing?

Abstract: IT is known that bees, like humans, can learn the orientation of a striped pattern, and recognize this orientation in other simple patterns that they have never previously encountered1,2. How is orientation analysed by the insect visual system? In the light of what is known about animal vision, there are two obvious possibilities. First, orientation could be determined purely in terms of the directional movement signals that the pattern generates as the bee approaches it or flies past it3,4. Such a scheme would fit in well with the common supposition that much of insect vision relies solely on motion cues4,5. An alternative view, not considered for insect vision so far, would be that specific features of the pattern, such as bars or edges, are extracted and their orientation analysed as in the mammalian cortex. Our findings argue strongly against the first and for the second possibility. They suggest that similar principles underlie the analysis of pattern orientation in insects and higher vertebrates.

Language-free layout analysis

Abstract: A system for isolating blocks, lines, words, and symbols within images of machine-printed textual documents that is, to a large existent, independent of language and writing system is described. This is achieved by exploiting a small number of nearly universal typesetting and layout conventions. The system does not require prior knowledge of page orientation (module 90/spl deg/), and copes well with nonzero skew and shear angles (within 10/spl deg/). Also it locates blocks of text without reliance on detailed a priori layout models, and in spite of unknown or mixed horizontal and vertical text-line orientations. Within blocks, it infers text-line orientation and isolates lines, without knowledge of the language, symbol set, text sizes, or the number of text lines. Segmentation into words and symbols, and determination of reading order, normally require some knowledge of the language: this is held to minimum by relying on shape-driven algorithms. The underlying algorithms are based on Fourier theory, digital signal processing, computational geometry, and statistical decision theory. Most of the computation occurs within algorithms that possess unambiguous semantics (that is, heuristics are kept to a minimum). The effectiveness of the method on English, Japanese, Hebrew, Thai, and Korean documents is discussed. >

System and method of generating interactive computer graphic images incorporating three dimensional textures

Abstract: A system and method of interactively generating computer graphic images for incorporating three dimensional textures. The method of the present invention includes defining an orientation of a polygon relative to a plurality of three dimensional (3D) texture data sets, determining a level of detail of a pixel associated with the polygon, and selecting a first 3D texture data set and a second 3D texture data set from the plurality of 3D texture data sets in accordance with the pixel level of detail. The method also includes mapping the pixel to a first position within the first 3D texture data set and to a second position within the second 3D texture data set in accordance with the orientation, and generating a display value for the pixel in accordance with the mapping of the pixel to the first and second positions.

Combining stereo and motion analysis for direct estimation of scene structure

Abstract: The authors describe an algorithm based on hierarchical model-based estimation and refinement that aims to make best use of the information in stereo and motion data sets to estimate scene structure. Information from both data sets is used to compute simultaneously stereo and motion correspondences that are consistent with a single scene structure. One result is that local ambiguities in information provided by one data set are resolved by information provided by the other data set. The algorithm uses an infinitesimal rigid-body motion model to estimate relative camera orientation and local ranges for both the stereo and motion components of the data. If the relative orientation of the cameras in the stereo data set is known, the solution proposed can be re-derived using fixed rather than variable camera parameters for the stereo data set. >

Geometrical calibration for 3D x-ray imaging

Abstract: Reconstructing a 3D structure from a set of its 2D X-ray projections requires that the source position and image plane orientation in 3D space be obtained with high accuracy for each of the imaging chain positions. This knowledge is generally obtained through a geometrical calibration of the data acquisition system. In this paper, we present a fully automatic method for such a geometrical calibration, well suited to a 3D X-ray imaging system which acquires sets of 2D projections during a rotation of the imaging chain. This method is based on (1) the use of a dedicated calibration phantom with reference points, (2) an automatic algorithm to detect and identify the reference points on the phantom's 2D X-Ray projections, and (3) the estimation of the imaging chain geometrical parameters by minimizing the reprojection mean quadratic error measured on these reference points. Results obtained both from simulation data and from data acquired on an experimental bench are presented.