Abstract: A limited number of views or projections, e.g., two, are used to generated a reconstructed image of an object. In order to improve the quality of the image, terracing and smoothing functions are implemented. In addition, the reconstructed image may be divided into objects and background prior to terracing and smothing and the object and background can be reconstructed separately. Further, after the reconstructed image is generated threat and texture analyses of the reconstructed image may be performed.

Abstract: Range discontinuities (44) in an imaged scene are located with superior accuracy by using a pair of stereoscopically related images (10, 12) of the scene to sense edges in the scene, and to determine the range of correlatable image pixels; segmenting the scene into regions (36) of similar intensity; assigning to each region (36) a range based upon the range of any correlatable pixels in it; and locating the boundary (44) between adjacent regions of substantially dissimilar range.

Abstract: A method and apparatus for detection of parallel edges in image processing systems is shown. A video source producing an image which is operated upon by Laplacian of Gaussian operator to produce an LOG image within which sign changes are detected to produce a zero crossing edge detected image. A vector gradient field of the LOG image is computed and subjected to a gradient field smoothing operation to produce a smoothed gradient field. The smoothed gradient field is examined to detect scaler minima within the field and the results thereof used to compute parallelism strength in accordance with preestablished criteria to generate a parallelism line image which is printed using a conventional printer.