| A. Filbois and D. Gemmerle. From step edge to line edge: Combining geometric and photometric information. In MVA '94 IAPR Workshop on Machine Vision Applications, pages 87--90, 1994. |
....for the extraction of anatomical features, e.g. blood vessels from an X ray angiogram [3] The published schemes for line detection can be classified into two categories. For a detailed review of these methods see [14] The first approach is to regard lines as objects having parallel edges [8, 5], and to extract them by combining the output of two specially tuned edge filters. By iteration in scale space, lines of arbitrary widths can be detected, but only with limited width resolution. Furthermore, the approach is computationally very expensive. The second approach is to regard the ....
A. Filbois and D. Gemmerle. From step edge to line edge: Combining geometric and photometric information. In MVA '94 IAPR Workshop on Machine Vision Applications, pages 87--90, 1994.
....for line points, elaborate and computationally expensive perceptual grouping schemes have to be used to select salient lines in the image [8, 9, 10, 7] Furthermore, lines cannot be extracted with sub pixel accuracy. The second approach is to regard lines as objects having parallel edges [11, 12, 13]. In a first step, the local direction of a line is determined for each pixel. Then two edge detection filters are applied in the direction perpendicular to the line, where each filter is tuned to detect either the left or right edge of the line. The responses of each filter are combined in a ....
Alain Filbois and Didier Gemmerle. From step edge to line edge: Combining geometric and photometric information. In MVA '94 IAPR Workshop on Machine Vision Applications, pages 87--90, 1994.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC