next up previous contents
Next: Connecting points with neighbours Up: Extracting features from an Previous: General global features

Finding top and bottom points from an image

 

findtb Find high and low gray level points
-in <image> input image
-dout <nodes> points in a data frame
[-size <maskrad>] radius of search area
[-neq] neighbourhood has not same gray level
[-t] find tops (light areas)
[-b] find bottoms (dark areas)

This command is used for finding points characterizing structure of (paper) image. Resulting data frame contains fields x, y and gray. First two define coordinates of points and third field has value 0 or 255 telling if point is bottom or top point, respectively.

Example: See section 6.6.4.



Anssi Lensu
Thu May 17 15:00:44 EET DST 2001