Feature extraction

This is an old revision of this page, as edited by Tarquin (talk | contribs) at 14:19, 8 June 2003. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Feature extraction is an area of image processing which involves using algorithms to detect and isolate various desired portions of a digitized image or video stream.

The following is just a list of subject headings to be filled in later

Template operations & Fourier Transforms


LOW-LEVEL Edge detection -- 1st order: Prewitt, Sobel, Canny, Spacek 2nd Order: Laplacian, Marr-Hildreth

Curvature -- Edge direction, changing intensity, autocorrelation

Image motion -- Area based, differntial approach. Optical flow.

SHAPE BASED Thresholding

Template matching

Hough transform -- Lines Circles/Ellipses Arbitrary shapes (Generalized Hough Transform)

FLEXIBLE METHODS -- Deformable, parameterized shapes Active contours (snakes)