edge detection

what are the threshold value for sobel, prewitt, roberts, log, canny, zerocross for an 320x280 dimension black n white eye picture with pixel of 320 pixel(width) and 280 pixel(height) for edge detection???

Answer 1

[David Young]

You have to choose these values yourself, either on the basis of a noise model for the image and an objective function you wish to minimise, or (more commonly) by trial and error.

Answer 2

[Image Analyst]

Perhaps you didn't read enough of the help. I've reproduced it here for you to read:

For the gradient-magnitude methods (Sobel, Prewitt, Roberts), thresh is used to threshold the calculated gradient magnitude. For the zero-crossing methods, including Lap, thresh is used as a threshold for the zero-crossings; in other words, a large jump across zero is an edge, while a small jump isn't. 

The Canny method applies two thresholds to the gradient: a high threshold for low edge sensitivity and a low threshold for high edge sensitivity. edge starts with the low sensitivity result and then grows it to include connected edge pixels from the high sensitivity result. This helps fill in gaps in the detected edges.

In all cases, the default threshold is chosen heuristically in a way that depends on the input data. The best way to vary the threshold is to run edge once, capturing the calculated threshold as the second output argument. Then, starting from the value calculated by edge, adjust the threshold higher (fewer edge pixels) or lower (more edge pixels).