CrossingDetect will only find zero crossings when applied to images of type .
For color images, CrossingDetect operates on the intensity averaged over all channels.
CrossingDetect[m] finds zero crossings in a numerical matrix m, returning a sparse array.
CrossingDetect effectively chops values smaller in magnitude than delta.
CrossingDetect by default treats all eight pixels surrounding a given pixel as adjacent.
The option setting CornerNeighbors->False treats only the four pixels in the coordinate directions as adjacent.
Using the option setting CornerNeighbors->None, CrossingDetect operates on the dual grid whose pixels correspond to the corners in the original image, thereby reducing the dimensions of the resulting image by one pixel.