[SciPy-User] Edge Detection
Thu Nov 12 09:23:53 CST 2009
All of the OpenCV edge detection routines are also available in
scikits.image if you have opencv (>= 2.0) installed.
On Tue, Nov 10, 2009 at 5:48 PM, Zachary Pincus <firstname.lastname@example.org> wrote:
> References: Start around just looking at the top google hits for "image
> processing edge detection" -- that should be a pretty good start. Also,
> google any unfamiliar terms below... I really find that there's a ton of
> good basic image-processing information available online.
> Code: Look at what's available in scipy.ndimage. There are functions for
> getting gradient magnitudes, as well as standard filters like Sobel etc.
> (which you'll learn about from the above), plus morphological operators for
> modifying binarized image regions (e.g. like erosion etc.; useful for
> getting rid of stray noise-induced edges), plus some basic functions for
> image smoothing like median filters, etc.
> For exploratory analysis, you might want some ability to interactively
> visualize images; you could use matplotlib or the imaging scikit, which is
> still pre-release but making fast progress:
> I've attached basic code for Canny edge detection, which should demonstrate
> a bit about how ndimage works, plus it's useful in its own right. There is
> also some code floating around for anisotropic diffusion and bilateral
> filtering, which are two noise-reduction methods that can be better than
> simple median filtering.
> On Nov 10, 2009, at 11:37 AM, Dan Yamins wrote:
>> I'm looking into using SciPy for a couple of edge-detection problems,
>> involving detection of edges in images of text (in simple, clean fonts).
>> If someone on this list could point me to a relevant resource / function,
>> that would be excellent. (I have essentially no background in image
>> processing, but am reasonably comfortable mathematically, and I would be
>> happy to dive into something fairly technical.)
>> SciPy-User mailing list
> SciPy-User mailing list
More information about the SciPy-User