Image processing — OZONE Asylum, home of the Mad Scientists

OZONE

Image processing

This page's ID: 28346

Edit Post

Who can edit a post?	The poster and administrators may edit a post. The poster can only edit it for a short while after the initial post.

Your User Name:
Your Password:
Login Options:	Remember Me On This Computer

Your Text: Insert Slimies » Insert UBB Code » Close Last Tag \| All Tags UBB Help	[b]Lord_Fukutoku:[/b] Actually those things were a big part of my BS course. Could you post some sample images so we can see if you have to use the heavy artillery or a straight forward technique. First of all, all this is called Digital image processing. You should search for image segmentation. This term cover the image processing techniques used to separate different regions of interrest in an image. On wikipedia the [url=http://fr.wikipedia.org/wiki/Segmentation_d'image]french[/url] page seems better than the [url=http://en.wikipedia.org/wiki/Segmentation_(image_processing)]english[/url] one. For the characters/digits recognition, you might need to generate the skeleton ( see [url=http://en.wikipedia.org/wiki/Topological_skeleton]topological skeleton[/url] ) of the regions ( obtained above ) and check the shape of the skeletons and see if they match some reference skeletons. If you aim for a pixel based approach, you might resize the different regions to a given resolution and compare them to the template of the patterns you are looking for. hint blurring both the template and the regions improves the tolerance of the algorithm. Reading about [url=http://en.wikipedia.org/wiki/Optical_character_recognition]OCR[/url] might help too. And in that field [url=http://en.wikipedia.org/wiki/Captcha#Computer_character_recognition]CAPTCHA defeating technique[/url] should give some precious tips. One thing we did during my BS was to make an FFT on the pattern we wanted to find in another image, then use the resulting images ( in the frequency domain ) as a kernel we applied on the FFT of the image supposedly containing the pattern. Doing an IFFT on the convoluted image gave a image that was mostly black, with some white pixels exactly where the pattern appeared in the initial image. I don't remember the gore(?) details but that's basically the idea. [edit] This is called 'Shape recognition by convolution' [/edit] [url=http://www.p01.org/][img]http://poi.ribbon.free.fr/files/p01_ozoneasylum_sig_galaxy.gif[/img][/url] [small](Edited by [url=http://www.ozoneasylum.com/user/2185]poi[/url] on 09-02-2006 00:29)[/small] Loading...
Options:	Enable Slimies Enable Linkwords

« Backwards — Onwards »

Show Forum Drop Down Menu