Hey all

Basically for my final project at university, I'm developing a vehicle license plate detection application. Now I consider myself an intermediate programmer, however my mathematics knowledge lacks anything above secondary school, therefore producing detection formulae is basically impossible.

I've spend a good amount of time looking up academic papers such as:

http://www.scribd.com/doc/266575/Detecting-Vehicle-License-Plates-in-Images
http://www.cic.unb.br/~mylene/PI_2010_2/ICIP10/pdfs/0003945.pdf
http://www.eurasip.org/Proceedings/Eusipco/Eusipco2007/Papers/d3l-b05.pdf

When it comes to the maths, I'm lost. Due to this testing various graphic images proved productive, for example:

to

However this approach is only catered to that particular image, and if the techniques were applied to different images, I'm sure a different, most likely poorer conversion would occur. I've read about a formula called the bottom hat morphology transform, which according to the first does the following:

"Basically, the trans- formation keeps all the dark details of the picture, and eliminates everything else (including bigger dark regions and light regions)."

Sadly I can't find much information on this, however the image within the documentation near the end of the report shows it's effectiveness. I'm aware this is complicated and vast, I'd just appreciate a little advice, even in terms of what transformation techniques I should focus on developing, or algorithm regarding edge detection or pixel detection.

Few things I need to add

• Developing in C Sharp
• Confining the project to UK registration plates only
• I can basically choose the images to convert as a demonstration

Thanks