OCR in images of different sizes

[Cristi@n]

Hello,

I have a problem with the OCR. I want to read a plate from a car but we have 2 sizes for the plates. One has 3 letters and 4 numbers as in image 4.jpg and the other has 3 letters and 3 numbers as in example 5.jpg. So the project its about reading these plates but here is the problem. In the captured image i find the pattern ECUADOR and from these coordinates I cut the image around the characters and numbers. The problem is when I want to read de 4 letters plate it does fine but when the plate its smaller (3letters plate) the cut of the image its as it were of 4 letters so OCR reads parts that i dont want (foto final .jpg) . So I am wondering if you could help me with this problem. I dont know how to recognize automatically if the plkate its 3 letter or 4 so i can read with OCR with any problem or if you know another way to do this..

Thanks in advance...

Cristian...

[Kenji_Yamamoto]

Hey Cristian,

Please inform more details as what kind of device are you using to acquisition images, software version and hardware (if applicable). Otherwise the following links show some OCR examples that may help you.

http://zone.ni.com/devzone/cda/epd/p/id/547

http://forums.ni.com/ni/board/message?board.id=200&requireLogin=False&thread.id=7131

Regards,