openCV - anpr system. Improve success rate
I am trying to write a very good ANPR (automatic number plate recognition) system for Brazil's cars plates. So far I have used the javaANPR method which is the X and Y projection to find the ROI (car plate). It works well but not so good with image that has a lot of shadow in the car. And I am using tesseract-ocr as well for character recognition.
I got 80% of success for really good car images, from cars not moving.
And I got less than 60% for not so good images from moving cars.
I have been resourcing online, reading papers, etc. What do you think could help me improve it ? Maybe marge two methods ? Use templateMatch as well ? Because I need about 95% - 98% of success rate.
I see the anpronline Their demo: https://www.anpronline.net/demo.html
They have done a really good job. It worked on 100% of my images.
Are you guys aware of what OCR engine do they use ? Maybe this is a top secret.
But can you guys point me to the right direction of how to improve my OCR ?
I really appreciate any help.
Thanks
I am afraid that about 99% of all good anpr detection algorithms have been patented or commercialized and are not publicly available from source code. What I suggest is try to search for recent research papers and try to implement them. Maybe take a look at using cascade classifier training. I think it should be possible to train in number plates if the view of the camera stays constant.