is it good to train a classifier for each character in ANPR?

asked 2016-03-18 09:25:27 -0600

I'm trying to create ANPR (for Persian character plates), the only solution I have came up with, is to train a classifier for each character but I 'm sure it should take a lot time to train classifier for each character also it should not have good performance in detection time. Isn't there any other ways to do OCR? or, if there is no other solution, how should I choose positive and negative samples to achieve a good detection hit rate?

edit retag flag offensive close merge delete

Comments

(and the answer is: no, you should not train a cascade per character)

berak gravatar imageberak ( 2016-03-18 09:31:50 -0600 )edit

@berak isn't there any way to OCR a persian plate?!

Alireza7991 gravatar imageAlireza7991 ( 2016-03-18 10:00:52 -0600 )edit
1

idk. maybe. cascades are the wrong way.

berak gravatar imageberak ( 2016-03-18 10:46:11 -0600 )edit