Methods to identify licence plates on cars

asked 2016-02-01 21:09:35 -0500

Polyquin gravatar image

updated 2016-02-01 21:40:58 -0500

Hi all,

I've been checking a fair bit of Opencv code on the Internet. I noticed most of the code will first preprocess the image (e.g. binarize, apply edges filter) before sending to K nearest for character recognition.

Would it be possible to run K nearest to identify the vehicle (ie. trucks) followed by another K nearest for character recognition. Does it make sense?

edit retag flag offensive close merge delete

Comments

can it be you're confusing kmeans (cluster to n centers) with knn (k nearest neighbour search / classification) ?

berak gravatar imageberak ( 2016-02-01 21:12:51 -0500 )edit
1

Ah yes I was confused. I'll make the change.

Polyquin gravatar imagePolyquin ( 2016-02-01 21:40:11 -0500 )edit
1

in general, i think, you're on the right path, it just might be easier, to find licence plates instead of cars or trucks first

berak gravatar imageberak ( 2016-02-01 22:03:30 -0500 )edit

Ahh i was trying to cut down on the amount of OCR required, if I can recognise trucks first.

Polyquin gravatar imagePolyquin ( 2016-02-01 22:05:12 -0500 )edit

sure, that's reasonable, still it's easier to find a rectangular region of a certain size, than detecting if it's a car.

berak gravatar imageberak ( 2016-02-01 22:08:37 -0500 )edit
1

@berak, I am going through CS231n on youtube. I noticed the slides were saying k nearest neighbours are not good for images. FYI.

Polyquin gravatar imagePolyquin ( 2016-02-02 05:10:16 -0500 )edit

yea, knn is the most ptimitive classifier. svm , ann might be better

berak gravatar imageberak ( 2016-02-02 05:35:57 -0500 )edit

yea, knn is the most primitive classifier. svm , ann might be better

berak gravatar imageberak ( 2016-02-02 05:36:18 -0500 )edit