Ask Your Question

Good feature extraction for handwritten characters using OpenCV python?

asked 2017-11-17 10:35:41 -0500

shebna12 gravatar image

I'm currently using the cv2.goodFeaturesToTrack() way. However, the corners it returns are somewhat vague and doesn't really do what i wanted wherein it would put some dots on the outline of the character. Here is an attached image of how it worked on my custom dataset: image description

corners = cv2.goodFeaturesToTrack(crop, 8, 0.02, 10)

If cv2.goodFeaturesToTrack() is not a good way of extracting features from handwritten characters, what are some of the better ways to do it? Thank you

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted

answered 2018-03-10 16:52:34 -0500

imad gravatar image

Hello , I think u can find ur answer here , am wroking in the same subject like you ( good luck )

edit flag offensive delete link more


  • how exactly does it answer the question ?
  • check your spelling, please.
berak gravatar imageberak ( 2018-03-10 17:00:53 -0500 )edit

in the link that i shared , there are above 20 function for feature extraction , and each one has a good result for specific type of data , in books and artical that am reading i found that wavelte method has the best result and there some other with good performance, but i can't find the implementation of it in opencv

imad gravatar imageimad ( 2018-03-10 17:08:37 -0500 )edit
  • use current documentation, please, like: ...

  • again, does it answer the problem above ?

  • only very few here were born with english as a first language, -- yet again - apply a spell-checker !

berak gravatar imageberak ( 2018-03-10 17:25:52 -0500 )edit
Login/Signup to Answer

Question Tools

1 follower


Asked: 2017-11-17 10:35:41 -0500

Seen: 626 times

Last updated: Nov 17 '17