Ask Your Question
1

Classification using SVM

asked 2014-04-25 13:55:19 -0600

kubag gravatar image

updated 2014-04-25 13:56:27 -0600

berak gravatar image

I have problem with classification using SVM. Let's say that I have 10 classes, digts from 0 to 9 (or some kind of symbols). I can train SVM to recognize theese classes, but sometimes I get image which is not digt, but SVM still tries to categorize this image. Is there a way to set threshold for SVM on the output maybe (as I can set it for Neural Networks) to reject bad images? May I ask for code sample (in C++ or Python with opencv)? Thanks in advance.

edit retag flag offensive close merge delete

Comments

As suggested in several topics before you could use the distance to the decision plane as a score for how good your SVM is classifying. This means the larger the value, the more certain you are that the element is assigned to that specific class. Use that value to threshold and only keep the most certain predictions?

StevenPuttemans gravatar imageStevenPuttemans ( 2014-10-20 05:49:47 -0600 )edit

1 answer

Sort by ยป oldest newest most voted
0

answered 2014-10-18 21:48:58 -0600

Maybe you could train the caegory which isn't digt the 11th catogory, or use a two step SVM the filter them

edit flag offensive delete link more

Question Tools

1 follower

Stats

Asked: 2014-04-25 13:55:19 -0600

Seen: 356 times

Last updated: Oct 18 '14