2
$\begingroup$

I have a database that consists of PHOG and LPQ features for each image. Now, I wish to train an SVM on these features for emotion recognition i.e SVM classifies the images on basis of emotion in the image.

Please provide a detailed procedure on how to use these features to train SVM.

Improve this question
$\endgroup$
2
  • $\begingroup$ It's hard to know how to answer this. What specifically are you uncertain about? What research have you done, and what approaches have you considered? What are you unsure about? Right now it's not clear what is preventing you from knowing how to do this on your own, so it's not clear how to help you. Please edit the question to tell us what approaches you've considered and why you've rejected them. The obvious answer is "just do it"; those are your features; now train a SVM on a training set, and see how it works. Have you tried it? Do you have some specific concern or uncertainty? $\endgroup$
    – D.W. ♦
    Commented Nov 6, 2016 at 18:24
  • $\begingroup$ See also cs.stackexchange.com/help/how-to-ask $\endgroup$
    – D.W. ♦
    Commented Nov 6, 2016 at 18:24

1 Answer 1

Reset to default
2
$\begingroup$

To train your SVM inevitably you need some baseline, which can be accquired from FERA 2011 contest. The whole procedure using this data is described in Emotion Recognition Using PHOG and LPQ features by Abhinav Dhall, Akshay Asthana, Roland Goecke and Tom Gedeon. After reading that there is a follow up FERA 2015.

Improve this answer
$\endgroup$
1
  • $\begingroup$ I am sorry for mainly links and references but the procedure is very vast (too broad to sum it up) and well described already. $\endgroup$
    – Evil
    Commented Nov 6, 2016 at 18:53

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.