0

I went through the Gender classification tutorial from openCV, http://docs.opencv.org/modules/contrib/doc/facerec/tutorial/facerec_gender_classification.html. I need to do emotion classification for which they say, "If you want to do emotion classification instead of gender classification, all you need to do is to update is your training data and the configuration you pass to the demo" . I used a dataset with 16 images each for happy and sad emotions. Happy dataset includes faces of happy men,women,kids and elders. Similarly sad dataset as well. But when I tested this on 4 images all 4 went wrong. What other changes should I do apart from the dataset as said in the link by, "configurations you pass to the demo". What configurations should I change from the gender classification example facerec_fisherfaces.cpp? I am new to OpenCV. Please help.

AnOldSoul
  • 4,017
  • 12
  • 57
  • 118
  • Can you update your link? The text was truncated. – Mark Miller Jul 06 '15 at 14:40
  • I assume by changing the data you also have changed the CSV files too? – Mark Miller Jul 08 '15 at 17:33
  • Also, the recognizer will not be accurate if the images are not the same size, the faces are not towards the camera, or the faces are not aligned well. It appears these are all the parameters [the "configurations you pass to the demo"], because the detection is merely using eigenvectors. – Mark Miller Jul 08 '15 at 17:38

1 Answers1

0

You will need atleast 200 images per emotion class. 16 images is not enough. Download some image dataset and use that and try. No need of changing any config data.

Kalpa-W
  • 348
  • 3
  • 22