Ask Your Question

OpenCV Haar-training

asked 2013-04-06 06:09:53 -0500

Shaky gravatar image

Need to detect Tiger faces in its natural habitat. Using inbuilt Haar-training (opencv_haartraining) feature to train the system but the performance is low. How to increase the hitrate while reducing the false alarm rate?

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted

answered 2013-04-06 11:47:48 -0500

More training and especially a better training of the background, by using more negatives is the first I should do. Secondly, try other classifiers, like SVM, random trees, ...

For more classifiers, check this link:

edit flag offensive delete link more


As the number of stages increases the hitrate as well as the false alarm rate increases. How to avoid this? Usage of 2200 negatives against 500 positives have been made, is that sufficient?? The OpenCV Haar training has an inbuilt cascade of weak classifiers with the Adaboost, how can we change this classifier?

Shaky gravatar imageShaky ( 2013-04-07 08:47:12 -0500 )edit

Basically a cascade classifier is made with boosting, like adaBoost. If you want another classifier, you just need to build a new system yourself. Steps to follow are for example :

  1. Calculate feature points of the image (SIFT or SURF)

  2. Create descriptors around those feature points

  3. Store desccriptors in a codebook

  4. Create a SM classifier with this data

Basically you need to google these items and read, so that you understand what happens!

StevenPuttemans gravatar imageStevenPuttemans ( 2013-04-07 11:11:11 -0500 )edit
Login/Signup to Answer

Question Tools


Asked: 2013-04-06 06:09:53 -0500

Seen: 464 times

Last updated: Apr 06 '13