Number of items in positive samples, haar cascade classifier

asked 2017-06-23 05:55:22 -0600

CV_open gravatar image

To create the haar cascade classifier, if I train it with images of only 1 object compared to many objects of the same class, will it be able to detect only that specific object that I trained it with or providing that there is not much variance within the class, will the resulting cascade classifier actually detect other objects within the class?

edit retag flag offensive close merge delete


in general, since you expect some variation in the real world, you need training images, which cover this variation. using a single image (or multiple synthetic images generated from that) will always be inferior to carefully modelling your situation with as many training images as possible.

berak gravatar imageberak ( 2017-06-24 01:14:59 -0600 )edit