LBP based Face Detection
Hello, I have been trying to use trainCascade to train a LBP feature based face classifier. However, the accuracy is not good. The number of pos and neg for my training is more than the data\lbpcascades\lbpcascade_frontalface.xml. The description of lbpcascade_frontalface.xml is: number of positive samples 3000 number of negative samples 1500
Now I used 5000 pos and 5000 neg for training but the trained classifier is worse than the default lbpcascade_frontalface.xml.
What is the reason? Thx in advance.