Ask Your Question
1

LBP based Face Detection

asked 2012-11-10 04:33:21 -0600

this post is marked as community wiki

This post is a wiki. Anyone with karma >50 is welcome to improve it.

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.

edit retag flag offensive close merge delete

1 answer

Sort by ยป oldest newest most voted
2

answered 2012-11-27 05:00:11 -0600

this post is marked as community wiki

This post is a wiki. Anyone with karma >50 is welcome to improve it.

Hi, I have trained LBP classifiers with my own code, and not using the OpenCV version. I have used nearly 10,000 face images in my training set. The negative patterns are collected on the fly after each stage. I had to give more that 10,000 images with no faces, otherwise the later stages were not able to find the false positives. The number of features for each stage that I used were, 5, 10, 15, 25, 50, and the resulting classifier was very good, comparable to other detectors available.

You need to check the number of features given to each stage, and also you might require many more negative image files. Check modified LBP and extended LBP papers if you want to have a better feel for LBP features and face detection.

edit flag offensive delete link more

Comments

Hello @venky, how do you specify the number of feature to use at each stage? I could not see this in the documentation. http://docs.opencv.org/doc/user_guide/ug_traincascade.html

_Robert gravatar image_Robert ( 2013-10-17 17:21:02 -0600 )edit

Can you please provide some link on LBP papers or documents that gives a better understanding of features and face detection?

mainul gravatar imagemainul ( 2014-03-21 10:40:07 -0600 )edit

Question Tools

Stats

Asked: 2012-11-10 04:33:21 -0600

Seen: 1,576 times

Last updated: Apr 11 '13