Haar Cascades vs. LBP Cascades in Face Detection

opencv cascade face-detection haar-wavelet viola-jones
Bojoeb picture Bojoeb · Jan 9, 2012 · Viewed 52.7k times · Source

I have been experimenting with face detection in OpenCV (Open Source Computer Vision Library), and found that one could use Haar cascades to detect faces as there are several of them provided with OpenCV. However, I have noticed that there are also several LBP cascades. After doing some research, I found that LBP stands for Local Binary Patterns, and it can also be used for face detection, according to the OpenCV Face Detection Documentation.

What I would like to know is, which works better? Which one performs faster, and which one is more accurate? It seems that LBP performs faster, but I'm not 100% sure about that either. Thanks.

Answer

Sam picture Sam · Jan 9, 2012

LBP is faster (a few times faster) but less accurate. (10-20% less than Haar).

If you want to detect faces on an embedded system, LBP is the default choice, because it does its calculations in integers.

Haar uses floats for processing, which have poorer support on embedded and mobile processors; as a result, the performance penalty is significant - big enough to make its usage on mobile phones impractical.

Related questions

Cannot find module cv2 when using OpenCV

I have installed OpenCV on the Occidentalis operating system (a variant of Raspbian) on a Raspberry Pi, using jayrambhia's script found here. It installed version 2.4.5. When I try import cv2 in a Python program, I get the following message: pi@…

Read More
How do I install Python OpenCV through Conda?

I'm trying to install OpenCV for Python through Anaconda, but I can't seem to figure this out. I tried conda install opencv conda install cv2 I also tried searching conda search cv No cigar. I ran across this which lists …

Read More
How to crop an image in OpenCV using Python

How can I crop images, like I've done before in PIL, using OpenCV. Working example on PIL im = Image.open('0.png').convert('L') im = im.crop((1, 1, 98, 33)) im.save('_0.png') But how I can do it on OpenCV? This …

Read More