Haar Cascades vs. LBP Cascades in Face Detection [closed]

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.

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.

An LBP cascade can be trained to perform similarly (or better) than the Haar cascade, but out of the box, the Haar cascade is about 3x slower, and depending on your data, about 1-2% better at accurately detecting the location of a face. This increase in accuracy is quite significant given that face detection can operate in the 95%+ accuracy range.

Below are some results when using the MUCT dataset.

A correct detection is noted when there is at least a 50% overlap between the ground-truth and OpenCV detected coordinates.

Cascade:haarcascade_frontalface_alt2.xml
Datafile:muct.csv
|---------------------------------------------------|
|   Hits  |  Misses  | False Detects  | Multi-hit   |
|  3635   |   55     |   63           |    5        |
|---------------------------------------------------|
Time:4m2.060s

vs:

Cascade:lbpcascade_frontalface.xml
Datafile:muct.csv
|---------------------------------------------------|
|   Hits  |  Misses  | False Detects  | Multi-hit   |
| 3569    |  106     |   77           |    3        |
|---------------------------------------------------|
Time:1m12.511s