19-11-2012, 05:36 PM
OpenCV + Face Detection
facedetect.pdf (Size: 913.05 KB / Downloads: 255)
introduction
Open source computer vision library written in C/C+
+, created and maintained by Intel
Cross-platform and extremely portable
Targeted for real-time applications
Functionality Overview
“Smart” windows
Image I/O, rendering
Processing keyboard and other events,
timeouts
Trackbars
Mouse callbacks
Video I/O
Creating a face detector
Original Viola-Jones paper (CVPR, 2001)
Collection of training images, positives and negatives
Run AdaBoost to distill a set of Haar-like features
which give good classifiers
Combine the yielded classifiers appropriately into a
cascade
Good news – OpenCV comes with an implementation of Viola-Jones!
A good reference -
Three tools to use – “createsamples”, “haartraining” and
“performance”
createsamples
Tool from OpenCV to automate creation of training samples
Four functionalities
1. create training samples from one image applying distortions
2. create training samples from from a collection of images,
without distortions
3. create testing samples with ground truth from one image
applying distortions
4. show images from the .vec internal format which contains a
collection of samples
Best to use a combination of the functionalities to create many
samples from many images with distortions and merge them