High-Level Vision Face Detection CS332 Visual Processing Department

High-Level Vision Face Detection CS332 Visual Processing Department

High-Level Vision Face Detection CS332 Visual Processing Department of Computer Science Wellesley College Face detection: Viola & Jones Multiple view-based classifiers based on simple features that best discriminate faces vs. non-faces Most discriminating features learned from thousands of samples of face and non-face image windows Attentional mechanism:

cascade of increasingly discriminating classifiers improves performance 1-2 Viola & Jones use simple features Use simple rectangle features: I(x,y) in gray area I(x,y) in white area within 24 x 24 image sub-windows initially consider 160,000 potential features per sub-window!

features computed very efficiently Which features best distinguish face vs. non-face? Learn most discriminating features from thousands of samples of face and non-face image windows 1-3 Learning the best features weak classifier using one feature: x = image window

f = feature p = +1 or -1 = threshold (x1,w1,1) normalize weights (xn,wn,0) n training samples,

equal weights, known classes find next best weak classifier final classifier AdaBoost use classification errors to update weights

~ 200 features yields good results for monolithic classifier 1-4 Attentional cascade of increasingly discriminating classifiers Early classifiers use a few highly discriminating features, low threshold 1st classifier uses two features, removes 50% non-face windows later classifiers distinguish harder

Increases efficiency examples Allows use of many more features Cascade of 38 classifiers, using ~6000 features 1-5 Training with normalized faces 5000 faces many more non-face patches faces are normalized for

scale & rotation small variation in pose Viola & Jones results With additional diagonal features, classifiers were created to handle image rotations and profile views 1-7 Faces everywhere...

Recently Viewed Presentations