Object detection
Presented by Minh Hoai Nguyen
Date: 28 March 2007
Object detection?
What we want
Miss a face!
Happy face!
Scanning window
Train a classifier on a
fixed size window
Outline
• Object Detection Using the Statistics of
Parts
– Schneiderman, H. & Kanade, T. CVPR00, IJCCV04
• Robust Real-time Face Detection
– Viola, P. & Jones, M. CVPR01, IJCV04
Bayes optimal classifier
• Image is defined by n attrs: x1,x2,…,xn
P(Object | x1 ,..., xn )
 ?1
P(Object | x1 ,..., xn )
P( x1 ,..., xn | Object ) P(Object )
 ?1
P( x1 ,..., xn | Object ) P(Object )

P( x1 ,..., xn | Object )
P(Object )
?
P( x1 ,..., xn | Object )
P(Object )
There are too many
parameters to learn
Naïve Bayes Assumption
• Assume: x1,x2,…,xn are cond. independent.
P( x1 ,..., xn | Object )
 P( xi | Object )

P( x1 ,..., xn | Object )  P( xi | Object )
Easier
to learn
• Problem: this might be a bad assumption
• Idea:
– Carefully divide x1,x2,…,xn into groups: P1, P2,…, Pk
– Assume P1, P2,…, Pk are independent
P ( x1 ,..., xn | Object )
P ( Pi | Object )

P ( x1 ,..., xn | Object )
P ( Pi | Object )
Independent groups/parts
• How to divide x1,x2,…,xn into ind. groups?
• Image pixels are highly correlated.
• Represent image by Wavelets instead.
Wavelet transform
10 filter responses for
each original pixel.
HL
LH
HH
• Wavelet transform is fully invertible.
• Partially de-correlate natural imagery
– More independence, easier to design parts
Designing parts
• Assumption:
– Each wavelet coefficient only depends on few
others.
– Group those coefficients into parts.
• Parts:
– 17 types, manually defined.
– Each part contains 8 coefficients.
Categories of parts
Intra-subband
Interfrequency
Local operator
Local operator
“Parts”
Inter-orientation
Local operator
Inter-frequency/
Inter-orientation
Local operator
Slide credit: Nicholas Chan
Final form of detector
How to compute these
statistics?
Count!
Multiple poses?
• Other tricks:
– Not going to talk about.
Reported results for faces
• Kodak dataset:
– Test set: 17 images, 46 faces, 36 profile views.
A bigger dataset
• From multiple sources 208 images, 441
faces, about 347 profiles.
Robust Real-time Face Detection
by Viola,P. & Jones, M.
Cascade of classifiers
• Most places do not have faces!
Simple features
Box filters
Approximation of
Harr-wavelets
Integral image
Feature evaluation can
be done by few lookups
Learning the cascade
• AdaBoost
– Weak classifiers are box filters
Learning cascade stages
• Using AdaBoost to train each stage:
– Adjust threshold to minimize false negatives.
– Adding features until target detection and
false positive rates are met (determined by
CV)
Learned cascade
• First classifier:
– 2 features
– 100% detection
– 40% false
detection
• The whole cascade:
– 38 stages
– 6000 features in total
– On dataset with 507 faces and 75 millions sub-windows, faces
are detected using 10 feature evaluations on average.
– On average, 10 feature evals/sub-window
Reported ROC curve
Comparison results
The end