Viola Jones Technique and Adaboost Classification

Viola/Jones Face Detector

Is a seminal approach to real-time object detection

Detection is very fast

Key ideas

Integral images for fast feature evaluation

Boosting for feature selection

Attentional cascade for fast rejection of non-face windows

Value = ∑ (pixels in white area) –∑ (pixels in black area)

Fast computation with integral images

The integral image computes a value at each pixel (x,y) that is the sum of the pixel values above and to the left of (x,y), inclusive

This can quickly be computed in one pass through the image

Computing sum within a rectangle

Let A,B,C,D be the values of the integral image at the corners of a rectangle

Then the sum of original image values within the rectangle can be computed as:

  sum = A – B – C + D

Only 3 additions are required for any size of rectangle

Haar like features



Feature selection

For a 24x24 detection region, the number of possible rectangle features is ~160,000!

Boosting

Boosting is a classification scheme that combines weak learners into a more accurate ensemble classifier

Training procedure

In each boosting round:

Find the weak learner that achieves the lowest weighted training error

Raise the weights of training examples misclassified by current weak learner

Then compute final classifier as linear combination of all weak learners

Advantages of boosting

Integrates classifier training with feature selection

Complexity of training is linear instead of quadratic in the number of training examples

Flexibility in the choice of weak learners, boosting scheme

Testing is fast

Easy to implement