Download presentation
Presentation is loading. Please wait.
Published byGilbert Merritt Modified over 9 years ago
1
F ACE D ETECTION FOR A CCESS C ONTROL By Dmitri De Klerk Supervisor: James Connan
2
O VERVIEW Haar-like features For the task of face detection AdaBoost Approach AdaBoost Weak or Base learning algorithm Training image weights Strong classifier Detection example Cascade classifier Tools and languages Face detection demo References Question & Answers
3
H AAR - LIKE FEATURES Our object detection procedure classifies images based on the value of simple features. There are three kinds of Haar-Like features Two-rectangle feature: Difference between the sum of the pixels within two rectangular regions. Three-rectangle feature: The sum of the pixels within two outside rectangles subtracted from the sum in a center rectangle. Four-rectangle feature: The difference between diagonal pairs of rectangles. If this value is above a threshold (set during learning). that feature is said to be present.
4
F OR THE TASK OF FACE DETECTION Say we have a database of images… Where images are labeled ‘+1’ if it’s a face and ‘-1’ otherwise. Our goal is: given a new image, find its label., +1, -1
5
A DA B OOST APPROACH Gather as many examples as possible of both faces and non-faces. Feed these examples together with labels indicating if their faces of not, to AdaBoost. AdaBoost will then produce a classification or prediction rule (WEAK CLASSIFIER). Given a new, unlabeled image, such a rule attempts to predict if it’s a face or not. The goal, is to generate the most accurate prediction possible on new images.
6
A DA B OOST APPROACH ( CONTINUED ) Building a highly accurate prediction rule is a difficult task. On the other hand, it is not hard at all to come up with very rough rules of thumb. An example of such a rule: Sure a rule like this will not come close to covering all faces… On the other hand, this rule makes prediction that are significantly better than random guessing. Ifis present, then predict it’s a face.
7
A DA B OOST AdaBoost – Ada ptive Boost ing Boosting is based on the observation that finding many rough rules of thumb can be a lot easier than finding a single highly accurate prediction rule. And producing a very accurate prediction rule by combining very rough inaccurate rules of thumb. Boosting algorithms combine weak classifiers in a meaningful way (Schapire ‘89).
8
W EAK OR B ASE LEARNING ALGORITHM The boosting algorithm calls the “weak” or “base” learning algorithm repeatedly. Which produces weak classifiers (rule of thumb). Each time feeding a different subset of the training examples. More precisely, a different distribution or weighting over the training examples. E.g. Weak or Base Learner
9
So how does AdaBoost use this “weak” algorithm? And how does it combine these weak classifiers into a “ strong classifier ”, highly accurate prediction rule? But if you had a whole lot of these weak classifiers, and each one " pushed " the final answer a little bit in the right direction, you'd have a strong, combined force for arriving at the correct solution. How to achieve this?
10
T RAINING IMAGE WEIGHTS Each training images is assigned a weight. Start with a uniform distribution(“weights”) over training images. The weight tell the “Weak” algorithm, which examples are important. Obtain a weak classifier from the “Weak” algorithm, based on the training images weights. Increase the weights on training images in which the weak classifier is not present in. Decrease the weights on the training images in which the weak classifier is present in. Repeat T times. By doing this subsequent weak classifier will focus on different subsets of the training images.
11
S TRONG CLASSIFIER h(x) = 1 0 ∑ (weight weak classifier ) ≥ ½(∑ (weight weak classifier ) ) otherwise If half of the total weight of weak classifiers are present. Then predict, the image is a face.
12
D ETECTION EXAMPLE h 3 ( ) = +3 contains the weak classifier 0 otherwise h 2 ( ) = +4 contains the weak classifier 0 otherwise h 1 ( ) = +3 contains the weak classifier 0 otherwise f( ) = sign[3 h 1 ( ) + 4 h 2 ( ) + 3 h 3 ( )] present not-present = 3 + 4 + 0 = 7 ≥ 5 The images is a face.
13
C ASCADE CLASSIFIER Viola and Jones combined a series of weak classifiers as a cascade. If an image fails any stage. The image is immediately classified as “Not Face” If the image makes it through all the stages. The images is classified as a “Face”. Reasons for using the cascade classifier make the detector faster.
14
T OOLS AND L ANGUAGES entire spectrum of the project. Walk us through the entire project, from requirements, analysis, interface, design, implementation, but spend roughly half of the talk discussing the test issues and results. User's Guide looks like Give a demo
15
F ACE DETECTION DEMO
16
R EFERENCES AdaBoost http://en.wikipedia.org/wiki/AdaBoost Builds on the work of Desmond Van Wyk Face Recognition System for Access Control (2006) How face detection work http://www.cognotics.com/opencv/servo_2007_series/part_2/sid ebar.html http://www.cognotics.com/opencv/servo_2007_series/part_2/sid ebar.html Fast Face Detection Using AdaBoost Julien Meynet [16 July 2003] The Boosting Approach to Machine Learning – An overview Robert E. Schapire [19 December 2001]
17
Q UESTIONS AND A NSWERS Thank you!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.