FACE DETECTION AND RECOGNITION By: Paranjith Singh Lohiya Ravi Babu Lavu.

16
FACE DETECTION AND RECOGNITION By: Paranjith Singh Lohiya Ravi Babu Lavu

Transcript of FACE DETECTION AND RECOGNITION By: Paranjith Singh Lohiya Ravi Babu Lavu.

FACE DETECTION AND RECOGNITION

By:

Paranjith Singh Lohiya

Ravi Babu Lavu

OVERVIEW

• Robust – very high Detection Rate (True-Positive Rate) & very low False-Positive Rate… always.

• Real Time – For practical applications at least 2 frames per second must be processed.

• Face Detection – not recognition. The goal is to distinguish faces from non-faces (face detection is the first step in the identification process)

MEASURES TOWARDS SPEEDING UP DETECTION RATE

• Integral image: a fast way to compute simple “features”

• In Adaboost the weak learner is nothing but a feature selector. The advantage is that if there are N weak learners there are merely N features to compute.

• Cascaded combination of classifiers. Most of true negatives are rejected very fast at the at the first few stages. Can keep high detection rate and low false positive rate.

IMAGE FEATURES

• Rectangle filters

• Similar to Haar wavelets

• Base resolution is 24-by-24

• 11 scales, scaling factor of 1.25

• 45396 features

COMPUTING FEATURES USING INTEGRAL IMAGE

• Can a simple feature (i.e. a value) indicate the existence of a face?

• All faces share some similar properties

• The eyes region is darker than the upper-cheeks.

• The nose bridge region is brighter than the eyes.

• That is useful domain knowledge

• Need for encoding of Domain Knowledge:

• Location - Size: eyes & nose bridge region

• Value: darker / brighter

COMPUTING INTEGRAL IMAGE

• Integral image value at a pixel (x, y) is the sum of the pixel values of the original image above and to the left of (x, y), inclusive.

• Integral image can be computed by one pass through the image

INTEGRAL IMAGE FOR COMPUTING SUM WITHIN A RECTANGLE

• The sum of the pixels within rectangle D can be computed with four array references.

• The value of the integral image at location 1 is the sum of the pixels in rectangle A.

• The value at location 2 is A + B, at location 3 is A + C, and at location 4 is A + B + C + D.

• The sum within D can be computed as 4 + 1 - (2 + 3).

ADABOOST

• Stands for “Adaptive” boost

• Constructs a “strong” classifier as a linear combination of weighted simple “weak” classifiers

Strong classifier

Weak classifier

WeightImage

ADABOOST LEARNING ALGORITHM

ADABOOST ALORITHM CHARACTERISTICS

• Features as weak classifiers • Each single rectangle feature may be regarded as a simple weak

classifier

• An iterative algorithm• AdaBoost performs a series of trials, each time selecting a new

weak classifier

• Weights are being applied over the set of the example images

• During each iteration, each example/image receives a weight determining its importance

PERFORMANCE WHILE CASCADING CLASSIFIERS

• For K stages of cascading with each stage having fi as the false positive rate, the overall false positive rate for the cascade is

• Similarly, the overall detection rate is

• To keep F very low and D very high, for each stage the goal is to have very high detection rate (close to 100%), but moderate false positive rate (say, 30%)

K

iifF

1

K

iidD

1

CASCADED CLASSIFIER

• A 1 feature classifier achieves 100% detection rate and about 50% false positive rate.

• A 5 feature classifier achieves 100% detection rate and 40% false positive rate (20% cumulative)

• using data from previous stage.

• A 20 feature classifier achieve 100% detection rate with 10% false positive rate (2% cumulative)

1 Feature 5 Features

F

50%20 Features

20% 2%

FACE

NON-FACE

F

NON-FACE

F

NON-FACE

IMAGESUB-WINDOW

LABELED DATA

• Training Data• 4916 hand labeled faces

• All frontal

• 10000 non faces

• Faces are normalized

• Scale, translation

• Many variations• Across individuals

• Illumination

• Pose (rotation both in plane and out)

CONCLUSION

• A set of experiments in the domain of face detection are presented which yields face detection performance comparable to the best previous systems.

• This system is about 15 times faster than the previously implemented detection system and this increase in speed will enable real time face detection applications on systems where they were previously infeasible.

• Scaling can also be achieved by scaling the detector itself, rather than scaling the image.

OUTPUT OF FACE DETECTOR ON TEST IMAGES

THANK YOU