Slide 1

Caifeng Shan, Member, IEEE IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 21, NO. 1, JANUARY 2012

Slide 2

INTRODUCTION METHOD EXPERIMENTS

Slide 3

INTRODUCTION METHOD EXPERIMENTS

Slide 4

Most of the existing works have been focused on analyzing a set of prototypic emotional facial expressions Using the data collected by asking subjects to pose deliberately these expressions In this paper, we focus on smile detection in face images captured in real-world scenarios

Slide 5

Slide 6

INTRODUCTION METHOD EXPERIMENTS

Slide 7

BOOSTING PIXEL DIFFERENCES S. Baluja and H. A. Rowley, Boosting set identification performance,Int. J. Comput. Vis., vol. 71, no. 1, pp. 111119, 2007 Baluja introduced to use the relationship between two pixels intensities as features.

Slide 8

they used five types of pixel comparison operators (and their inverses):

Slide 9

The binary result of each comparison, which is represented numerically as 1 or 0, is used as the feature. Thus, for an image of pixels, there are or 3312000 pixel- comparison features

Slide 10

Instead of utilizing the above comparison operators, we propose to use the intensity difference between two pixels as a simple feature For an image of 24*24 pixels, there are or 331200 features extracted

Slide 11

AdaBoost ( Adaptive Boosting ) AdaBoost learns a small number of weak classifiers whose performance is just better than random guessing and boosts them iteratively into a strong classifier of higher accuracy the weak classifier consists of feature (i.e., the intensity difference),threshold, and parity indicating the direction of the inequality sign as follows:

Slide 12

Slide 13

Slide 14

INTRODUCTION METHOD EXPERIMENTS

Slide 15

Data Database : GENKI4K consists of 4000 images (2162 smile and 1828 nonsmile) In our experiments, the images were converted to grayscale the faces were normalized to reach a canonical face of 48*48 pixels

Slide 16

Data

Slide 17

Illumination Normalization Histogram equalization (HE) Single-scale retinex (SSR) Discrete cosine transform (DCT) LBP TanTriggs

Slide 18

Illumination Normalization

Slide 19

Boosting Pixel Intensity Differences Average of (left) all smile faces and (right) all nonsmile faces

Slide 20

Impact of Pose Variation

Slide 21

Slide 22

Thank you