Face Detection
The primary objective is to be able to detect faces and also analysis the facial feature and expression so as to identify attributes such as gender, smile, age of people and also whether the person is wearing glasses.

Approach
OpenCV library is used to detect and segment faces from video images:1.Using a cascade of boosted classifiers working with haar-like features.2.Training classifiers by a database of face and non-face images.3.Input images are scanned at different scales to find regions that are likely to contain faces.

The pictures below show the result of face detection.

Gender | Glasses | Smile Detection
We use the SVM classifier method: data points are dealt with as a p-dimensional vector. We use the library LibSVM.

The pictures below shows the different stages of the image processing:

1.Segment out face rectangle
2.Scale to 24*24 grayscale image
3.Equalize histogram to increase contrast
4.Scale the intensity to [-1, 1]
5.Form a 576 (24x24) dimensional vector
6.Train the gender model with LIBSVM.

The three face databases we use are:

FERET database:

Gender Detection

1.Database
FERET http://www.nist.gov/humanid/colorferet
FA | FB | QR | QL | HL | HR

2.Rate of accuracy
FB(dvd2) : 246/268 = 91.791%

Glasses Detection

1.Database
FERET (FA | FB | QR | QL)
GENKI
WWW (from internet)

2.Rate of AccuracyDatabase
FB(dvd2) : 248/268 = 92.5373 %

Smile Detection

1.Database
GENKI http://mplab.ucsd.edu, The MPLab GENKI-4K Dataset

2.Rate of Accuracy
GENKI
File2113.jpg – file2440.jpg : 278/323 = 86.0681%
File2000.jpg – file2500.jpg : 417/492 = 84.7561%

3.Result is better when tested with webcams.

Future work
Age Estimation

1.Using PCA to get the age vector( facial features of every age )
2.Extract the wrinkle features using edge detection and then using classifier to separate people of different ages