Algorithm 1 proposed HAG-MSF-CRFs algorithm

Input:M${}_{train}$ = {(I${}_n$,T${}_n$)}${}_{n=1}^m$, M${}_{test}$.

where M${}_{train}$ is the data used for training model $\mathfrak{A}$, M${}_{test}$ is the testing data, I is the input training image and T(i,j)∈ {1,2,3,4,5,6} is the ground truth data.

a: Face segmentation part:

Step a.1: Training a segmentation model $\mathfrak{A}$ through training data (training images and labels)

Step a.2: Finding the center of each super-pixel, extracting patches and passing to the model $\mathfrak{A}$

Step a.3: Using the probabilistic classification method and creating probability maps for each class, represented as:

p${}_{skin}$, p${}_{mouth}$, p${}_{eyes}$, p${}_{nose}$, p${}_{hair}$, and p${}_{back}$

b. Head pose, age and gender classification part:

if head pose estimation:

$f=$p${}_{skin}$ + p${}_{mouth}$ + p${}_{eyes}$ + p${}_{nose}$ + p${}_{hair}$

Else if age classification:

$f=$p${}_{skin}$ + p${}_{mouth}$ + p${}_{eyes}$ + p${}_{nose}$ + p${}_{hair}$

Else if gender recognition:

$f=$p${}_{skin}$ + p${}_{eyes}$ + p${}_{nose}$ + p${}_{hair}$

where f is the feature vector.

c. Training an RDF classifier for each case (head pose, age and gender)

Output: estimated pose, age class and gender.