AGE ESTIMATION: A CLASSIFICATION PROBLEM. HANDE ALEMDAR, BERNA ALTINEL, NEŞE ALYÜZ, SERHAN DANİŞ. Project Overview. Subset Overview. Aging Subset of Bosphorus Database: 1-4 neutral and frontal 2D images of subjects 105 subjects Total of 298 scans Age range: [18-60]
HANDE ALEMDAR, BERNA ALTINEL, NEŞE ALYÜZ, SERHAN DANİŞ
The essential manifold structure preserved by measuring local neighborhood distances
X Size of training data for OLPP should be LARGE enough
based on neighborhood information
Neighborhood information is preserved
measures local density around a sample point
with the constraint :
=> Minimizing this function: ensure that if xi and xj are close then their projections yi and yj are also close
Not symmetric, therefore the basis functions are not orthogonal
(1) Preprocessing: PCA projection
(2) Constructing the Adjacency Graph
(3) Choosing the Locality Weights
(4) Computing the Orthogonal Basis Functions
(5) OLPP Embedding
with the greatest eigenvalue
A set of Gabor filters with different frequencies and orientations may be helpful for extracting useful features from an image.
We used 6 different rotations and 4 different scales on 16 overlapping patches of the images.
We generate 768 features for each image.Gabor Filter
Estimate age, just based on the average value of the training set
The K-nearest-neighbor (KNN) algorithm measures the distance between a query scenario and a set of scenarios in the data set.
Experiments #2K-nearest-neighbor algorithm
2. Normalization can be applied:POSSIBLE FUTURE WORK ITEMS: