Identity Processing

From Robert-Depot
Revision as of 10:21, 29 September 2009 by Rtwomey (talk | contribs) (Face recognition)

Jump to: navigation, search

Identity Processing

Face detection

Active Appearance Models

Face recognition

PCA
Elastic Bunch Graph Matching (EBGM)
  1. Integer to float conversion - Converts 256 gray levels into floating point equivalents.
  2. Geometric normalization – Lines up human chosen eye coordinates.
  3. Masking – Crops the image using an elliptical mask and image borders such that only the face from forehead to chin and cheek to cheek is visible.
  4. Histogram equalization – Equalizes the histogram of the unmasked part of the image.
  5. Pixel normalization – scales the pixel values to have a mean of zero and a standard deviation of one.
  • default face normalization parameters from CSU FacePerf program:
#define ELLIPSE_X    65.0
#define ELLIPSE_Y    50.0
#define ELLIPSE_A    64.0
#define ELLIPSE_B    118.0

#define EDGE_PRE     0
#define EDGE_POST    0

#define EYE_LX       30.0
#define EYE_LY       45.0
#define EYE_RX       100.0
#define EYE_RY       45.0

#define SIZE_WIDTH   130
#define SIZE_HEIGHT  150

#define NOISE        0.0
#define SCALE        1.0
#define SHIFT_X      0.0
#define SHIFT_Y      0.0

#define HIST_NONE    0
#define HIST_PRE     1
#define HIST_POST    2