Identity Processing
From Robert-Depot
Contents
Identity Processing
Face detection
- with opencv: http://opencv.willowgarage.com/wiki/FaceDetection
- Picasa Face Detection and Tagging
Active Appearance Models
- AAM-API c++ - http://www2.imm.dtu.dk/~aam/
Face recognition
- http://info.polarrose.com/features/
- PittPatt http://www.pittpatt.com/
- good paper http://www.cs.colostate.edu/~vision/faceperf/Bolme_IISWC2007.pdf
PCA
- already done! http://svn.roberttwomey.com/of/faceRecTest
Elastic Bunch Graph Matching (EBGM)
- Download csu FacePerf software: http://www.cs.colostate.edu/~ross/downloads/csuFaceIdEval5.tgz
- normalization schedule:
- Integer to float conversion - Converts 256 gray levels into floating point equivalents.
- Geometric normalization – Lines up human chosen eye coordinates.
- 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.
- Histogram equalization – Equalizes the histogram of the unmasked part of the image.
- 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