[attachment=11461]
Progress
 Understanding of related material is completed.
 Beginning of implementation has begun
DF-LDA Algorithm
The output are the Optimal Discriminant Features (ODF) which will be projected onto the DF-LDA based subspace.
The basic idea of complex mathematical computations in order To reduce the dimensions is to obtain better classification. The F-LDA step is incorporated in the case of closed classes to obtain the required ODF’s.
Feret Dataset
 Feret Dataset consists of facial images at different angles which are not normalized. Also includes data files which have feature data points (ground truths).
 Feature data points – includes x, y-axis locations of facial features such as left and right eyes, nose, and center of mouth.
Implementation preprocessing image files
 Each image in Feret dataset are bzipped and and in tiff image format.
 Using a simple batch script to unzip the files and convert tiff image files to PGM format using convert function from ImageMagick 5.5.7.
Implementation creating eye-coordinates file
 Each image in Feret has an associated .gnd file which lists feature data points.
 Perl script is used to extract left and right eye coordinates from each .gnd file and placed into an one eye coordinate file which lists image name and eye-coordinates.
Implementation normalization
 Normalization is done by reading each line in the eye coordinates file.
 These are the steps for normalization [4]:
 The image is scaled so as to make the distance between the eye's constant. In this step, the image is also cropped to a smaller size that will include essentially just the face. The standard FERET normalization crops the image to 150x130 pixels with 70 pixels between the centers of the eyes.
 A mask is applied that zeroes out pixels not in an oval that contains the typical face. Thus, hair, shirt collars, etc. are typically removed. The mask is generated analytically by specifying the dimensions of the masking oval.
 Histogram equalization is used to smooth the distribution of grey values for the non-masked pixels.
 The image is normalized so the non-masked pixels have mean zero and standard deviation one.
Implementation Image Lists
 Image Lists is a file which lists on each line the same-class normalized images.
 Using Perl, we parse the directory list of normalized images and create this file.
 This image list is a reference for training to know which images belong to a single class
Implementation What's next?
 Need to implement the DF-LDA algorithm for training using normalized files.
 Experimentation and Analysis of results.