Page 146 - Algorithm Collections for Digital Signal Processing Applications using MATLAB

Chapter 4

SELECTED APPLICATIONS
Algorithm Collections

1. EAR PATTERN RECOGNITION USING
EIGEN EAR

Ear pattern recognition is the process of classifying the unknown ear image
as one among the finite category. The following is the report on the
experiment done on ear pattern recognition with the small database. The
experiment uses twelve ear images collected from four persons. Three
images are collected from each person. Among them, eight images are used
to train the classifier. Remaining four images are used to test the classifier.
The steps involved in Ear pattern recognition using Eigen ears are
summarized below.

1.1 Algorithm

Step 1: Mean and variance of the collected ear images are made almost
equal using mean and variance normalization technique described in
the section 3-5. Mean and variance of one of the image from the
collections is treated as desired mean and desired variance. (See
figure 4-1)

135