Contour Pick-Up and Registration of Infrared Images of Palm.

摘要

In this thesis an approach of Contour Pick-up and image registration is presented for infrared images of palm. Contour Pick-up is based on Gauss- Laplase kernel and image registration is implemented by their cross-correlation function. In order to use the temperature variety attained from the infrared images for diagnoses of metabolically diseases, man used to get the different time temperature of a certain area artificial point by point. It always wastes time and the data cannot be very accurate. This Thesis gives a method that avoids these disadvantages. First, the contour is picked up from the environment by using the convolution of Gauss-Laplase kernel. Then we filled inside the edge with darkness. Counting the max value of their cross-correlation function realize registration of the infrared images of palm. The results of experiment prove this method to be feasible.