Biomedical Engineering Reference
In-Depth Information
The k-means algorithm is applied iteratively, since the calculation of the centroid
location can vary the associated points. The algorithm converges if centroids location
does not vary. Each tree level represents a node division of the nearby superior stage.
The initial number of clusters is defined by 10, with 5 tree levels. These values
have shown good results, working with the actual database.
A model of a vocabulary tree with 2 levels and 3 initial clusters is shown in figure 3.
3
Experimental Settings
3.1
Databases Used
Authors have built an image database in order to develop this work. This database
contains 738 images of 704×756 pixels and 24 bit per pixel using a SAT-S280 SATIR
camera, which contains two sensors, one of them is a thermal sensor and another is a
visible camera. An example of that image is observed on figure 4.
Fig. 4.
Example of image from our visible and thermal camera
Our database is composed by 41 subjects, corresponding to 18 images per subject,
acquired in 3 different sessions, 6 images per session, during one month. These im-
ages are composed by two images, visible and thermal image, as it is observed in
figure 4. We have divided that image in two parts, and we have got 1476 images, 738
visible face images and 738 thermal facial images. In particular, false thermal colour
is given for the sensor according to characteristics of each person. All images have
been stored in PNG format. Besides, after segmentation process, we have equally split
in two sets of 738 images with different modalities: face and head. Therefore, the
images are divided into categories depending on the type of information they provide,
having a total of 2952 images:
•
Heads: Thermal images of full heads of subjects (738 images).
•
Heads: Visible images of full heads of subjects (738 images).
•
Faces: Thermal images of facial details. (738 images).
•
Faces: Visible images of facial details. (738 images).
The following figures present some examples of thermal and visible images of heads
(in figure 5) and faces (in figure 6) with the specified format.
Search WWH ::
Custom Search