Analyzing the results

This example presents a basic implementation that can be adapted in several cases, such as 3D object recognition, face recognition, or as a part of clustering analysis. The goal of this chapter is to present how we can easily compare vectors unsupervised in order to find the similarity between images. In this section, we will present seven cases and analyze the results. This result will help us understand the possibilities of this kind of algorithm, for example, for a drone to find a target even with variations in the color or the angle of the picture.

In the following screenshot, we can see the first three searches and we can observe high accuracy in the result; even in the case of a bus, the result displays the result elements in different angles, rotations, and colors:

In the following screenshot, we see the searches 4 (horse), 5 (flower), and 6 (elephant), and we can observe that in an image with good contrast in colors, the algorithm performs well:

In case of...