Detecting DoG features and extracting SIFT descriptors

The preceding technique, which uses cv2.cornerHarris, is great for detecting corners and has a distinct advantage because even if the image is rotated corners are still the corners. However, if we scale an image to a smaller or larger size, some parts of the image may lose or even gain a corner quality.

For example, take a look at the following corner detections in an image of the F1 Italian Grand Prix track:

Figure 6.3: Corner detections in an image of the F1 Italian Grand Prix track

Here is the corner detection result with a smaller version of the same image:

Figure 6.4: Corner detections in a smaller image of the F1 Italian Grand Prix track

You will notice how the corners are a lot more condensed; however, even though we gained some corners, we lost others! In particular, let's examine the Variante Ascari chicane, which looks like a squiggle at the end of the part of the track that runs straight from northwest to southeast...