Published in


[CV] 11. Scale-Invariant Local Feature Extraction(1): Auto Scale Selection

1. Motivation: Why scale-invariant?

Figure 1. Why the scale invariance is important, from [2]

2. Fundamentals to Scale-Invariant Detectors.

2.1 From point to region

Figure 2. Detected point of interest and its corresponding defined region
Figure 3. Comparison of two feature representations extracted from regions of different images, from [1, 10]
Figure 4. Example of a region defined around the point of interest (keypoint), from [11]

2.2 Scale selection

Figure 4. Illustration of the exhaustive search, from [1, 10]
Figure 5. Signature function with varying region sizes of an interest point, adapted from [1, 2]
Figure 6. Complete picture of auto scale selection, adapted from [1, 2]

3. Choice for signature function: Laplacian-of-Gaussian

Figure 7. equation of Laplacian of Gaussian (LoG) and its behavior with circles of increasing scale, adapted from [1]
Figure 8. Automatic scale selection with Laplacian of Gaussian, from [1, 10]
Figure 9. LoG detector result, from [1, 5]




This publication is for organizing and posting what I’ve studied in scope of CS and Mathematics

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store