Scale space
lastmod 2019-12-06created 2019-12-063 edits
Scale-space theory is a framework for multi-scale signal representation developed by the computer vision, image processing and signal processing communities with complementary motivations from physics and biological vision. It is a formal theory for handling image structures at different scales, by representing an image as a one-parameter family of smoothed images, the scale-space representation, parametrized by the size of the smoothing kernel used for suppressing fine-scale structures.
About
Scale is one of the most important concepts related to human vision. When we look at a scene with our eyes, what we can see differs considerably depending on how far away we view it from. The closer we look, the more detail of objects we can see; the farther away we look, the more we see the rough structure and outline. We often say we look at something "at a small scale" or "at a large scale": looking closely in detail is viewing at a small scale, and stepping back to look at the whole is viewing at a large scale.