Scale-invariant feature transform (SIFT)

Even though corner features are interesting, they are not good enough to characterize the truly interesting parts. When we talk about image content analysis, we want the image signature to be invariant to things such as scale, rotation and illumination. Humans are very good at these things. Even if I show you an image of an apple upside down that's dimmed, you will still recognize it. If I show you a really enlarged version of that image, you will still recognize it. We want our image recognition systems to be able to do the same.

Let's consider the corner features. If you enlarge an image, a corner might stop being a corner, as follows:

In the second case, the detector will not pick up this corner. And, since it was picked up in the original image, the second image will not be matched with the first one. It's basically the same image, but the corner features-based method will totally miss it. This means that a corner detector is not exactly scale-invariant...