What is the story behind the story about SIFT descriptor?

1. What is descriptor in SIFT?
2. How is SIFT descriptor of a key point generated?
3. How does the SIFT descriptor achieve scale invariance?
4. Is SIFT a detector or descriptor?

What is descriptor in SIFT?

A SIFT descriptor is a 3-D spatial histogram of the image gradients in characterizing the appearance of a keypoint. The gradient at each pixel is regarded as a sample of a three-dimensional elementary feature vector, formed by the pixel location and the gradient orientation.

How is SIFT descriptor of a key point generated?

For each key point, the dominant orientation is determined to achieve rotation invariance. SIFT descriptors are calculated as a histogram of image gradients around key points to characterize the local appearance of each selected key point. Readers can find more detailed material about the SIFT feature in Ref.

How does the SIFT descriptor achieve scale invariance?

To obtain contrast invariance, the SIFT descriptor is normalized to unit sum. In this way, the weighted entries in the histogram will be invariant under local affine transformations of the image intensities around the interest point, which improves the robustness of the image descriptor under illumination variations.

Is SIFT a detector or descriptor?

The Scale-Invariant Feature Transform (SIFT) bundles a feature detector and a feature descriptor. The detector extracts from an image a number of frames (attributed regions) in a way which is consistent with (some) variations of the illumination, viewpoint and other viewing conditions.