Speeded up robust features (SURF) was proposed by Herbert Bay, Tinne Tuytelaars, and Luc Van Gool in 2006. Some of the drawbacks of SIFT are that it is slow and computationally expensive. To target this problem, SURF was conceived. Apart from the increase in speed, the other motivations behind SURF were as follows :
- Fast interest point detection
- Distinctive interest point description
- Speeded up descriptor matching
Just like we saw in SIFT, or even ORB for that matter, SURF also aims to achieve invariance in rotation, scale changes, illumination changes, and also any change in the viewpoint. In the coming sections, we will look at how SURF is able to achieve all of these invariances and at the same time be fast ...