Local feature representations

A relatively recent development in the computer vision world has been the development of local-feature based methods. Local features are computed on a small region of the image, unlike the previous features we considered, which had been computed on the whole image. Mahotas supports computing a type of these features, Speeded Up Robust Features (SURF). There are several others, the most well-known being the original proposal of SIFT. These features are designed to be robust against rotational or illumination changes (that is, they only change their value slightly when illumination changes).

When using these features, we have to decide where to compute them. There are three possibilities that are commonly used:

  • Randomly ...

Get Building Machine Learning Systems with Python - Second Edition now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.