Detecting the scale-invariant SURF features

When trying to match features across different images, we are often faced with the problem of scale changes. That is, the different images to be analyzed can be taken at a different distance from the objects of interest, and consequently, these objects will be pictured at different sizes. If we try to match the same feature from two images using a fixed size neighborhood then, because of the scale change, their intensity patterns will not match.

To solve this problem, the concept of scale-invariant features has been introduced in computer vision. The main idea here is to have a scale factor associated with each of the detected feature points. In recent years, several scale-invariant features have been ...

Get OpenCV 2 Computer Vision Application Programming Cookbook now with O’Reilly online learning.

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