In computer vision, the concept of interest points, also called keypoints or feature points, has been largely used to solve many problems in object recognition, image registration, visual tracking, 3D reconstruction, and more. Instead, of evaluating an image as a whole, it could be better to select points that can contain information that perform local analysis on the point to achieve results to apply local or globally. This approach works well as long as a sufficient number of such points are detected in the images of interest and as long as these points are distinct and stable features that can be accurately localized.
Because they are used to analyze image content, feature points should ideally be detected at the same scene or object location no matter from which viewpoint, scale, or orientation the image was taken. View invariance is a very desirable...