Interest Point Detector and Feature Descriptor Survey

Many algorithms for computer vision rely on locating interest points, or keypoints in each image, and calculating a feature description from the pixel region surrounding the interest point. This is in contrast to methods such as correlation, where a larger rectangular pattern is stepped over the image at pixel intervals and the correlation is measured at each location. The interest point is the anchor point, and often provides the scale, rotational, and illumination invariance attributes for the descriptor; the descriptor adds more detail and more invariance attributes. Groups of interest points and descriptors together describe the actual objects. However, there are many methods and variations in feature description. Some methods use features that are not anchored at interest points, such as polygon shape descriptors, computed over larger segmented polygon-shaped structures or regions in an image. Other methods use interest points only, without using feature descriptors at all. And some methods use feature descriptors only, computed across a regular grid on the image, with no interest points at all. Terminology varies across the literature. In some discussions, interest points may be referred to as keypoints. The algorithms used to find the interest points maybe referred to as detectors, and the algorithms used to describe the features may be called descriptors. We use the terminology interchangeably in this work. Keypoints may be considered a set composed of (1) interest points, (2) corners, (3) edges or contours, and (4) larger features or regions such as blobs; see Figure 6-1. This chapter surveys the various methods for designing local interest point detectors and feature descriptors.