Looking at feature detection

In computer vision, the process of finding areas of interest in an image is called feature detection. Under the hood, for each point of the image, a feature detection algorithm decides whether an image point contains a feature of interest. OpenCV provides a whole range of feature detection (and description) algorithms.

In OpenCV, the details of the algorithms are encapsulated and all of them have similar APIs. Here are some of the algorithms: 

• Harris corner detection: We know that edges are areas with high-intensity changes in all directions. Harris and Stephens came up with this algorithm, which is a fast way of finding such areas. This algorithm is implemented as cv2.cornerHarris in OpenCV.
• Shi-Tomasi corner detection: Shi and Tomasi developed a corner detection algorithm, and this algorithm is usually better than Harris corner detection by finding the N strongest corners. This algorithm is implemented as cv2.goodFeaturesToTrack in OpenCV.
• Scale-Invariant Feature Transform (SIFT): Corner detection is not sufficient when the scale of the image changes. To this end, David Lowe developed a method to describe keypoints in an image that are independent of orientation and size (hence the term scale-invariant). The algorithm is implemented as cv2.xfeatures2d_SIFT in OpenCV2 but has been moved to the extra modules in OpenCV3 since its code is proprietary.
• SURF: SIFT has proven to be really good, but it is not fast enough for most applications. This is where SURF comes in, which replaces the expensive Laplacian of a Gaussian (function) from SIFT with a box filter. The algorithm is implemented as cv2.xfeatures2d_SURF in OpenCV2, but, like SIFT, it has been moved to the extra modules in OpenCV3 since its code is proprietary.

OpenCV has support for even more feature descriptors, such as Features from Accelerated Segment Test (FAST), Binary Robust Independent Elementary Features (BRIEF), and Oriented FAST and Rotated BRIEF (ORB), the latter being an open source alternative to SIFT or SURF.

In the next section, we'll learn how to use SURF to detect features in an image.