Chapter 6
Corner and Interest Point Detection
Corner detection is valuable for locating complex objects and for tracking them in 2-D or 3-D. This chapter discusses this detection problem and considers methods that are best suited for the task.
Look out for:
• the ways in which corner features are useful.
• the variety of methods available for corner detection—template matching, the second-order derivative method, the median-based method, the Harris interest point detector.
• where the corner signal is a maximum: how detector bias arises.
• how corner orientation may be estimated.
• why invariant feature detectors are needed: the hierarchy of relevant types of invariance.
• how feature detectors may be made invariant to similarity and affine ...
Get Computer and Machine Vision, 4th Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
