4.3. Phase congruency
The comparison of edge detectors highlights some of their innate problems: incomplete contours; the need for selective thresholding; and their response to noise. Further, the selection of a threshold is often inadequate for all the regions in an image since there are many changes in local illumination. We shall find that some of these problems can be handled at a higher level, when shape extraction can be arranged to accommodate partial data and to reject spurious information. There is though natural interest in refining the low-level feature extraction techniques further.
Phase congruency is a feature detector with two main advantages: it can detect a broad range of features; and it is invariant to local (and smooth) ...
Get Feature Extraction and Image Processing for Computer 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.
