The MSER algorithm uses the same mechanism as the watershed algorithm; that is, it proceeds by gradually flooding the image from level 0 to level 255. As the level of water increases, you can observe that the sharply delimited, darker areas form the basins that have a relatively stable shape for a period of time (recall that under the immersion analogy, the water levels correspond to the intensity levels). These stable basins are the MSER. These are detected by considering the connected regions at each level and measuring their stability. This is done by comparing the current area of a region with the area it previously had when the level was down by a value of delta. When this relative variation reaches a local minimum, the ...
How it works...
Get OpenCV 4 Computer Vision Application Programming Cookbook - Fourth 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.
