Description Combination and Region Merging

Abstract

The iterative region growing algorithm isolates surface regions sequentially based on the original HK-sign map regions. As discussed in Chapter 4, three different region descriptions are recorded for each region so that the effects of the sequential processing might be accounted for in the final segmentation. The static first-within-tolerance region description and the dynamic best-fit region description computed by the algorithm provide a dual region decomposition that can be integrated by a higher level process that understands how the region descriptions were created. The first-within-tolerance region description is obtained by a “monotonic” computational process that employs strict approximation requirements and strict updating procedures. The best-fit region description is obtained via a more flexible “non-monotonic” computational process that controls only the connectivity of the growing region and does not control the connectivity of the previously discovered regions if they are affected by the liberal best-fit updating procedures. The best-fit so far surface list complements these two dual region descriptions by retaining a snapshot of the best-fit regions at the time of region definition.