Biomedical Engineering Reference
In-Depth Information
Fig. 3.8
A single region in an image that is progressively split into quad-regions when adjacent
regions do not satisfies a set criteria
FDWFKPHQWEDVLQV
ZDWHUVKHGOLQHV
LPDJHRIWZRGDUNRYDOV
Fig. 3.9
Conceptual idea for watershed segmentation (Image adapted from
mathworks�com�au
)
boundaries between adjacent segments (catchment regions) erode and those seg-
ments merge. The other approach is to compute a complete partition of the image
into basins, and subsequently find the watersheds by boundary detection (Fig.
3.10
).
This section introduced the reader to some common algorithms for segmentation
but is certainly not limited to these alone. For those interested in the field of image
processing, the authors suggest the following textbooks and review articles that
provide greater detail, Demirkaya et al. (2009); González and Woods (2011); Suri
et al. (2002, 2005); Umbaugh (2005).
3.3.5
Using Specialised Medical Software
Segmentation algorithms presented in the previous section is a sample of what ex-
ists in an active research field. Published algorithms in the literature allow computer
scientists, capable of advanced programming skills, to program and implement the
Search WWH ::
Custom Search