Blob extraction
From Wikipedia, the free encyclopedia
Blob extraction is an image segmentation technique that categorizes the pixels in an image as belonging to one of many discrete regions. Blob extraction is generally performed on the resulting binary image from a thresholding step. Blobs may be counted, filtered, and tracked.
Inconsistent terminology for this procedure exists, including region labeling, connected-component labeling, blob discovery, or region extraction.
Well-known algorithms for accomplishing this exist, including a sequential algorithm and recursive algorithm.
Blob extraction appears to be related to but distinct from "blob detection".
Contents |
[edit] Sequential algorithm
Check the north and west pixel (when considering 4-connectivity) or the northeast, north, northwest, and west pixel for 8-connectivity.
[edit] Recursive algorithm
[edit] References
Horn, Berthold Klaus Paul (1986). Robot Vision. MIT Press, 69-71. ISBN 0-262-08159-8.
[edit] See Also
- OpenCV Blob Extraction Library
- Algorithms on Wikipedia
- Connected component (graph theory)
- Blob detection
