Model-Controlled Flooding is a methodology for image preprocessing and segmentation
that allows for the integration of a priori information about image objects
into flooding simulation with watershed methods for segmentation.
Modeling the initial seeding, region growing and stopping rules of the watershed flooding process
allows users to customize the simulation with user-defined or default model functions incorporating
prior information. MCF preprocessing defines images with desirable features for further segmentation
using existing methods and can lead to substantial improvements. The approach uses a size filter
based on the MCF framework and has been successively demonstrated in diverse applications:
concealed object detection, speckle counting in single cell studies, and on benchmark microscopic image
data sets. MCF achieves benchmark error rates well below those reported in the literature on
multiple test data sets, and in comparisons with other algorithms. It is alsy rather
easily adapted to new imaging contexts.
MCF is introduced and studied in several applications in
The code is just as used in the studies in the above paper, and can be used to replicate those applications as well as a starting point for customization for other applications.
Folders and Files:
This work was supported in part by the U.S. National Institutes of Health under grants P50-GM081883 and RC1-AI086032. Any opinions, findings and conclusions or recommendations expressed in this work are those of the authors and do not necessarily reflect the views of the NIH.
This software is made freely available to any interested user. The authors can provide no support nor assistance with implementations beyond the details and examples here, nor extensions of the code for other purposes. The authors are of course interested in opportunities for creative applications that could define research collaborations, but will not and cannot support routine applications.
The download has been tested to confirm all details are operational as described here.
It is understood by the user that neither the authors nor Duke University bear any responsibility nor assume any liability for any end-use of this software.
It is expected that appropriate credit/acknowledgement be given should the software be included as an element in other software development or in publications.
We hope you enjoy exploring and using the methodology represented in this code, and benefit in your studies from its application.