What is it about?
Separation of image into meaningful parts is very important in many image processing applications. One method (Multi-thresholding segmentation) for this image separation purpose is to consider similar pixels of an image as whole regions within the image using some defined thresholds. Finding the optimum values for those threshold is a problem in the field of image processing. In this paper, a new method of optimization was used for finding those numbers.
Featured Image
Why is it important?
Image thresholding is important in many image processing applications. For example, using this method we can separate organ regions of the human body in medical imaging techniques to decrease the amount of information for post-processing. Another famous application is converting a gray-level or color image into black and white image.
Perspectives
Main part of this publication is to show the ability of heuristic optimization methods for the problem of image thresholding segmentation. It is clear that finding the best value for threshold values, need a robust and powerful optimization algorithm especially in the case of big data sets. We showed that , using multi swarm intelligent instead of single swarm is more efficient, faster and provide better results.
Mohammad Hamed Mozaffari
University of Ottawa
Read the Original
This page is a summary of: Convergent heterogeneous particle swarm optimisation algorithm for multilevel image thresholding segmentation , IET Image Processing, August 2017, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-ipr.2016.0489.
You can read the full text:
Contributors
The following have contributed to this page
