Information granules in image histogram analysis

•A concept of granular computing employed in image enhancement is discussed.•2D granular histogram analysis is introduced.•The newly developed approach builds an information granule able to highlight a region.•The method identifies a seed points cloud that refer to structure under consideration.•The...

Full description

Saved in:
Bibliographic Details
Published in:Computerized medical imaging and graphics 2018-04, Vol.65, p.129-141
Main Author: Wieclawek, Wojciech
Format: Article
Language:English
Subjects:
Computation
Computed tomography
Cumulative histogram
Digital imaging
Equalization
Granular computing
Histogram analysis
Histogram equalization
Histograms
Image acquisition
Image enhancement
Image histogram
Image processing
Image processing systems
Intensification of gray levels
Justifiable granular computing
Median
Medical imaging
Tomography
Weighted median
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•A concept of granular computing employed in image enhancement is discussed.•2D granular histogram analysis is introduced.•The newly developed approach builds an information granule able to highlight a region.•The method identifies a seed points cloud that refer to structure under consideration.•The proposed approach allows the redistribution of gray levels of a specific range. A concept of granular computing employed in intensity-based image enhancement is discussed. First, a weighted granular computing idea is introduced. Then, the implementation of this term in the image processing area is presented. Finally, multidimensional granular histogram analysis is introduced. The proposed approach is dedicated to digital images, especially to medical images acquired by Computed Tomography (CT). As the histogram equalization approach, this method is based on image histogram analysis. Yet, unlike the histogram equalization technique, it works on a selected range of the pixel intensity and is controlled by two parameters. Performance is tested on anonymous clinical CT series.
ISSN:0895-6111
1879-0771
DOI:10.1016/j.compmedimag.2017.05.003