Single channel medical images enhancement using fractional derivatives.
The current research uses the Grünwald-Letnikov (GL) fractional differential mask to improve satellite and medical images. One of the important image enhancement methods in digital image processing is texture enhancement. A fractional differential-based two-dimensional discrete gradient operator is...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0319990 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The current research uses the Grünwald-Letnikov (GL) fractional differential mask to improve satellite and medical images. One of the important image enhancement methods in digital image processing is texture enhancement. A fractional differential-based two-dimensional discrete gradient operator is based on the definition of Grünwald-Letnikov (GL) interpretation of fractional calculus, which is extended from a one-dimensional operator through the analysis of its spectrum to improve the image texture. Which then extracts more subtle texture information, and gets around the lack of a classical gradient operator. Based on the GL fractional differential, an approximate two-dimensional isotropic gradient operator mask was created using the GL fractional derivative, the technique generates [Formula: see text] and [Formula: see text] pixel-sized masks that preserve the correlation between neighboring pixels. The strength of the mask, which was a variable and non-linear filter, could be changed by varying the intensity factor to enhance the image. Experimental results show that the operator may emphasize the texture and obtain more complex information. Compared to the conventional classical methods, the suggested way has an excellent promotional effect on texture enhancement compared to the previous method on grayscale images. |
|---|---|
| ISSN: | 1932-6203 |