| Autor: |
Warrier, Gayathry Sobhanan, Mahapatra, Hariballav, Khuntia, Monalisa, Rajesh, M., Vincent, Rajiv, Pathak, Avinav |
| Zdroj: |
SN Computer Science; September 2023, Vol. 4 Issue: 5 |
| Abstrakt: |
Appropriate vascular segmentation is dependent on effective picture pre-processing techniques that improve the contrast of the blood vessels, reduce noise, eliminate non-uniform illumination, highlight thin vessels, and retain background texture. These techniques are necessary for accurate vessel segmentation. Here, both the edge- and texture-smoothed data from the vessel probability map are used in the derivation of the adaptive optimal q-order in the G-L mask. The smooth information is not affected, the textures are maintained, and the contrast of the blood vessels is enhanced, thanks to the proposed filter. In addition to sharpening the focus on the vessels themselves, a Gaussian curve fitting is used to contrast stretch the entire image. Retinal fundus images processed with cerebral DSA are subjected to both qualitative and quantitative assessments of contrast enhancement. Quantitative performance indicators are tabulated and compared to other approaches to show how well this technique works for improving medical images everywhere. The suggested filter is easy to implement, flexible enough to adapt to different images, and effective at increasing both vessel contrast and overall image contrast. |
| Databáze: |
Supplemental Index |
| Externí odkaz: |
|
Full text from SpringerLink