TL;DR
A novel image segmentation model that integrates Retinex theory within a hybrid-order total variation framework is proposed that effectively mitigates staircase artifacts and retains structural details, resulting in more natural image restorations and improved segmentation accuracy.
Improved reconstruction performance can be achieved by the proposed model compared with classical TV, biharmonic, and TV2 inpainting methods, and is duly proved through quantitative assessments based on Peak Signal-to-Noise Ratio, Structural Similarity Index Measure, and Mean Squared Error.
This is the first study to formulate an ACM for segmenting intensity inhomogeneity images corrupted by AGMG noise, and the proposed model proves significantly more effective for the segmentation of images degraded by intensity inhomogeneity and mixed AGMG noise.
A multi-scale image fusion framework is proposed, which leverages adaptive exposure, color gradients, and contrast, and demonstrates consistent improvements over state-of-the-art methods across multiple metrics.
Prior-Guided Histogram Equalization (PGHE), a lightweight enhancement framework that integrates conventional HE with Retinex-based illumination priors, and functions as a plug-in module that improves existing HE variants with measurable gains in Structural Similarity and perceived naturalness at a modest cost in Absolu...
The approach provides a mathematically consistent and perceptually coherent formulation for multi-exposure fusion using curvature-driven multiscale representation using curvature-driven multiscale representation.
Many studies rely heavily on the 3-D reconstruction of optical microscope (OM) images; however, conventional approaches such as Z-stacking are limited to a single viewing angle, which inevitably results in visual blind spots. Moreover, OM systems often struggle to reliably match keypoints when processing samples with w...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
