Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
The authors evaluate salt-and-pepper noise removal via recursive thresholded median filtering using both standard SSIM and a novel structural metric called SSIM-Map. Conventional image-domain quality metrics often mask localized degradation and residual impulse artifacts in restored textures. By computing structural similarity across sliding-window singular value decomposition (SVD) entropy maps, SSIM-Map demonstrates significantly greater sensitivity to edge blur and subtle artifact leakage.
Standard SSIM regularly overlooks fine-grained restoration failures, but evaluating structural similarity across SVD-derived entropy maps exposes the residual impulse artifacts and blur that conventional IQA misses.
This paper studies the removal of salt-and-pepper (SP) noise from grayscale images using a median filter (MF) within a recursive thresholding algorithm. Denoising performance is assessed using two complementary metrics: SSIM-Img and SSIM-Map.SSIM-Img is standard Image Quality Assessment (IQA), the conventional Structural Similarity Index (SSIM) computed between the restored and clean images. SSIM-Map is novel IQA, an SSIM-based evaluation computed between entropy maps of these images, where the maps are obtained using singular value-decomposition entropy in sliding windows. We show that SSIM-Map is more sensitive to residual impulse artifacts, blur, and local intensity transitions, and therefore complements the conventional SSIM-Img metric.