Figure 5From: Noise-compensated homotopic non-local regularized reconstruction for rapid retinal optical coherence tomography image acquisitions Magnified view of the red rectangular regions shown in Figure 4 , and processed results of three different algorithms (DT-CWT, BM3D, Proposed). 5(a1), (a2), (a3), (a4) magnified regions from original image; 5(b1), (b2), (b3), (b4) magnified regions from reconstructed image using DT-CWT; 5(c1), (c2), (c3), (c4) magnified regions from reconstructed image using BM3D; 5(d1), (d2), (d3), (d4) magnified regions from reconstructed image using NCHR; It can be observed that the proposed method (NCHR) results in improved important tissue contrast for the boundaries (see red arrows) and important features (see blue arrows), which can be very helpful for clinical and research purposes.Back to article page