Improved DCT-Based Nonlocal Means Filter for MR Images Denoising

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="232685.fig.006a" src="https://static.hindawi.com/articles/cmmm/volume-2012/232685/figures/232685.fig.006a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>T1-weighted image</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="232685.fig.006b" src="https://static.hindawi.com/articles/cmmm/volume-2012/232685/figures/232685.fig.006b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>T2-weighted image</td></tr></table></td></tr><tr class="fig-image" id="c"><td><img alt="232685.fig.006c" src="https://static.hindawi.com/articles/cmmm/volume-2012/232685/figures/232685.fig.006c.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(c) </b>PD-weighted image</td></tr></table></td></tr></table>

<table>PSNR comparison of UNLM-DCT, UNLM, and NLM for different images and noise conditions. The proposed method outperforms the others in almost all the cases in terms of PSNR.</table>

Computational and Mathematical Methods in Medicine

fig6

Figure 6

Figure 6: Improved DCT-Based Nonlocal Means Filter for MR Images Denoising 