Geometrical image denoising using quadtree segmentation

We propose a quadtree segmentation based denoising algorithm, which attempts to capture the underlying geometrical structure hidden in real images corrupted by random noise. The algorithm is based on the quadtree coding scheme proposed in our earlier work and on the key insight that the lossy compression of a noisy signal can provide the filtered/denoised signal. The key idea is to treat the denoising problem as the compression problem at low rates. The intuition is that, at low rates, the coding scheme captures the smooth features only, which basically belong to the original signal. We present simulation results for the proposed scheme and compare these results with the performance of wavelet based schemes. Our simulations show that the proposed denoising scheme is competitive with wavelet based schemes and achieves improved visual quality due to better representation for edges.