Anisotropic diffusion noise filtering using region adaptive smoothing strength

• New AD-based denoising method using adaptive smoothing strength is proposed.
• Many classifiers are used to consider the varying noise characteristics.
• Training data are filtered to obtain balanced training results.
• Simple region analysis metric is proposed.

This paper presents an improved anisotropic diffusion method using region adaptive smoothing strength. Unlike existing methods, the proposed method uses an adaptive classifier to find a good estimate of the optimal smoothing strength for each iteration to consider the varying noise characteristics. Further, when training the classifiers, the usefulness of the training data is verified and less useful data are excluded to avoid degraded training results, thereby generating robust and improved denoising performance. For reduction of the computational complexity, this paper also proposes a simple region analysis technique. Consequently, the proposed method is appropriate for the devices that have relatively small computing power. Experimental results confirm that the proposed method outperforms AD-based benchmark methods by increased peak signal-to-noise ratio up to 2.37 dB and structural similarity up to 0.0557 for 10% noise level.