Color image denoising by chromatic edges based vector valued diffusion
This work addresses color image denoising for applications like photography or computer vision, but it appears incremental as it builds on existing diffusion methods with a focus on chromatic edges.
The authors tackled color image denoising by proposing an improved geometric diffusion scheme that incorporates edges from all three color channels to avoid color smearing artifacts, achieving good denoising with edge preservation compared to other schemes.
In this letter we propose to denoise digital color images via an improved geometric diffusion scheme. By introducing edges detected from all three color channels into the diffusion the proposed scheme avoids color smearing artifacts. Vector valued diffusion is used to control the smoothing and the geometry of color images are taken into consideration. Color edge strength function computed from different planes is introduced and it stops the diffusion spread across chromatic edges. Experimental results indicate that the scheme achieves good denoising with edge preservation when compared to other related schemes.