Partial Differential Equation

Feature Learning via Partial Differential Equation with Applications to Face Recognition

We propose a novel Partial Differential Equation (PDE) based method for feature learning. The feature learned by our PDE is discriminative, also translationally and rotationally invariant, and robust to illumination variation.

An Anisotropic Diffusion PDE for Noise Reduction and Thin Edge Preservation

An image denoising operator defined by a non-linear partial differential equation(PDE) is presented, which can remove noise, enhance step-like edges and keep the locality of the edges.