image inpainting

In today’s world, the amount of available information grows exponentially every day. Most of this data is visual data. Correspondingly, the demand for the algorithm of image rent is growing. Traditionally, the first approaches to computer vision problems were classical algorithms without the use of machine learning. Such approaches are limited by many factors. First of all, the conditions imposed on the input images are applied – the shooting angle, lighting, position of objects on the scene, etc. Other classical algorithms cannot meet the needs of modern computer vision problems.

Image inpainting is an important research area in image processing.  Its main purpose is to supplement missing or damaged domains of images using information from surrounding areas.  This step can be performed by using nonlinear diffusive filters requiring a resolution of partial differential evolution equations.  In this paper, we propose a filter defined by a partial differential nonlinear evolution equation with spatial fractional derivatives.  Due to this, we were able to improve the performance obtained by known inpainting models based on partial differential equations and extend certa