Low-level features for inpainting quality assessment

The paper presents an attempt to use a machine learning approach for inpainting quality assessment. Inpainting has received a lot of attention in recent years and quality assessment is an important task to evaluate different image reconstruction approaches. We present an approach for objective inpainting quality assessment based on natural image statistics and machine learning techniques. Our method is based on observation that when images are properly normalized or transferred to a transform domain, local descriptors can be modeled by some parametric distributions. The shapes of these distributions are different for non-inpainted and inpainted images. Approach permits to obtain a feature vector strongly correlated with a subjective image perception by a human visual system.