Image Inpainting by Kriging Interpolation Technique
This addresses the time-consuming manual process of image inpainting for digital image restoration, though it appears incremental as it applies an existing statistical technique to a known bottleneck.
The paper tackled the problem of automatically predicting damaged regions in images by proposing a novel statistical image inpainting algorithm based on Kriging interpolation, which achieved high PSNR values in recovering test images from scratches and text damage.
Image inpainting is the art of predicting damaged regions of an image. The manual way of image inpainting is a time consuming. Therefore, there must be an automatic digital method for image inpainting that recovers the image from the damaged regions. In this paper, a novel statistical image inpainting algorithm based on Kriging interpolation technique was proposed. Kriging technique automatically fills the damaged region in an image using the information available from its surrounding regions in such away that it uses the spatial correlation structure of points inside the k-by-k block. Kriging has the ability to face the challenge of keeping the structure and texture information as the size of damaged region heighten. Experimental results showed that, Kriging has a high PSNR value when recovering a variety of test images from scratches and text as damaged regions.