Inpainting of Structural Reconstruction of Monuments Using Singular Value Decomposition Refinement of Patches

Abstract

Image Inpainting of ruined historic monuments and heritage sites can help in visualizing how these may have existed in the past. An inpainted image of a monument can serve as a tool for physical reconstruction purpose. The purpose of the proposed method is to fill cracks and gaps of selected damaged regions in heritage monuments by exploiting the statistical properties of foreground and background along with the spatial location of the damage in the image of the monuments. The patch based image inpainting algorithm is improved by segmenting the image using K means clustering to search the candidate patches in relevant source region only. Segmentation improves patch searching in terms of both quality and time. The priority of the patch to fill is decided based on the standard deviation of the patch around destination pixel. K n similar patches are selected from the source region based on minimum value of sum squared distance. The selected patches are refined using an efficient patch refinement scheme using higher order singular value decomposition to capture underlying pattern among the candidate source patches. The threshold for refinement is selected by using minimum and maximum value of standard deviation of the target patch. This eliminates random variation and unwanted artifacts. Experimental results carried on a large number of natural images and comparisons with well-known existing methods demonstrate the efficacy and superiority of the proposed method.

Patch based Image Inpainting Technique Using Adaptive Patch Size and Sequencing of Priority Terms

“…As image inpainting is an image editing tool user intervention is needed in the form of marking the region to be inpainted. In order to evaluate our algorithm we have compared our results with the basic Criminisi's [1] algorithm, alpha trimmed filter [21], EBIIMPD [22], knnkvalpha (kn similar patches in the vicinity of damaged area with alpha trimmed filter) [24], knnsvd (kn similar patches with SVD for patch refinement) [25] and knnkvsvd (kn similar patches in the vicinity of damaged area with SVD for patch refinement). Parameters which are important in deciding the quality of an image are mean square error (MSE), luminance(L), cross correlation(XK), absolute difference (AD), normalized absolute error (NAE), structural content(SC), PSNR and structural similarity [23].…”