Exemplar-based inpainting using local binary patterns

Abstract

This paper focuses on novel image reconstruction method based on modified exemplar-based technique. The basic idea is to find an example (patch) from an image using local binary patterns, and replacing non-existed ('lost') data with it. We propose to use multiple criteria for a patch similarity search since often in practice existed exemplar-based methods produce unsatisfactory results. The criteria for searching the best matching uses several terms, including Euclidean metric for pixel brightness and Chi-squared histogram matching distance for local binary patterns. A combined use of textural geometric characteristics together with color information allows to get more informative description of the patches. Texture synthesis method proposed by Efros and Freeman for patch restoration is utilized in the proposed method. It allows optimizing an overlap region between patches using minimum error boundary cut. Several examples considered in this paper show the effectiveness of the proposed approach for large objects removal as well as recovery of small regions on several test images.

Image extrapolation for photo stitching using nonlocal patch-based inpainting

“…A proper selection of the coefficient  in multiple criteria proposed in [36]. This weighting factor can vary from 0 to 1.…”

Image inpainting using a neural network

“…Accounting for the confidence factor ) ( S C  allows you to assign less weight to the restored pixels as the distance from the available pixels from the area increases S [2,5,7]. Figure 2).…”