Exemplar-based Image Inpainting base on Structure Construction

Image inpainting technique is that repairs damaged area or remove areas in an image. In order to deal with this kind of problems, not only a robust image inpainting algorithm should be used, technique of structure generation is also needs to adopt in inpainting procedure. In this paper, we extend an exemplar-based image inpainting method by incorporating Bezier curves to construct missing edge information. Before we apply our inpainting procedure to a damaged image, mean shift segmentation is used to extract contours of each region. After the structure information of an image is determined, destroyed contours will be connected in curve fitting process and damaged regions will be inpainted by using exemplar-based inpainting method. The experimental results show that our proposed method could deal with several kinds of pictures well.

[1]  Alexei A. Efros,et al.  Scene completion using millions of photographs , 2007, SIGGRAPH 2007.

[2]  Tony F. Chan,et al.  Non-texture inpainting by curvature-driven diffusions (CDD) , 2001 .

[3]  Peter Meer,et al.  Edge Detection with Embedded Confidence , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Shih-Chang Hsia A fast efficient restoration algorithm for high-noise image filtering with adaptive approach , 2005, J. Vis. Commun. Image Represent..

[5]  Manuel Menezes de Oliveira Neto,et al.  Fast Digital Image Inpainting , 2001, VIIP.

[6]  Patrick Pérez,et al.  Region filling and object removal by exemplar-based image inpainting , 2004, IEEE Transactions on Image Processing.

[7]  Dorin Comaniciu,et al.  Robust analysis of feature spaces: color image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Tony F. Chan,et al.  Nontexture Inpainting by Curvature-Driven Diffusions , 2001, J. Vis. Commun. Image Represent..

[9]  Daniel Cohen-Or,et al.  Fragment-based image completion , 2003, ACM Trans. Graph..

[10]  Guillermo Sapiro,et al.  Image inpainting , 2000, SIGGRAPH.