Exemplar-Based Image Inpainting using Automatic Patch Optimization

Image inpainting has a wide range of applications in image processing. Exemplar-based technique can inpaint texture and structure regions simultaneously. However, the size of patch influences the result of inpainting. So far, there is no easy way to automatically determine the size of patch. Structure tensor can be used to determine priority, because it is able to determine the properties of a local area. In the paper, the size of patch is computed by structure tensor when adopting exemplar-based technique. To reduce blockiness, boundary constraints is added for searching for similar patches. The experiments show our proposed method can inpaint texture, flat, structure images. Adding boundary constraints can eliminate blockiness to a certain extent.

[1]  Ting-Zhu Huang,et al.  Exemplar-Based Image Inpainting Using a Modified Priority Definition , 2015, PloS one.

[2]  Satoshi Goto,et al.  Side match distortion based adaptive error concealment order for 1Seg video broadcasting application , 2009, 2009 IEEE International Symposium on Circuits and Systems.

[3]  Zongben Xu,et al.  Image Inpainting by Patch Propagation Using Patch Sparsity , 2010, IEEE Transactions on Image Processing.

[4]  Silvano Di Zenzo,et al.  A note on the gradient of a multi-image , 1986, Comput. Vis. Graph. Image Process..

[5]  Christine Guillemot,et al.  Examplar-based inpainting based on local geometry , 2011, 2011 18th IEEE International Conference on Image Processing.

[6]  Pierre Kornprobst,et al.  Mathematical problems in image processing - partial differential equations and the calculus of variations , 2010, Applied mathematical sciences.

[7]  Rajesh Pandurang Borole,et al.  Image Restoration and Object Removal Using Prioritized Adaptive Patch-Based Inpainting in a Wavelet Domain , 2017, J. Inf. Process. Syst..

[8]  Humberto Bustince,et al.  Two-step Algorithm for Image Inpainting , 2017, EUSFLAT/IWIFSGN.

[9]  Adam Finkelstein,et al.  PatchMatch: a randomized correspondence algorithm for structural image editing , 2009, SIGGRAPH 2009.

[10]  Anupam,et al.  Fast and Enhanced Algorithm for Exemplar Based Image Inpainting , 2010, 2010 Fourth Pacific-Rim Symposium on Image and Video Technology.

[11]  Jenq-Neng Hwang,et al.  Exemplar-Based Video Inpainting Without Ghost Shadow Artifacts by Maintaining Temporal Continuity , 2009, IEEE Transactions on Circuits and Systems for Video Technology.

[12]  Patrick Pérez,et al.  Non-Local Patch-Based Image Inpainting , 2017, Image Process. Line.

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

[14]  Z. Yao,et al.  Image inpainting algorithm based on partial differential equation technique , 2013 .

[15]  Peng Li,et al.  Two anisotropic fourth-order partial differential equations for image inpainting , 2013, IET Image Process..

[16]  Yunmei Chen,et al.  Application of partial differential equation‐based inpainting on sensitivity maps , 2005, Magnetic resonance in medicine.

[17]  Miska M. Hannuksela,et al.  The error concealment feature in the H.26L test model , 2002, Proceedings. International Conference on Image Processing.

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

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

[20]  Xiaohui Yang,et al.  Novel image inpainting algorithm based on adaptive fourth-order partial differential equation , 2017, IET Image Process..

[21]  Gabriele Facciolo,et al.  Variational Framework for Non-Local Inpainting , 2015, Image Process. Line.

[22]  Rajesh Pandurang Borole,et al.  Image Restoration using Prioritized Exemplar Inpainting with Automatic Patch Optimization , 2017 .