Home
Call For Papers
Submission
Author
Registration
Publications
About
Contact Us

  Image Inpainting  
  Authors : Devidas Lokhande; R.G.Zope; Vrushali Bendre
  Cite as:

 

Inpainting refers to the art of restoring lost parts of image and reconstructing them based on the background information i.e. Image inpainting is the process of reconstructing lost or deteriorated parts of images using information from surrounding areas. The purpose of inpainting is to reconstruct missing regions in a visually plausible manner so that, it seems reasonable to the human eye. There have been several approaches proposed for the same. This paper introduce a new image inpainting using modified exemplar based method approach which include salient structure completion and texture propogation.In salient structure completion step, incomplete salient structures are completed through content based image retrieval technique. In the texture propagation step first synthesizes texture information of completed salient structures. Then the texture information is propagated into remaining missing regions by patch based inpainting method.

 

Published In : IJCSN Journal Volume 3, Issue 1

Date of Publication : 01 February 2014

Pages : 110 - 115

Figures : 09

Tables : --

Publication Link : IJCSN-2014/3-1/Image-Inpainting

 

 

 

Devidas Lokhande : Department of Electronics and Telecommunication, Pune University S.R.E.S.COE Kopargaon, Maharashtra, India

R.G.Zope : Department of Electronics and Telecommunication, Pune University S.R.E.S.COE Kopargaon, Maharashtra, India

Vrushali Bendre : Department of Electronics and Telecommunication, Pune University S.R.E.S.COE Kopargaon, Maharashtra, India

 

 

 

 

 

 

 

Exemplar

Image inpainting

Object removal

Structure completion

Texture Synthesis

We have presented a novel inpainting method for removing objects from digital photographs.The result is an image in which the selected object has been replaced by a visually plausible background that mimics the appearance of the source region and produce more precise texture information. Our approach employs an modified exemplar based texture synthesis technique. In this method, We have presented a novel inpainting technique based on automatic salient structure completion using content based image retrieval technique. The completed salient structures divide the target area into several sub-regions. Then, texture propagation is used to synthesize the texture information with samples from corresponding adjacent sub-regions. In this paper we compares exemplar-based method and image inpainting modified exemplar based method interms of PSNR(dB).it is found that both technique work noticeably well in removal of object from color, black and white images;but the image inpainting using modified exemplar based method we get better PSNR and little blurred in image than exemplar based technique and offers more precise texture information.

 

 

 

 

 

 

 

 

 

[1] Bertalmio, M., Sapiro, G., Caselles, V., et al. “Image inpainting’’. In: Proc.Computer Graphics (SIGGRAPH’00), Singapore, 2000, pp 417–424.

[2] Bertalmio, M., Vesa, L., Sapiro, G., et al., “Simultaneous structure and texture Image inpainting’’. IEEE Trans. Image Process. 12 (8), 2003,pp 882–889.

[3] Chan, T.F., Shen, J., “Non-texture inpainting by curvature driven diffusion’’. J. Vision Commun. Image Represent. 12 (4), 2001, pp 436–449.

[4] Chan, T.F., Shen, J., ‘’Mathematical models for local non-texture inpainting’’.SIAM J. Appl. Math. 62 (3), 2002,pp 1019–1043.

[5] Chen, J.Q., Pappas, T.N., Mojsilovic, A., et al.,“Adaptive perceptual color-texture image segmentation.” IEEE Trans. Image Process. 14 (10), 2005, pp1524–1536.

[6] Cheng, W. H., Hsieh, C.W., Lin, S.K., et al., “Robust algorithm for exemplar based image inpainting”. In Proc. Internat. Conf. on Computer Graphics, Imaging Vision, Beijing, 2005, pp 64–69.

[7] Criminisi, A., Perez, P., Toyama, K., “Region filling and object removal by exemplar-based inpainting”. IEEE Trans. Image Process. 13 (9), 2004, pp 1200–1212.

[8] Dobrosotskaya, J.A., Bertozzi, A.L., “A wavelet-laplace variational technique for mage deconvolution and inpainting”. IEEE Trans. Image Process. 17 (5), 2008,pp 657–663.

[9] Efros, A.A., Leung, T.K., “Texture synthesis by non-parametric sampling”. In: Proc. Internat. Conf. on Computer Vision (ICCV’99), Kerkyra, 1999, pp 1033–1038.

[10] Grossauer, H., “A combined PDE and texture synthesis approach to inpainting”.In: Proc. European Conf. on Computer Vision, Slovansky ostrov, vol. 4, 2004,pp 214–224

[11] Hays, J., Efros, A.A., “Scene completion using millions of photographs”. Commun. ACM 51 (10), 2008,pp 87–94

[12] Ignácio, U.A., Jung, C.R.,“Block-based image inpainting in the wavelet domain”. Visual Comput. 23 (9–11), 2007, pp 733–741

[13] M. Bertalmio, A.L. Bertozzi, and G. Sapiro, "Navier stokes, Fluid Dynamics, and Image and Video Inpainting", Proceedings of Conf. Comp. Vision Pattern Rec., Hawaii, Dec 2001. pp 355–362,

[14] Li, H., Wang, S., Zhang, W., et al., “Image inpainting based on scene transform and color transfer”. Pattern Recognition Lett. 31 (7), 2010, pp 582–592.

[15] Sun, J., Yuan, L., Jia, J., et al., “Image completion with structure propagation”. ACM Trans. Graphics 24 (3), 2005, pp 861–868.