Somanka Maiti
Gaurav Bhatnagar
Abstract
In this article, a blockwise regression-based image inpainting framework is proposed. The core idea is to fill the unknown region in two stages: Extrapolate the edges to the unknown region and then fill the unknown pixels values in each sub-region demarcated by the extended edges. Canny edge detection and linear edge extension are used to respectively identify and extend edges to the unknown region followed by regression within each sub-region to predict the unknown pixel values. Two different regression models based on K-nearest neighbours and support vectors machine are used to predict the unknown pixel values. The proposed framework has the advantage of inpainting without requiring prior training on any image dataset. The extensive experiments on different images with contrasting distortions demonstrate the robustness of the proposed framework and a detailed comparative analysis shows that the proposed technique outperforms existing state-of-the-art image inpainting methods. Finally, the proposed techniques are applied to MRI images suffering from susceptibility artifacts to illustrate the practical usage of the proposed work.
- J. Weickert. 1996. Theoretical Foundations of Anisotropic Diffusion in Image Processing. Springer, 1996. Google Scholar
Digital Library
- M. Bertalmio, A. L. Bertozzi, and G. Sapiro. 2001. Navier-stokes, fluid dynamics, and image and video inpainting. In Proceedings of Computer Vision and Pattern Recognition, Vol. 1, 355–362.Google Scholar
- T. F. Chan and J. Shen. 2001. Nontexture inpainting by curvature-driven diffusions. J. Vis. Commun. Image Represent. 12, 4 (2001), 436–449. Google ScholarDigital Library
- A. Bugeau and M. Bertalmio. 2009. Combining texture synthesis and diffusion for image inpainting. In Proceedings of the International Conference on Computer Vision Theory and Applications, 26–33. Google ScholarDigital Library
- M. Bertalmio, G. Sapiro, V. Caselles, and C. Ballester. 2000. Image inpainting. In Proceedings of Annual Conference on Computer Graphics and Interactive Techniques, 417–424. Google ScholarDigital Library
- A. Telea. 2004. An image inpainting technique based on the fast marching method. J. Graph. Tools 9, 1 (2004), 23–34.Google ScholarCross Ref
- T. Chan and J. Shen. 2001. Local inpainting models and tv inpainting. SIAM J. Appl. Math. 62, 3 (2001), 1019–1043.Google Scholar
- A. Criminisi, P. Pérez, and K. Toyama. 2004. Region filling and object removal by exemplar-based image inpainting. IEEE Trans. Image Process. 13, 9 (2004), 1200–1212. Google ScholarDigital Library
- E. Karaca and M. A. Tunga. 2018. Interpolation-based image inpainting in color images using high dimensional model representation. In Proceedings of European Signal Processing Conference, 2425–2429.Google Scholar
- L. He, Y. Xing, K. Xia, and J. Tan. 2018. An adaptive image inpainting method based on continued fractions interpolation. Discr. Dynam. Nat. Soc. 2018 (2018), 9801361-1–9801361-18.Google Scholar
- E. Karaca and M. A. Tunga. 2018. An interpolation-based texture and pattern preserving algorithm for inpainting color images. Expert Syst. Appl. 91 (2018), 223–234. Google ScholarDigital Library
- F. Boßmann, T. Sauer, and N. Sissouno. 2019. Modeling variational inpainting methods with splines. Front. Appl. Math. Stat. 5 (2019), 27-1–27-12.Google ScholarCross Ref
- Z. Xu and J. Sun. 2010. Image inpainting by patch propagation using patch sparsity. IEEE Trans. Image Process. 19, 5 (2010), 1153–1165. Google ScholarDigital Library
- M. Hanif, A. Tonazzini, P. Savino, and E. Salerno. 2018. Non-local sparse image inpainting for document bleed-through removal. J. Imag. 4, 5 (2018), 68–82.Google ScholarCross Ref
- D. Ding, S. Ram, and J. J. Rodriguez. 2018. Perceptually aware image inpainting. Pattern Recogn. 83 (2018), 174–184.Google ScholarDigital Library
- H. Wang, L. Jiang, R. Liang, and X.-X. Li. 2017. Exemplar-based image inpainting using structure consistent patch matching. Neurocomputing 269 (2017), 90–96. Google ScholarDigital Library
- H. Liu, X. Bi, G. Lu, and W. Wang. 2019. Exemplar-Based Image Inpainting With Multi-Resolution Information and the Graph Cut Technique. IEEE Access 7 (2019), 101641–101657, 2019.Google ScholarCross Ref
- Q. Peng, Y. M. Cheung, X. You, and Y. Y. Tang. 2016. A hybrid of local and global saliencies for detecting image salient region and appearance. IEEE Trans. Syst. Man Cybernet.: Syst. (2016), 1–12.Google Scholar
- Z. Li, J. Liu, and J. Cheng. 2019. Exploiting multi-direction features in MRF-based image inpainting approaches. IEEE Access 7 (2019), 179905–179917.Google ScholarCross Ref
- A. Criminisi, P. Perez, and K. Toyama. 2003. Object removal by exemplar-based inpainting. Proc. Comput. Vis. Pattern Recogn. 2 (2003), 1–8.Google Scholar
- D. Helbert, M. Malek, P. Bourdon, and P. Carre. 2019. Patch graph-based wavelet inpainting for color images. J. Vis. Commun. Image Represent. 64 (2019).Google Scholar
- D. Ding, S. Ram, and J. J. Rodríguez. 2019. Image inpainting using nonlocal texture matching and nonlinear filtering. IEEE Trans. Image Process. 28, 4 (2019), 1705–1719.Google ScholarDigital Library
- A. Halim and B. V. R. Kumar. 2019. An anisotropic PDE model for image inpainting. (unpublished).Google Scholar
- H. Li, W. Luo, and J. Huang. 2017. Localization of diffusion-based inpainting in digital images. IEEE Trans. Inf. Forens. Secur. 12, 12 (2017), 3050–3064.Google ScholarDigital Library
- A. Bugeau, M. Bertalmío, V. Caselles, and G. Sapiro. 2010. A comprehensive framework for image inpainting. IEEE Trans. Image Process. 19, 10 (2010), 2634–2645. Google ScholarDigital Library
- N. Komodakis. 2006. Image completion using global optimization. Proc. Comput. Vis. Pattern Recogn. 1 (2006), 442–452. Google ScholarDigital Library
- V. Jain and S. Seung. 2009. Natural image denoising with convolutional networks. In Advances in Neural Information Processing Systems, 769–776. Google ScholarDigital Library
- J. Xie, L. Xu, and E. Chen. 2012. Image denoising and inpainting with deep neural networks. In Advances in Neural Information Processing Systems, 341–349. Google ScholarDigital Library
- S. Roth and M. J. Black. 2005. Fields of experts: A. framework for learning image priors. Proc. Comput. Vis. Pattern Recogn. 2 (2005), 860–867. Google ScholarDigital Library
- G. Papandreou, P. Maragos, and A. Kokaram. 2008. Image inpainting with a wavelet domain hidden markov tree model. In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, 773–776.Google Scholar
- A. Levin, A. Zomet, and Y. Weiss. 2003. Learning how to inpaint from global image statistics. In Proceedings of IEEE International Conference on Computer Vision, 305–312. Google ScholarDigital Library
- M. S. Sapkal, P. K. Kadbe, and B. H. Deokate. 2016. Image inpainting by Kriging interpolation technique for mask removal. In Proceedings of International Conference on Electrical, Electronics, and Optimization Techniques, 310–313, 2016.Google Scholar
- C.-W. Shih, T.-H. Lai, H.-C. Chu, and Y.-M. Chen. 2013. Image completion using prediction concept via support vector regression. Mach. Vis. Appl. 24, 4 (2013), 753–768.Google ScholarCross Ref
- J. Canny. 1986. A computational approach to edge detection. IEEE Trans. Pattern Anal. Mach. Intell.6 (1986), 679–698. Google ScholarDigital Library
- Z. Wang, H. R. Sheikh, and A. C. Bovik. 2003. Objective video quality assessment. The Handbook of Video Databases: Design and Applications, 1041–1078.Google Scholar
- Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 4 (2004), 600–612. Google ScholarDigital Library
- B. Scholkopf. 2005. Support vector machines and kernel algorithms. In Encyclopedia of Biostatistics. John Wiley Sons, 5328–5335.Google Scholar
- L. Bi, O. Tsimhoni, and Y. Liu. 2011. Using the support vector regression approach to model human performance. IEEE Trans. Syst. Man Cybernet. A: Syst. Hum. 41, 3 (2011), 410–417. Google ScholarDigital Library
- R. C. McKinstry and D. Y. Jarrett. 2004. Magnetic susceptibility artifacts on MRI: A hairy situation. Am. J. Roentgenol 182, 2 (2004), 532–532.Google ScholarCross Ref
- A. Mittal, R. Soundararajan, and A. C. Bovik. 2013. Making a completely blind image quality analyzer. IEEE Sign. Process. Lett. 20, 3 (2013), 209–212.Google ScholarCross Ref
Index Terms
- A Novel Image Inpainting Framework Using Regression
Recommendations
Edge-Guided Image Inpainting with Transformer
Advances in Visual ComputingAbstractImage inpainting aims to complete missing regions by extracting the features of the image through the information of the known region. Traditional image inpainting approaches like patch-based and diffusion-based methods are robust for simple ...
Image Retrieval Using Digital Image Inpainting Techniques
Image retrieval is an inverse problem in digital image processing. In this paper, the authors deal with restoration of image using digitally image inpainting methods. In this inpainting technique, one can extract a missing an important part or can ...
Image Inpainting: A Review
AbstractAlthough image inpainting, or the art of repairing the old and deteriorated images, has been around for many years, it has recently gained even more popularity, because of the recent development in image processing techniques. With the improvement ...
Comments