Definition:Image inpainting refers to the process of filling-in missing data in a designated region of the visual input.
Image inpainting [1], [2], [3] refers to the process of filling-in missing data in a designated region of the visual input (Figure 1). The object of the process is to reconstruct missing parts or damaged image in such a way that the inpainted region cannot be detected by a causal observer. Applications range from the reconstruction of missing blocks introduced by packet loss during wireless transmission, reversing of impairments, such as cracks, scratches, and dirt, in scanned photographs and digitized artwork images, to removal/introduction of image objects such as logos, stamped dates, text, persons, and special effects on the scene. Typically, after the user selects the region to be restored, the inpainting algorithm automatically repairs the damaged area by means of image interpolation.
References
S.-D._ Rane, G. Sapiro, and M. Bertalmio, “Structure and Texture Filling-In of Missing Image Blocks in Wireless Transmission and Compression Applications,” IEEE Transactions on Image Processing, Vol. 12, No. 3, March 2003, pp. 296–303.
C.-A.-Z. Barcelos, M.-A. Batista, A.-M. Martins, and A.-C. Nogueira, “Level Lines Continuation Based Digital Inpainting,” Proc. XVII Brazilian Symposium on Computer Graphics and Image Processing (SIBGRAPI′04), October 2004, pp. 50–57.
A. Criminisi, P. Perez, and K. Toyama, “Region Filling and Object Removal by Exemplar-Based Image Inpainting,” IEEE Transactions on Image Processing, Vol. 13, No. 9, September 2004, pp. 1200–1212.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer Science+Business Media, Inc.
About this entry
Cite this entry
(2006). Image Inpainting. In: Furht, B. (eds) Encyclopedia of Multimedia. Springer, Boston, MA. https://doi.org/10.1007/0-387-30038-4_98
Download citation
DOI: https://doi.org/10.1007/0-387-30038-4_98
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-24395-5
Online ISBN: 978-0-387-30038-2
eBook Packages: Computer ScienceReference Module Computer Science and Engineering