• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Patch size adaptive image inpainting

Vol. 15, No. 10, October 31, 2021
10.3837/tiis.2021.10.010, Download Paper (Free):


Texture synthesis technology has the advantages of repairing texture and structure at the same time. However, during the filling process, the size of the patch is fixed, and the content of the filling is not fully considered. In order to be able to adaptively change the patch size, we used the exemplar-based inpainting technique as the test algorithm, considering the image structure and texture, calculated the image structure patch size and texture patch size, and comprehensively determined the image patch size. This can adaptively change the patch size according to the filling content. In addition, we use multi-layer images to calculate the priority, so that the order of image repair was more stable. The proposed repair algorithm is compared with other image repair algorithms. The experimental results showed that the proposed adaptive image repair algorithm can better repair the texture and structure of the image, which proved the effectiveness of the proposed algorithm.


Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.

Cite this article

[IEEE Style]
H. Liu, G. Lu, X. Bi, W. Wang, "Patch size adaptive image inpainting," KSII Transactions on Internet and Information Systems, vol. 15, no. 10, pp. 3642-3667, 2021. DOI: 10.3837/tiis.2021.10.010.

[ACM Style]
Huaming Liu, Guanming Lu, Xuehui Bi, and Weilan Wang. 2021. Patch size adaptive image inpainting. KSII Transactions on Internet and Information Systems, 15, 10, (2021), 3642-3667. DOI: 10.3837/tiis.2021.10.010.

[BibTeX Style]
@article{tiis:25018, title="Patch size adaptive image inpainting", author="Huaming Liu and Guanming Lu and Xuehui Bi and Weilan Wang and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2021.10.010}, volume={15}, number={10}, year="2021", month={October}, pages={3642-3667}}