Image inpainting is an image completion technique that has a wide range of applications such as image restoration, object removal and occlusion lling in view synthesis. In this paper, two novel techniques are proposed to enhance the performance of Criminisi's algorithm, which inpaints images with an exemplar- based approach. First, a gradient-based searching is developed, which drastically lowers the computational complexity of global searching. Second, the patch matching process is modied with a distance-dependent criterion, such that the accuracy of the best matching candidate is enhanced. The experimental results have shown that with our proposed technique, computational cost is substantially reduced and the inpainting quality is also improved. For large images of 1024 768 pixels, our inpainting algorithm is almost 5 times faster than the original algorithm.
|Title of host publication||Proceedings of the 33rd WIC Symposium on information theory in the Benelux joint with the 2nd WIC/IEEE SP Symposium on Information Theory and Signal Processing in the Benelux, 24-25 may 2012, Boekeloo, Netherlands|
|Publication status||Published - 2012|
|Event||conference; the 33rd WIC Symposium on Information Theory in the Benelux; 2012-05-24; 2012-05-25 - |
Duration: 24 May 2012 → 25 May 2012
|Conference||conference; the 33rd WIC Symposium on Information Theory in the Benelux; 2012-05-24; 2012-05-25|
|Period||24/05/12 → 25/05/12|
|Other||the 33rd WIC Symposium on Information Theory in the Benelux|