| Autor: |
I M S B Rebecca Fernando., D. Jemi Florinabel |
| Rok vydání: |
2020 |
| Předmět: |
|
| Zdroj: |
Advances in Intelligent Systems and Computing ISBN: 9789811550287 |
| Popis: |
The work given in this paper explains the process of inpainting the images under global optimization technique. Initially, patch selection has been taken from an image by the clustering method to determine the portion of the unavailable information in an image. This takes place by the selection of the patch of lost portion in an image by grouping of the pixels in a region that gives a high quality of the image which has been followed by the refining of patches. The patch refinement takes place using high order singular value decomposition (HOSVD) that gets the cluster of patches and remove the unwanted pixels that are not needed for the inpainting. This collects the pattern from the patches that are clustered initially. At last, the weight value is obtained from the patches that has refined and the objective function has been included to get the clear image which gives a clear resemblance of the original image using Markov random field (MRF). |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
