Image and Video Completion by Using Bayesian Tensor Decomposition
Reconstruction of image and video from sparse observations attract a great deal of interest in the filed of image/video compression, feature extraction and denoising. Since the color image and video data can be naturally expressed as a tensor structure, many methods based on tensor algebra have been...
Saved in:
Published in | International journal of computer science issues Vol. 15; no. 5; pp. 1 - 8 |
---|---|
Main Authors | , , , |
Format | Journal Article |
Language | English |
Published |
Mahebourg
International Journal of Computer Science Issues (IJCSI)
2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Reconstruction of image and video from sparse observations attract a great deal of interest in the filed of image/video compression, feature extraction and denoising. Since the color image and video data can be naturally expressed as a tensor structure, many methods based on tensor algebra have been studied together with promising predictive performance. However, one challenging problem in those methods is tuning parameters empirically which usually requires computational demanding cross validation or intuitive selection. In this paper, we introduce Bayesian Tucker decomposition to reconstruct image and video data from incomplete observation. By specifying the sparsity priors over factor matrices and core tensor, the tensor rank can be automatically inferred via variational bayesian, which greatly reduce the computational cost for model selection. We conduct several experiments on image and video data, which shows that our method outperforms the other tensor methods in terms of completion performance. |
---|---|
ISSN: | 1694-0814 1694-0784 |
DOI: | 10.5281/zenodo.1467644 |