Learning-Based Image Super-Resolution with Directional Total Variation | ||||
The International Conference on Electrical Engineering | ||||
Article 64, Volume 7, 7th International Conference on Electrical Engineering ICEENG 2010, May 2010, Page 1-11 PDF (186.21 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/iceeng.2010.33038 | ||||
![]() | ||||
Author | ||||
Osama. A. Omer | ||||
Department of Electrical Engineering, South Valley University, Aswan. | ||||
Abstract | ||||
Abstract: We propose a super-resolution algorithm based on local adaptation. In the proposed algorithm, the mapping function from the low-resolution images to high-resolution image is estimated by adaptation. Moreover, the property of the high-resolution image is learned and incorporated in a regularization-based restoration. The proposed regularization function is used as a general directional total variation with adaptive weights. The adaptive weights of the directional total variation are estimated based on the property of the partially reconstructed high-resolution image. The regularization function can be thought as a linear combination of smoothness in different directions. The convexity conditions as well as the convergence conditions are studied for the proposed algorithm. | ||||
Keywords | ||||
Super-resolution; image fusion; Restoration; directional total variation; regularization | ||||
Statistics Article View: 159 PDF Download: 276 |
||||