29 August 2016 Super resolution reconstruction based on adaptive regularization using constrained particle swarm optimization
Author Affiliations +
Proceedings Volume 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016); 100334B (2016) https://doi.org/10.1117/12.2244004
Event: Eighth International Conference on Digital Image Processing (ICDIP 2016), 2016, Chengu, China
Abstract
Super-resolution (SR) reconstruction produces one or a set of high-resolution (HR) images from a set of low-resolution (LR) images. Regularization is a classical method for SR reconstruction. It contains only one fixed regularization parameter in most cases. Considering the difference between the LR images, such as noise, resolution, and the registration error, each LR image should correspond to different parameters according to a certain rule. Hence, we used generalized regularization schemes which contain multiple parameters. In order to obtain the optimal parameters, a new adaptive regularization method based on constrained particle swarm optimization algorithm (ARCPSO) is proposed. The initial value of each parameter is adaptive given. Furthermore, the particle swarm optimization (PSO) algorithm is applied to automatically select the optimal parameters in the proper range of initial values. The experimental results verify the effectiveness of our algorithm and demonstrate the superiority of our approach compared with traditional regularization methods.
© (2016) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jianzhen Li, Jianzhen Li, Junhong Sun, Junhong Sun, Feng Wang, Feng Wang, Kailu Guo, Kailu Guo, } "Super resolution reconstruction based on adaptive regularization using constrained particle swarm optimization", Proc. SPIE 10033, Eighth International Conference on Digital Image Processing (ICDIP 2016), 100334B (29 August 2016); doi: 10.1117/12.2244004; https://doi.org/10.1117/12.2244004
PROCEEDINGS
5 PAGES


SHARE
Back to Top