4 February 2014 Deinterlacing algorithm using gradient-regularized modular neural networks
Author Affiliations +
Abstract
An intrafield deinterlacing algorithm based on gradient-regularized modular neural networks is proposed. The proposed method defines six gradient regularization terms for every missing pixel. Different modular neural networks are selectively used according to the gradient of the pixel to be interpolated. With the statistics of the six gradient regularization terms, a more robust output is generated by modular neural networks. When compared with existing deinterlacing algorithms, the proposed algorithm improves the peak signal-to-noise-ratio while achieving better subjective quality.
© 2014 SPIE and IS&T
Hao Zhang, Hao Zhang, Ruolin Wang, Ruolin Wang, Wenjiang Liu, Wenjiang Liu, Mengtian Rong, Mengtian Rong, } "Deinterlacing algorithm using gradient-regularized modular neural networks," Journal of Electronic Imaging 23(1), 013014 (4 February 2014). https://doi.org/10.1117/1.JEI.23.1.013014 . Submission:
JOURNAL ARTICLE
6 PAGES


SHARE
Back to Top