Deinterlacing algorithm using gradient-regularized modular neural networks
4 February 2014 Deinterlacing algorithm using gradient-regularized modular neural networks
Hao Zhang, Ruolin Wang, Wenjiang Liu, Mengtian Rong
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 0091-3286/2014/$25.00 © 2014 SPIE and IS&T
Hao Zhang, Ruolin Wang, Wenjiang Liu, and 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
Published: 4 February 2014
Lens.org Logo
CITATIONS
Cited by 3 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neural networks

Evolutionary algorithms

Video

Image quality

Computer aided design

Visualization

Convolution

Back to Top