Regular Articles

Deinterlacing algorithm using gradient-regularized modular neural networks

[+] Author Affiliations
Hao Zhang

Shanghai Jiao Tong University, Department of Electronic Engineering, Shanghai, China

Ruolin Wang

Shanghai Jiao Tong University, Department of Electronic Engineering, Shanghai, China

Wenjiang Liu

Shanghai Jiao Tong University, Department of Electronic Engineering, Shanghai, China

Mengtian Rong

Shanghai Jiao Tong University, Department of Electronic Engineering, Shanghai, China

J. Electron. Imaging. 23(1), 013014 (Feb 04, 2014). doi:10.1117/1.JEI.23.1.013014
History: Received May 10, 2013; Revised December 4, 2013; Accepted January 10, 2014
Text Size: A A A

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.

Figures in this Article
© 2014 SPIE and IS&T

Citation

Hao Zhang ; Ruolin Wang ; Wenjiang Liu and Mengtian Rong
"Deinterlacing algorithm using gradient-regularized modular neural networks", J. Electron. Imaging. 23(1), 013014 (Feb 04, 2014). ; http://dx.doi.org/10.1117/1.JEI.23.1.013014


Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging & repositioning the boxes below.

Related Book Chapters

Topic Collections

PubMed Articles
Advertisement
  • Don't have an account?
  • Subscribe to the SPIE Digital Library
  • Create a FREE account to sign up for Digital Library content alerts and gain access to institutional subscriptions remotely.
Access This Article
Sign in or Create a personal account to Buy this article ($20 for members, $25 for non-members).
Access This Proceeding
Sign in or Create a personal account to Buy this article ($15 for members, $18 for non-members).
Access This Chapter

Access to SPIE eBooks is limited to subscribing institutions and is not available as part of a personal subscription. Print or electronic versions of individual SPIE books may be purchased via SPIE.org.