Motion adaptive deinterlacing with modular neural networks

Hyunsoo Choi, Chulhee Lee

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)


In this letter, a motion adaptive deinterlacing algorithm based on modular neural networks is proposed. The proposed method uses different neural networks based on the amount of motion. Modular neural networks were selectively used depending on the differences between the adjacent fields. We also used motion vectors to select optimal input pixels from the adjacent fields. Motion estimation was used to find input blocks for the neural networks with minimum errors. Intra/inter-mode switching was employed to address inaccurate motion estimation problems.

Original languageEnglish
Article number5733392
Pages (from-to)844-849
Number of pages6
JournalIEEE Transactions on Circuits and Systems for Video Technology
Issue number6
Publication statusPublished - 2011 Jun

Bibliographical note

Funding Information:
Manuscript received August 17, 2009; revised April 16, 2010 and August 27, 2010; accepted October 14, 2010. Date of publication March 17, 2011; date of current version June 3, 2011. This work was supported by the Korea Science and Engineering Foundation (KOSEF), under Grant 2009-0077978, funded by the Korean Government (MEST). This paper was recommended by Associate Editor M. Comer.

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering


Dive into the research topics of 'Motion adaptive deinterlacing with modular neural networks'. Together they form a unique fingerprint.

Cite this