Blotch removal in degraded digital video using independent component analysis

Author

Ceccarelli, Michele ; Petrosino, Alfredo

Author_Institution

RCOST, Sannio Univ., Benevento, Italy

Volume

1

fYear

2004

fDate

25-29 July 2004

Lastpage

272

Abstract

Blotchy noise is one of the most common and visually annoying noises noticed in digitized motion picture films. This work investigates a three-stage blotchy noise reduction scheme combining efforts of temporal median filtering, ICA unsupervised learning and deflation after motion/compensation estimation. Implementation of each module of the scheme is discussed; finally performance of the scheme is tested and compared with other methods over real short sequences and results are discussed.

Keywords

cinematography; filtering theory; image denoising; independent component analysis; median filters; motion estimation; unsupervised learning; video signal processing; ICA unsupervised learning; blotch removal; blotchy noise reduction scheme; compensation estimation; degraded digital video; digitized motion picture films; independent component analysis; motion estimation; temporal median filtering; Degradation; Detectors; Forward error correction; Independent component analysis; Material storage; Motion analysis; Motion detection; Motion pictures; Noise reduction; Video compression;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-8359-1

Type

conf

DOI

10.1109/IJCNN.2004.1379912

Filename

1379912