Title :
Image Coding Using Nonlinear Evolutionary Transforms
Author :
Takamura, S. ; Shimizu, Atsuki
Author_Institution :
NTT Media Intell. Labs., NTT Corp., Yokosuka, Japan
Abstract :
Transform is one of the most important tools for image/video coding technology. In this paper, novel nonlinear transform generation based on genetic programming is proposed and implemented into H.264/AVC and HEVC reference software to enhance coding performance. The transform procedure itself is coded and transmitted. Despite this overhead, 0.590% (vs. JM18.0) and 1.711% (vs. HM5.0) coding gain was observed in our preliminary experiment.
Keywords :
data compression; genetic algorithms; image coding; image enhancement; transforms; video coding; H.264-AVC reference software; HEVC reference software; coding performance enhancement; genetic programming; image-video coding technology; nonlinear evolutionary transforms; nonlinear transform generation; Discrete wavelet transforms; Encoding; Genetic programming; Image coding; Video coding; genetic programming; nonlinear transform; ransform coding;
Conference_Titel :
Data Compression Conference (DCC), 2013
Conference_Location :
Snowbird, UT
Print_ISBN :
978-1-4673-6037-1
DOI :
10.1109/DCC.2013.100
