DocumentCode :
3444459
Title :
Research on integral (3D) image compression technology based on neural network
Author :
Zheng, Wanying ; Piao, Yan
Author_Institution :
College of Electronic Information Engineering, Changchun University of Science and Technology, China, 130022
fYear :
2012
fDate :
16-18 Oct. 2012
Firstpage :
382
Lastpage :
386
Abstract :
Three dimensional image systems offer significant benefits over conventional two dimensional systems. Integral imaging is a promising technique for delivering high-quality three-dimensional content. However, a large amount of data produces during acquisition prohibits direct transmission of Integral Image data. In this work we propose volume pixel matching encoder and a neural network color restoration for Integral Image compression. The proposed encoder is based on pixel matching to reconstruct discarded elemental images and use the method of neural network to recovery the color. Comparing with JPEG compression method, the algorithm is more effective as show in PSNR.
Keywords :
image compression; integral imaging; neural network;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image and Signal Processing (CISP), 2012 5th International Congress on
Conference_Location :
Chongqing, Sichuan, China
Print_ISBN :
978-1-4673-0965-3
Type :
conf
DOI :
10.1109/CISP.2012.6469768
Filename :
6469768
Link To Document :
بازگشت