DocumentCode :
1583597
Title :
Hybrid Recursive Super-resolution Image Reconstruction using Neural Networks
Author :
Zhang, Di ; Miao, Xuelan ; He, Jiazhong
Author_Institution :
Shaoguan Univ., Shaoguan
Volume :
1
fYear :
2007
Firstpage :
192
Lastpage :
196
Abstract :
Most published super-resolution image reconstruction techniques usually perform well on small magnifications, however, as magnification increases, they suffer two severe problems: the exponentially increased computational complexity and the degradation of reconstruction quality caused by severe ringing artifacts. In this paper, a hybrid recursive reconstruction algorithm using neural networks is proposed to tackle these two problems.
Keywords :
computational complexity; image reconstruction; image resolution; neural nets; computational complexity; hybrid recursive super-resolution image reconstruction; neural networks; reconstruction quality; Computational complexity; Computer science; Degradation; Helium; Image reconstruction; Image resolution; Image sampling; Neural networks; Pixel; Strontium;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Natural Computation, 2007. ICNC 2007. Third International Conference on
Conference_Location :
Haikou
Print_ISBN :
978-0-7695-2875-5
Type :
conf
DOI :
10.1109/ICNC.2007.423
Filename :
4344180
Link To Document :
بازگشت