Title :
Enlargement of Digital Images by Using Neural Network
Author :
DeXin, Ren ; Jiufen, Zhao ; JiuLing, Zhao ; ShunHong, Wang
Author_Institution :
National Univ. of Defense Technol., ChangSha
Abstract :
In this paper, an image enlargement method using neural network was proposed. In the high resolution multi-neural network (MNN), two NN are used, corresponding to the region with rapid change (high local variance) and the region requiring a smooth interpolation (low local variance). The weighted sum of the two NN outputs is defined as the result of enlargement. The simulation results show that the method is well for image enlargement
Keywords :
image processing; neural nets; digital image enlargement; high local variance; low local variance; multineural network; neural network; smooth interpolation; Digital images; Equations; Frequency estimation; Image resolution; Image sampling; Interpolation; Mean square error methods; Multi-layer neural network; Neural networks; Signal resolution; Image enlargement; local variance; neural network;
Conference_Titel :
Intelligent Systems Design and Applications, 2006. ISDA '06. Sixth International Conference on
Print_ISBN :
0-7695-2528-8
DOI :
10.1109/ISDA.2006.140
