中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
A MLP-PNN neural network for CCD image super-resolution in wavelet packet domain (EI CONFERENCE)

文献类型:会议论文

作者Zhao X. ; Fu D. ; Zhai L.
出版日期2008
会议名称2008 International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM 2008, October 12, 2008 - October 14, 2008
会议地点Dalian, China
关键词Image super-resolution methods process an input image sequence of a scene to obtain a still image with increased resolution. Classical approaches to this problem involve complex iterative minimization procedures typically with high computational costs. In this paper is proposed a novel algorithm for super-resolution that enables a substantial decrease in computer load. First decompose and reconstruct the image by wavelet packet. Before constructing the image use neural network in place of other rebuilding method to reconstruct the coefficients in the wavelet packet domain. Second probabilistic neural network architecture is used to perform a scattered-point interpolation of the image sequence data in the wavelet packet domain. The network kernel function is optimally determined for this problem by a MLP-PNN (Multi Layer Perceptron - Probabilistic Neural Network) trained on synthetic data. Network parameters dependent on the sequence noise level. This super-sampled image is spatially Altered to correct finite pixel size effects to yield the final high-resolution estimate. This method can decrease the calculation cost and get perfect PSNR. Results are presented showing the quality of the proposed method. 2008 IEEE.
收录类别EI
源URL[http://ir.ciomp.ac.cn/handle/181722/34007]  
专题长春光学精密机械与物理研究所_中科院长春光机所知识产出_会议论文
推荐引用方式
GB/T 7714
Zhao X.,Fu D.,Zhai L.. A MLP-PNN neural network for CCD image super-resolution in wavelet packet domain (EI CONFERENCE)[C]. 见:2008 International Conference on Wireless Communications, Networking and Mobile Computing, WiCOM 2008, October 12, 2008 - October 14, 2008. Dalian, China.

入库方式: OAI收割

来源:长春光学精密机械与物理研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。