DocumentCode :
3579775
Title :
Based on the Technique of Regularization MAP Super-Resolution Image Reconstruction Algorithm
Author :
Zhiyuan Zha ; Hui Liu ; Junkui Li
Author_Institution :
Fac. of Inf. Eng. & Autom., Kunming Univ. of Sci. & Technol., Kunming, China
Volume :
1
fYear :
2014
Firstpage :
31
Lastpage :
34
Abstract :
In this paper, we studied two kinds of image super-resolution algorithms based on MAP-The single frame and multi-frame based regularization technique. In multi-frame version the local adaptive regularized parameter derived from the local image features was introduced to improve the regularization performance, while insufficient considerate in single version. The algorithms adaptively update the parameter and reconstructed image via iterative optimization. Experimental results show that the both algorithm can reconstruct the desire image, the reconstruction result of multi-frame adaptive algorithm is superior to the single-frame version on the objective evaluation index.
Keywords :
image reconstruction; image resolution; iterative methods; maximum likelihood estimation; image features; image reconstruction algorithm; image super-resolution algorithm; iterative optimization; maximum a posteriori; multiframe adaptive algorithm; multiframe based regularization technique; objective evaluation index; regularization MAP super-resolution image; single frame based regularization technique; Adaptive algorithms; Algorithm design and analysis; Gaussian noise; Image reconstruction; Spatial resolution; Adaptive; MAP; Regularization; Super-Resolution;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computational Intelligence and Design (ISCID), 2014 Seventh International Symposium on
Print_ISBN :
978-1-4799-7004-9
Type :
conf
DOI :
10.1109/ISCID.2014.30
Filename :
7064072
Link To Document :
بازگشت