DocumentCode :
3660148
Title :
Super-resolution image reconstruction via patch haar wavelet feature extraction combined with sparse coding
Author :
Xuan Zhu;Benyuan Li;Jiyao Tao;Bo Jiang
Author_Institution :
School of Information Science and Technology, Northwest University, Xi´an, Shaanxi Province, China
fYear :
2015
Firstpage :
770
Lastpage :
775
Abstract :
This paper presents a new approach to single-image super-resolution reconstruction, based on patch haar wavelet feature extraction combined with sparse coding. The training sample set is constructed by image patches haar wavelet transform to extract the horizontal, vertical and diagonal high frequency component composition column feature vector. Then, we train a pair of learning dictionaries which have good adaptive ability by using joint training method. Learning dictionaries combined with sparse coding theory to realize the image super-resolution reconstruction. As the experiment results show, the new method has good performs for recovering the lost high frequency information, and has good robustness.
Keywords :
"Training","Feature extraction","Image reconstruction","Dictionaries","Wavelet transforms","Interpolation","Image resolution"
Publisher :
ieee
Conference_Titel :
Information and Automation, 2015 IEEE International Conference on
Type :
conf
DOI :
10.1109/ICInfA.2015.7279388
Filename :
7279388
Link To Document :
بازگشت