DocumentCode :
653359
Title :
Fast Wavelet Thresholding Algorithms for Face Image Inpainting
Author :
Yibin Yu ; Jinguo Cao ; Yaofang Tang ; Junying Gan
Author_Institution :
Sch. of Inf. Eng., Wuyi Univ., Jiangmen, China
fYear :
2013
fDate :
20-23 Aug. 2013
Firstpage :
1445
Lastpage :
1449
Abstract :
Wavelet iteration inpainting has been well known as an important method of image inpainting, which usually requires a lot of iterations. There are some fast algorithm can be used in image inpainting. A Fast Iterative Shrinkage Thresholding Algorithm (FISTA) was introduced to carry out our face image inpainting. Compared with the standard iterative thresholding algorithm, this algorithm is more effective. The numerical experiments show that our algorithms can improve the convergence of the algorithm. In addition, we proposed a new dynamic threshold strategy and got a better restoration quality.
Keywords :
image restoration; image segmentation; iterative methods; wavelet transforms; FISTA; dynamic threshold strategy; face image inpainting; fast iterative shrinkage thresholding algorithm; fast wavelet thresholding algorithms; restoration quality; wavelet iteration inpainting; dynamic thresholding; fast iterative shrinkage thresholding; image inpainting; iterative hard thresholding;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Green Computing and Communications (GreenCom), 2013 IEEE and Internet of Things (iThings/CPSCom), IEEE International Conference on and IEEE Cyber, Physical and Social Computing
Conference_Location :
Beijing
Type :
conf
DOI :
10.1109/GreenCom-iThings-CPSCom.2013.254
Filename :
6682266
Link To Document :
بازگشت