Title :
Blind Image Restoration using the Cepstrum Method
Author :
Kang, Xiumei ; Peng, Qingjin ; Thomas, Gabriel ; Yu, Chunsheng
Author_Institution :
Dept. of Mech. & Manuf. Eng., Manitoba Univ., Winnipeg, Man.
Abstract :
Much research has been conducted on blind image restoration using the cepstrum method for degradations caused by out-of-focus and motion blurring due to the camera´s focus settings and/or camera´s motion that lead to a uniformly blurred image. The restoration of an image with a still background and a moving object is seldom addressed in the literature. This paper presents a method that extracts the blurred object from the background first, and then estimates the parameters of the PSF using the cepstrum method. Final restoration is achieved by using a classical Wiener filter. Experimental results show that the proposed method is able to achieve satisfactory restored images
Keywords :
Wiener filters; cepstral analysis; image motion analysis; image restoration; Wiener filter; blind image restoration; camera motion; cameras focus settings; cepstrum method; motion blurring; object extraction; point spread function; Additive noise; Cables; Cepstrum; Computer aided manufacturing; Image restoration; Optical distortion; Parameter estimation; Power transmission lines; Wiener filter; Wind; cepstrum method; image restoration;
Conference_Titel :
Electrical and Computer Engineering, 2006. CCECE '06. Canadian Conference on
Conference_Location :
Ottawa, Ont.
Print_ISBN :
1-4244-0038-4
Electronic_ISBN :
1-4244-0038-4
DOI :
10.1109/CCECE.2006.277481