The regularization parameter plays a crucial role in the quality of a restored super-resolution image. In this paper, we propose a method for parametric regularization based on the incomplete orthogonalization method. The method truncates the Arnoldi recurrence. Specifically, an integer k is selected so that it is necessary to keep only the k previous orthogonal vectors for Arnoldi process. The others are not needed in the process and may be discarded. The method can be inexpensively computed by the incomplete orthogonal process. Thus a convenient way for choosing the regularization parameter is presented.

Date Published: 30 November 2009
PDF: 6 pages
Proc. SPIE 7506, 2009 International Conference on Optical Instruments and Technology: Optical Systems and Modern Optoelectronic Instruments, 75062G (30 November 2009); doi: 10.1117/12.837781

Published in SPIE Proceedings Vol. 7506:
2009 International Conference on Optical Instruments and Technology: Optical Systems and Modern Optoelectronic Instruments
Yongtian Wang; Yunlong Sheng; Kimio Tatsuno, Editor(s)