Title :
Using bounded-influence M-estimators in multi-frame super-resolution reconstruction: A comparative study
Author :
El-Yamany, Noha A. ; Papamichalis, Panos E.
Author_Institution :
Dept. of Electr. Eng. Dept., Southern Methodist Univ., Dallas, TX
Abstract :
This paper introduces a comparative study of bounded-influence M-estimators in the context of multi-frame super-resolution reconstruction. The objectives of this study are to compare these estimators in terms of robustness, and to highlight the associated tradeoff between robustness and edge preservation (crispness) in the presence of registration errors and motion outliers.
Keywords :
image motion analysis; image reconstruction; image registration; image resolution; bounded-influence M-estimators; image resolution; motion outliers; multiframe super-resolution reconstruction; registration error; Bismuth; High-resolution imaging; Image reconstruction; Image resolution; Layout; Mathematical model; Motion estimation; Optical noise; Robustness; Strontium; M-estimators; influence function; multi-frame super-resolution;
Conference_Titel :
Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-1765-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2008.4711760
