Title :
A highly robust estimator for computer vision
Author :
Zhuang, Xinhua ; Haralick, Robert M.
Author_Institution :
Dept. of Electr. & Comput. Eng., Missouri Univ., Columbia, MO, USA
Abstract :
The authors present a highly robust estimator called an MF-estimator for general regression. It is argued that the kind of estimators needed by computer vision must be highly robust and that the classical robust estimators do not render a high robustness. It is explained that the high robustness becomes possible only through partially but completely modeling the unknown log likelihood function. Partial modeling explores a number of important heuristics implicit in the regression problem and takes place by taking them into consideration with the Bayes statistical decision rule, while maximizing the log likelihood function. Experiments with the simplest location estimation showed that the performance of the MF-estimator was superior to that of the classical M-estimator
Keywords :
Bayes methods; computer vision; decision theory; estimation theory; pattern recognition; probability; Bayes statistical decision rule; MF-estimator; computer vision; heuristics; log likelihood function; pattern recognition; picture processing; Artificial intelligence; Computer errors; Computer vision; Gaussian noise; Image processing; Machine vision; Motion estimation; Roads; Robustness; Solids;
Conference_Titel :
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location :
Atlantic City, NJ
Print_ISBN :
0-8186-2062-5
DOI :
10.1109/ICPR.1990.118162