Документ взят из кэша поисковой машины. Адрес
оригинального документа
: http://www.stsci.edu/stsci/meetings/irw/proceedings/schulzt.dir/section3_3.html
Дата изменения: Mon Apr 18 17:45:42 1994 Дата индексирования: Sun Dec 23 19:49:19 2007 Кодировка: Поисковые слова: vallis |
Following Snyder, Hammoud, and White (1993), we simplify the noise model by defining the modified data
and by considering the situation in which the CCD read-out noise variance is large. In this case, the modified data are approximately equal in distribution to a Poisson process whose mean function is
Therefore, the pseudo-log-likelihood takes the form
where terms that do not depend on the unknown object or parameters
have been omitted. The maximum likelihood estimator of these
parameters will maximize
for a particular
data set
, subject to the
physical constraint that the object estimate be a nonnegative
function. An explicit, closed form solution to this problem is not
known. Therefore, in the next section we propose a technique for
producing estimates numerically by using the expectation-maximization
(EM) algorithm (Dempster et al. 1977).