There are a large number of application fields where measurements deriving
from digital images can assume a great relevance. Nevertheless, to make a p
rofitable use of such measurements, it is indispensable to achieve a comple
te and quantitative control on uncertainties that real systems introduce al
ong the chain of steps going from real-world objects to the results of the
measurement process, This paper deals with this nontrivial task and, in par
ticular, with the analytical expression of uncertainty characterizing the r
esults of image processing software. At first, a simplified model of uncert
ainty of digital images is derived and experimentally tested; then the Cann
y edge detector output uncertainty is analytically expressed and verified b
oth in artificial and real-world images.