producer accuracy are two widely used measures of class
accuracy. The producer’s accuracy refers to the probability that a
certain land-cover of an area on the ground is classified as such,
while the user’s accuracy refers to the probability that a pixel
labeled as a certain land-cover class in the map is really this class.
The user and producer accuracy for any given class typically are
not the same. In the above example, an estimate for the producer
accuracy of water is 46 75.4%
61 = while the user accuracy is 46 92%
50 = .
As a user of a classification, I can expect that roughly 92% of all
the pixels classified as water are indeed water on the ground.
However, as a producer, I am quite unsettled by the fact that I only
classified 75.4% of all the water pixels as such