Image modeling establishes the relation between an object and its image when an optical microscope is used to measure the dimensions of an object of size comparable to the illumination wavelength. It accounts for the influence of all of the parameters that can affect the image and relates the apparent feature width (FW) in the image to the true FW of the object. The values of these parameters, however, have uncertainties, and these uncertainties propagate through the model and lead to parametric uncertainty in the FW measurement, a key component of the combined measurement uncertainty. The combined uncertainty is required in order to decide if the result is adequate for its intended purpose and to ascertain if it is consistent with other results. The parametric uncertainty for optical photomask measurements derived using an edge intensity threshold approach has been described previously; this paper describes an image library approach to this issue and shows results for optical photomask metrology over a FW range of 10 nm to 8 µm using light of wavelength 365 nm. The principles will be described; a one-dimensional image library will be used; the method of comparing images, along with a simple interpolation method, will be explained; and results will be presented. This method is easily extended to any kind of imaging microscope and to more dimensions in parameter space. It is more general than the edge threshold method and leads to markedly different uncertainties for features smaller than the wavelength.