The disclosure relates to methods and systems for automatically focusing multiple images of one or more objects on a substrate. The methods include obtaining, by a processor, a representative focal distance for a first location on the substrate based on a set of focal distances at known locations on the substrate. The methods also include acquiring, by an image acquisition device, a set of at least two images of the first location. The images are each acquired using a different focal distance at an offset from the representative focal distance. The methods further include estimating, by a processor, an ideal focal distance corresponding to the first location based on comparing a quality of focus for each of the images, and storing the estimated ideal focal distance and the first location in the set of focal distances at known locations.