These assertions are tested on a large set of randomized input images, to handle the worst cases.

The resulting image will be more informative than any of the input images.

Let's say that we want to check if a model image can be seen in an input image.

Find interesting feature points in the input image.

If there isn't a suitable arbitrary basis, then it is likely that the input image does not contain the target object.

Compare all the transformed point features in the input image with the hash table.

So the element with the highest value tells what line that is most represented in the input image.

This allows the algorithm to run on an arbitrarily large number of input images.

The acquisition of images (producing the input image in the first place) is referred to as imaging.

Once installed, it can be invoked by specifying the input images.