Suppose we have an empty form scanned in a b & w tiff file. We scan some filled forms and we could use form template to detect wich kind of form are the filled forms, even we could use the anchoring mecanism in order to detect some zones of the form (that we define on the empty form). It will be great if we could make a DropOut of the filled form: that's is, a new Image deleting from the filled form the data that appears on the empty form, so we could obtain an image only with the data filled by the users. This way we could make a better OCR, for example. If you don't understand what I mean, please, let me know and I'll send you some examples.