Abstract: Various backgrounds, forms, or templates are scanned, features are extracted, and the features are stored in memory. When a composite image is scanned (image of interest plus part of background), features are extracted from the composite image. Features in the composite image are correlated to stored background features to identify which background is present. If necessary, background features from memory are shifted in two dimensions to accommodate displacement of the background. Features corresponding to the background are deleted from the features in the composite image. For forms and templates, features are used to identify the background, and then the information is directly extracted from the composite image.

Abstract: A user interface high-lighter function for scanner software that allows a user to automatically select a portion or several disjoint portions of text within a region of text in a preview scan of a document. When activated, the high-lighter function causes the normal mouse cursor to be replaced with a high-lighter icon having an active edge. Using the mouse, the active edge of the high-lighter icon is moved across a desired portion of text, and background pixels traversed are displayed in a different color. The traversed pixels are then used as input for an image processing routine. Text regions are generated from the traversed pixels. The beginning and ending of lines not high-lighted are cropped. A polygonal bounding box is then displayed around the selected text. An un-highlight mode can be activated to reduce the selected text. An optimized re-scan of the to selected text can now be performed.