Abstract: A system and method automatically detects user defined zones in a document image of a form, compensating for skew and displacement of the image with respect to a original image of form. The system provides a mechanism to input an image for a form document, such as a scanner. The system processes the image to reduce its resolution and to remove significant skew. The image is presented to the user to define the zones. These zones are areas from which the user desires to extract meaningful data through optical character recognition, such as names, dates, addresses, and items on a invoice form. The system further processes the image to remove horizontal and vertical lines, and to create a number of blocks, representing either text or image data. The lines are removed and the blocks formed by runlength smoothing with various parameters. The blocks form clusters of connected pixels. The blocks are labeled such that any set of connected blocks share a unique identification value.

Abstract: A system and method provides for indexing and retrieval of stored documents using a decomposition of words in the documents in n-grams, or linear word subunits. The documents are indexed as pages in a number of banks. For each bank there is a bank index. The individual n-grams are identified for each page are stored in the bank index. Each bank index further contains an entry map that indicates whether a given n-gram is present in any of the pages of the bank, and then provides an index to a page map that further indicates which page in the bank contains the n-gram. When a search query is input, the query words are decomposed into their n-grams. The query word n-grams are compared first with entry maps to determine if the query word n-grams appear on any page in the bank. If so, the associated page map is traversed to determine which page in the bank contains the query word n-grams. The n-grams on the page are compared with the query word n-grams to determine the presence of an match therebetween.