Abstract: Method and apparatus for querying a document image database based on texture, i.e., analytically discernable patterns in the document images of the database. According to the invention, a document image database could be browsed for documents with a particular texture in a variety of ways. For example, a user could input an example document image with a similar appearance to the desired document. Alternatively, the user could employ a simple interface to define a synthetic document based on selection of a few categories. The synthetic document would then serve as an example for search. Or the user may employ a graphical interface to more precisely define an example for search. Thus, the user's knowledge of the general appearance of the desired document or documents provides the basis for the search.

Abstract: An improved document management system with high-speed retrieval by example retrieves a document attaching a target document, in whole or part, by comparing descriptors of documents. A descriptor is derived from a pattern of labels, where each label is associated with a character, or more precisely, a character bounding box. A bounding box is found by examining contiguous pixels in an image. The particular label associated with a bounding box depends on the value of a metric measured from that bounding box. In one system, the metric is the spacing between the bounding box and an adjacent bounding box, in which the labels approximately reflect a pattern of word lengths. In other systems, where words lengths are not present, the metric might be pixel density and the pattern of labels approximately reflect a pattern of denser characters and sparser characters.