Abstract: The method includes segmenting a document image to identify image objects within the document image and applying an automatic algorithm to the image objects so as to assign initial metadata to the image objects. The method further includes selecting image objects from the set of image objects whose metadata satisfy filtration criteria so as to exclude those selected image objects from processing and processing a rest of the image objects in the set of image objects. The method further includes presenting the document image, image objects, and metadata to the user and enabling input from the user to manage the image objects, subsets, and metadata.

Abstract: A method 100 of enabling a user to retrieve information from a digital image is provided. The method includes segmenting a document image at 104 to identify image objects within the document image and applying an automatic algorithm to the image objects so as to assign initial metadata to the image objects at 106. The method 100 further includes selecting image objects from the set of image objects whose metadata satisfy filtration criteria 110 so as to exclude those selected image objects from processing and processing a rest of the image objects in the set of image objects. The method 100 further includes presenting the document image, image objects, and metadata to the user at 116 and enabling input from the user to manage the image objects, subsets, and metadata.

Abstract: A method and a system by which a document image is analyzed for the purposes of establishing a searchable data structure characterizing ground-truthed contents of the document represented by the document image operates by segmenting a document image into a set of image objects, and linking the image objects with fields that store metadata. Image objects identified by segmenting the document image are grouped into subsets. The image objects are grouped according to characteristics suggesting that the image objects may have common ground-truthed metadata. By grouping the image objects into subsets, the image objects may be indexed to facilitate the ground-truthing process. In some embodiments, the index of representative image objects is presented to the user in a table form. A database of image objects with ground-truthed metadata is formed. Interactive tools and processes facilitate ground-truthing based on paired image objects and metadata.

Abstract: A method and a system by which a document image is analyzed for the purposes of establishing a searchable data structure characterizing ground-truthed contents of the document represented by the document image operates by segmenting a document image into a set of image objects, and linking the image objects with fields that store metadata. Image objects identified by segmenting the document image are grouped into subsets. The image objects are grouped according to characteristics suggesting that the image objects may have common ground-truthed metadata. By grouping the image objects into subsets, the image objects may be indexed to facilitate the ground-truthing process. In some embodiments, the index of representative image objects is presented to the user in a table form. A database of image objects with ground-truthed metadata is formed. Interactive tools and processes facilitate ground-truthing based on paired image objects and metadata.

Abstract: The present invention provides an electronic file and file structure solution for comprehensive management of documents captured as scanned objects, raster objects or representation. Using the present invention a representation of a document is created using any type of imaging device. The representation includes objects present in the document. The location in the document of the objects in the plurality of objects is identified. One copy of each different object in the plurality of objects is stored in the file. The location of objects in the plurality of objects are stored in the file in a spatial layout index. The file thus contains all of the information required to faithfully reproduce the original document. In order to reconstruct the document, the objects are placed at the locations identified by the spatial layout index.

Abstract: The present invention is a system and method for character recognition using pattern recognition. In one embodiment of the invention, a plurality of representations of a plurality of characters is received by a system. A plurality of cipher labels are assigned to representations in the plurality of representations. The plaintext identity of cipher labels in the plurality of cipher labels is determined using isomorphic pattern recognition. The present invention includes A plaintext isomorphic dictionary containing plaintext words organized by their root isomorphic patterns. Additionally, the present invention includes a Raster-Plaintext Library which contains extensive data on taster letters, and their plaintext identities, from an exhaustive collection of fonts.