Method of Retrieving Information from a Digital Image
OwnerCameron Telfer Howieinventor
Life of this patent
Estimating the term…
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.
Claims20
A method of enabling a user to retrieve information from a document image, the method including:
- segmenting the document image to identify a set of image objects within the document image;
- creating machine readable data structures linking the image objects with metadata fields;
- applying an automatic algorithm to the image objects so as to assign initial metadata to the linked metadata fields;
- selecting image objects from the set of image objects whose metadata satisfy filtration criteria specified by at least one user, so as to exclude those selected image objects from processing;
- processing a rest of the image objects in the set of image objects so as to group the rest of the image objects into a plurality of subsets, each subset including one or more image objects;
- presenting the document image, image objects, and metadata to the at least one user;
- and
- enabling input from the at least one user so as to manage the image objects, subsets, and metadata.
A system for retrieving information from a document image, the system including a user input device, a display, a memory, a document image stored in the memory and information for enabling a user to retrieve information from the document image, the information including instructions for:
- segmenting the document image to identify a set of image objects within the document image;
- creating machine readable data structures linking the image objects to metadata fields;
- assigning initial metadata to the metadata fields by means of an automatic algorithm;
- selecting image objects from the set of image objects whose metadata satisfy filtration criteria as specified by a user, so as to exclude such selected image objects from processing;
- processing a rest of the image objects in the set of image objects so as to group the rest of the image objects into a plurality of subsets, each subset including one or more image objects;
- presenting the document image, image objects, and metadata on the display;
- and
- enabling input by means of the user input device so as to manage the image objects, subsets, and metadata.
Dependencies are inferred from the claim text.