Partial Perceptual Image Hashing for Document Deconstruction
AssigneeBottomline Technologies, Inc.
InventorsShane O'Hara, Mitchell Ransom
Life of this patent
Estimating the term…
Abstract
A system and method for deconstructing a document is described herein, where the method is an improvement over existing document deconstruction techniques. These improvements increase speed and accuracy by rapidly identifying the source in a document by splitting the document into a plurality of sections and performing a perceptual image hashing on each section. Then a hamming distance is used to compare the hash for each section with the hashes of known documents to identify the source who sent the document.
Claims20
An apparatus for identifying a source associated with a new document, the apparatus comprising:
- a special purpose processor with a plurality of cores;
- a memory electrically connected to the special purpose processor;
- and
- a mass storage device holding a database of known sources, the mass storage device electrically connected to the special purpose processor, wherein each known source in the database includes a known source image hash for each of a plurality of known sections of a known source document, said plurality of known sections containing a visually discernable image;
- wherein an image of the new document stored in the memory is split into a plurality of new sections by the special purpose processor, said plurality of new sections containing a visually discernable image,
- a perceptual image hash is calculated by the special purpose processor for each of the plurality of new sections of the new document, and
- a hamming distance is calculated between the perceptual image hash of at least one of the plurality of new sections of the new document and each entry in the database of the known sources for a corresponding section of the known source document, the known source associated with a smallest hamming distance identified as the source associated with the new document.
A method for identifying a source associated with a new document, the method comprising:
- splitting an image of the new document stored in a memory into a plurality of new sections of the new document by a special purpose processor with a plurality of cores, wherein the memory is electrically connected to the special purpose processor, said plurality of new sections containing a visually discernable image;
- calculating a perceptual image hash by the special purpose processor for each of the plurality of new sections of the new document;
- calculating a hamming distance between the perceptual image hash of at least one of the plurality of new sections of the new document and for each entry in a database of known sources for a corresponding section;
- and
- identifying the known source associated with a smallest hamming distance as the source associated with the new document;
- wherein a mass storage device holds the database of the known sources, the mass storage device electrically connected to the special purpose processor.
Dependencies are inferred from the claim text.