Controlled authentication of physical objects

Abstract

A physical object is scanned and a digital image of the object is generated from the scan. At least one subset of the image, known as an “authentication region” is selected. A plurality of feature vectors, arising from the physical structure of the object, are extracted from certain locations of interest within an authentication region and combined to generate a unique identifier or “digital fingerprint” for that object. Preferably, authentication regions for feature vector extraction are automatically selected by a software process. To identify or authenticate an object, a system may compare a digital fingerprint of an object to digital fingerprints previously stored in a database. Digital fingerprint data may specify a set of features (also termed “locations of interest”) which may be referenced in the creation of a “fingerprint template” which is a template of certain locations of interest and/or attributes selected for authenticating a particular class of objects.

1 . A currency handling device comprising:
 a piece of note handling equipment configured to process a note within a controlled induction environment;   an image capture device integrated with the piece of note handling equipment, the image capture device configured to capture digital image data of at least a portion of the note as the note is processed by the piece of note handling equipment and before the note leaves the controlled induction environment; and   a processor coupled to the image capture device, the processor configured to attempt to authenticate the note by:
 selecting at least one authentication region of the digital image data captured by the image capture device; 
 analyzing the at least one authentication region of the digital image data to form a digital fingerprint of the note, wherein the digital fingerprint comprises:
 for each authentication region of the at least one authentication region:
 data identifying the authentication region, the data including a location of the authentication region in the digital image data; 
 data identifying at least one location of interest in the authentication region; and 
 for each location of interest of the at least one authentication region, data identifying at least one feature vector that characterizes the location of interest; and 
 
 data identifying at least one of the currency handling device, the piece of note handling equipment, and the controlled induction environment; 
 
 storing the digital fingerprint in a database before the note leaves the controlled induction environment; 
 extracting at least one image feature from the digital image data; 
 converting the at least one image feature to at least one image feature vector; 
 accessing the database to retrieve the digital fingerprint; and 
 comparing the at least one image feature vector to the digital fingerprint. 
   
     
     
         2 . The currency handling device of  claim 1 , wherein the note processed by the piece of note handling equipment comprises at least one of a paper note, paper bill, coin, or any other item of currency having a monetary value. 
     
     
         3 . The currency handling device of  claim 1 , wherein the piece of note handling equipment is configured to stack, count, and strap paper money notes. 
     
     
         4 . The currency handling device of  claim 1 , wherein the image capture device comprises at least one of a scanner, a camera, a specially-adapted sensor array from any of a CCD array, an imaging microscope, a smart phone camera, a video camera, an x-ray machine, or any other imaging capture device responsive to electromagnetic radiation. 
     
     
         5 . The currency handling device of  claim 1 , wherein the processor is further configured to automatically select the at least one authentication region based on a predetermined fingerprint template. 
     
     
         6 . The currency handling device of  claim 5 , wherein the predetermined fingerprint template comprises a stored data structure that specifies a class of currency objects of which the note is a member, at least one authentication region for the class of currency objects, and at least one location of interest within the authentication region for generating the digital fingerprint of the note. 
     
     
         7 . The currency handling device of  claim 5 , wherein the predetermined fingerprint template is stored in a secure database to keep the location of the authentication region secret. 
     
     
         8 . The currency handling device of  claim 1 , wherein the processor is further configured to:
 convert each feature vector within the digital fingerprint into an encrypted feature vector; and   store each encrypted feature vector in a secure database.   
     
     
         9 . The currency handling device of  claim 1 , wherein the digital image data includes a note serial number corresponding to the note and the database includes a plurality of digital fingerprints, wherein each digital fingerprint included in the plurality of digital fingerprints is associated with a note serial number for a particular note. 
     
     
         10 . The currency handling device of  claim 9 , wherein the processor is further configured to:
 extract the note serial number from the digital image data;   access the database; and   lookup the note serial number for the note in the database to retrieve the digital fingerprint.   
     
     
         11 . The currency handling device of  claim 1 , wherein the processor is further configured to generate at least one of an indication of authenticity and a result of suspected non-authenticity for the note based on the comparison between the at least one image feature vector and the digital fingerprint. 
     
     
         12 . The currency handling device of  claim 11 , wherein the processor is further configured to generate a confidence metric associated with the at least one of the indication of authenticity and the result of suspected non-authenticity. 
     
     
         13 . The currency handling device of  claim 11 , wherein the result of suspected non-authenticity includes a sequence number indicating a strap number and a position of the note within a strap of 100 notes held together by a single paper band. 
     
     
         14 . A currency handling device comprising:
 a piece of note handling equipment configured to accept a note presented for deposit;   an image capture device integrated with the piece of note handling equipment, the image capture device configured to capture digital image data of a portion of the note; and   a processor coupled to the image capture device, the processor configured to attempt to authenticate the note as the note is accepted by the piece of note handling equipment by:   extracting at least one image feature from the digital image data;   converting the at least one image feature into at least one image feature vector;   accessing a database including a plurality digital fingerprints, wherein each digital fingerprint within the plurality of digital fingerprints corresponds to a particular note and each digital fingerprint comprises:
 at least one authentication region, for each authentication region:
 data identifying the authentication region, the data including a location of the authentication region in digital image data of a portion of a particular note corresponding to a particular digital fingerprint; 
 data identifying at least one location of interest in the authentication region; and 
 for each location of interest of the at least one authentication region, data identifying at least one feature vector that characterizes the location of interest; and 
 
 data identifying at least one of the currency handling device, the piece of note handling equipment, and a controlled induction environment in which a particular digital fingerprint was formed; and 
   comparing the at least one image feature vector to at least one digital fingerprint included in the database.   
     
     
         15 . The currency handling device of  claim 14 , wherein the digital image data includes a note serial number corresponding to the note and the plurality of digital fingerprints in the database is indexed by note serial numbers so that each note corresponding to a digital fingerprint is associated with a unique note serial number. 
     
     
         16 . The currency handling device of  claim 15 , wherein the processor is further configured to attempt to authenticate the note by:
 extracting the note serial number corresponding to the note from the digital image data;   querying the database to retrieve a digital fingerprint associated with the note serial number; and   comparing the at least one image feature vector to the digital fingerprint associated with the note serial number.   
     
     
         17 . The currency handling device of  claim 14 , wherein the processor is further configured to:
 generate at least one of an indication of authenticity and a result of suspected non-authenticity for the note based on the comparison between the at least one image feature vector and the digital fingerprint; and   associate the result of suspected non-authenticity with an identifier for the note to facilitate identification of the note by the currency handling device.   
     
     
         18 . The currency handling device of  claim 14 , wherein the currency handling device is at least one of an ATM machine and a currency counter. 
     
     
         19 . A method comprising:
 scanning a note presented for deposit or exchange using a portable optical device configured to capture digital image data of a portion of the note;   attempting to authenticate the note using a processor coupled to the portable optical device, the processor configured to execute instructions causing the processor to:   receive the digital image data;   extract at least one image feature from the digital image data;   convert the at least one image feature into at least one image feature vector;   access a database including a digital fingerprint for the note; wherein the digital fingerprint includes:
 at least one authentication region, for each authentication region:
 data identifying the authentication region, the data including a location of the authentication region in digital image data of a portion of the note; 
 data identifying at least one location of interest in the authentication region; and 
 for each location of interest of the at least one authentication region, data identifying at least one feature vector that characterizes the location of interest; and 
 
 data identifying at least one of a controlled induction environment in which the digital fingerprint was formed and a piece of note handling equipment that processed the note within the controlled induction environment; and 
   compare the at least one image feature vector to the digital fingerprint.   
     
     
         20 . The method of  claim 19 , wherein the at least one feature vector of the note is unique to at least one of a paper and a printing of the note. 
     
     
         21 . The method of  claim 19 , wherein the portable optical device is installed at least one of a bank teller station and a money counter. 
     
     
         22 . The method of  claim 19 , further comprising:
 determining a result of suspected non-authenticity for the note based on the comparison between the image feature vector and the digital fingerprint; and   refusing to exchange the note for other currency.