System and method for detecting fraudulent transactions of items having item-identifying indicia

• US 7,422,147 B2
• Filed: 12/22/2006
• Issued: 09/09/2008
• Est. Priority Date: 12/22/2006
• Status: Expired due to Fees

• Current Assignee: Walter Steven Rosenbaum
• Original Assignee: Walter Steven Rosenbaum
• Inventors: Rosenbaum, Walter Steven
• Primary Examiner(s): Lee; Michael G.
• Assistant Examiner(s): SHARIFZADEH, ALI REZA
• Application Number:
  US11/615,003
• Publication Number:
  US 20080149725A1
• Time in Patent Office: 627 Days
• Field of Search: 235/385, 235/383, 235/435
• US Class Current: 235/383
• CPC Class Codes: G06Q 20/20 Point-of-sale [POS] network systems
• CPC Class Codes: G07G 1/0054 with control of supplementary check-parameters, e.g. weight or number of articles
• CPC Class Codes: G07G 3/006 False operation

Abstract

A method of detecting a fraudulent transaction of an item having an item-identifying indicium processes the indicium to obtain item-identifying information, and captures a digital representation of a surface area of the item. The item-identifying information is used to retrieve a stored digital representation of the surface area of the item. Further, the method compares the captured digital representation with the stored digital representation to determine if the captured digital representation corresponds to the stored digital representation.

Claims

1. A method of detecting a fraudulent transaction of an item having an item-identifying indicium, wherein the item-identifying indicium includes at least one of a bar code, an RFID tag, a magnetic stripe, a pattern code, a two-dimensional bar code and a non-visible identification sign, the method comprising:

processing the indicium to obtain item-identifying information stored in a data base, the item-identifying information being associated in the data base with a stored digital image of a surface area of the item;

capturing a digital image of a predetermined surface area of an item using a digital image acquisition device;

transferring the captured digital image from the digital image acquisition device to a processor;

using the item-identifying information to retrieve the stored digital image of the surface area of the item associated with the item-identifying information;

transferring the stored digital image from the data base to the processor; and

subjecting the captured digital image and the stored digital image in the processor to an orientation invariant digital pattern match algorithm that computes a correlation value between the captured digital image and the stored digital image to determine if the captured digital image corresponds to the stored digital image as a function of a predetermined correlation threshold value.

2. The method of claim 1, further comprising generating a notification if the captured digital image does not correspond to the stored digital image, wherein the notification is indicative of a fraudulent item.

3. The method of claim 2, wherein the notification includes at least one of audio, visual and vibration signals.

4. The method of claim 3, wherein the notification includes a presentation of product identification information relating to the fraudulent item.

5. The method of claim 1, wherein using the item-identifying information to retrieve a stored digital image includes accessing a data base that includes for each item an item data set including item-identifying information and an associated digital image of the item.

6. The method of claim 1, wherein the digital image of the surface area is captured of one of a packaging surrounding an immediate area of a printed indicium, a selected or random area away from the printed indicium, and an entire packaging.

7. The method of claim 1, wherein the correlation algorithm is a Fourier-Mellin class of algorithm.

8. The method of claim 7, wherein the correlation algorithm compares the determined correlation value with the correlation threshold value, and wherein a fraudulent item transaction is detected if the determined correlation value is lower than the correlation threshold value.

9. The method of claim 1, where correlation is achieved via at least one of color patterns, character string optical character recognition and spatial relationships.

10. A system for detecting a fraudulent transaction of an item having an item-identifying indicium, wherein the item-identifying indicium includes at least one of a bar code, an RFID tag, a magnetic stripe, a pattern code, a two-dimensional bar code and a non-visible identification sign, the system comprising:

a memory device containing a data base configured to store item-identifying information associated with a stored digital image of a surface area of the item;

a reader configured to process the indicium to obtain item-identifying information stored in the data base;

an imaging device configured to capture a digital image of a predetermined surface area of an item; and

a processor coupled to the reader, the imaging device and the memory device, wherein the processor is configured to use the item-identifying information to retrieve the stored digital image of the surface area of the item associated with the item-identifying information from the data base of the memory device, and to subject the captured digital image and the stored digital image to an orientation invariant digital pattern match algorithm that computes a correlation value between the captured digital image and the stored digital image to determine if the captured digital image corresponds to the stored digital image as a function of a predetermined correlation threshold value.

11. The system of claim 10, wherein the processor is further configured to generate a notification if the captured digital image does not correspond to the stored digital image, wherein the notification is indicative of a fraudulent item.

12. The system of claim 11, wherein the processor is coupled to means for generating at least one of audio, visual and vibration notification signals.

13. The system of claim 11, wherein the notification includes a presentation of product identification information relating to the fraudulent item.

14. The system of claim 10, wherein the data base includes for each item an item data set including item-identifying information and an associated digital image of the item.

15. The system of claim 10, wherein the imaging device is configured to capture a digital image of one of a packaging surrounding an immediate area of a printed indicium, a selected or random area away from the printed indicium, and an entire packaging.

16. The system of claim 10, wherein the processor is configured to perform a Fourier-Mellin class of correlation algorithm.

17. The system of claim 10, wherein the correlation algorithm compares the determined correlation value with the correlation threshold value, and wherein a fraudulent item is detected if the determined correlation value is lower than the correlation threshold value.