System and method for preventing cashier and customer fraud at retail checkout

• US 8,448,859 B2
• Filed: 09/04/2009
• Issued: 05/28/2013
• Est. Priority Date: 09/05/2008
• Status: Active Grant

• Current Assignee: Datalogic Adc, Inc. (Datalogic S.p.A.)
• Original Assignee: Datalogic Adc, Inc. (Datalogic S.p.A.)
• Inventors: Goncalves, Luis, Beghtol, Justin, Gremmer, Isaac, Ostrowski, Jim
• Primary Examiner(s): HESS, DANIEL A
• Application Number:
  US12/554,630
• Publication Number:
  US 20100059589A1
• Time in Patent Office: 1,362 Days
• Field of Search: 235/383
• US Class Current: 235/383
• CPC Class Codes: G06K 5/00 Methods or arrangements for verifying the correctness of markings on a record carrier; Column detection devices
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G07G 1/0054 with control of supplementary check-parameters, e.g. weight or number of articles
• CPC Class Codes: G07G 3/003 Anti-theft control theft alarms G08B13/00
• CPC Class Codes: G08B 13/248 EAS system combined with another detection technology, e.g. dual EAS and video or other presence detection system

Abstract

Systems and methods for preventing fraud during retail checkout are described. A system includes: item identifier acquisition devices to acquire identifiers (e.g., barcodes) of items to be transacted; cameras or imagers to acquire images of the items to be transacted; an object recognition component to perform visual recognition of the acquired items through comparison of the acquired images of the items with a database and obtain identifiers of items represented in the database that correspond to an acquired image according to a correspondence criterion; a comparison component to compare a set of identifiers acquired through the item identifier acquisition devices with a set of identifiers obtained through the object recognition component; and an alerting component to provide an alert in case of discrepancies between the two sets.

Claims

1. A detection method comprising:

acquiring first identifiers of items to be transacted during retail checkout;

acquiring images of the items to be transacted during retail checkout;

comparing the acquired images with a database of item information to obtain presence or absence of second identifiers of items associated with the acquired images;

detecting differences between a set of said first identifiers and a set of said second identifiers by comparing presence or absence of the first identifiers with the presence or absence of the second identifiers, wherein the detecting is adapted to be performed identifier by identifier or between the sets as a whole; and

reporting detected differences between the set of first identifiers and the set of second identifiers based on pricing considerations.

2. The method of claim 1, wherein the first identifiers and the second identifiers are universal product codes.

3. The method of claim 1, wherein acquiring the first identifiers comprises acquiring first identifiers through at least one of a bi-optic scanner, a hand-held scanner and a keyboard.

4. The method of claim 1, wherein comparing the acquired images with the database of item information to obtain second identifiers of items associated with the acquired images comprises:

obtaining at least one second identifier for each item depicted in an acquired image.

5. The method of claim 1, wherein comparing the acquired images with the database of item information to obtain second identifiers of items associated with the acquired images comprises:

for an acquired image, extracting features from the acquired image; and

for the acquired image, comparing the extracted features with the database of item information to obtain, for the acquired image, one or more items that satisfy a matching criterion with the acquired image, wherein the second identifiers are identifiers associated with the one or more items satisfying the matching criterion with the acquired image.

6. The method of claim 1, wherein the acquiring images of the items to be transacted during retail checkout comprises performing motion detection and/or optical flow analysis of a video stream or sequence of images to select images salient to the items to be transacted and/or to separate images pertaining to one item from images pertaining to another item.

7. The method of claim 1, wherein the acquiring of images of the items to be transacted is triggered by the acquiring the first identifiers of items to be transacted.

8. The method of claim 1, further comprising providing an alert if differences between the set of first identifiers and the set of second identifiers have been detected.

9. The method of claim 8, wherein the alert is provided in real time or at a scheduled interval.

10. The method of claim 1, further comprising storing the acquired first identifiers and the acquired images.

11. The method of claim 1, further comprising adding time information to the acquired first identifiers and the acquired images.

12. The method of claim 1, further comprising detecting differences between the set of first identifiers and the set of second identifiers only for a predetermined class of items.

13. The method of claim 1, further comprising reporting detected differences between the set of first identifiers and the set of second identifiers based on a fraud suspicion level.

14. The method of claim 1, wherein the set of first identifiers and the set of second identifiers contain a different number of entries.

15. The method of claim 1, wherein the set of first identifiers and the set of second identifiers are adapted to independently contain no entries, one entry, or multiple entries.

16. The method of claim 1, wherein said detecting differences comprises detecting differences between corresponding first identifiers and second identifiers to detect whether identifier substitution has occurred.

17. The method of claim 1, wherein said detecting differences comprises detecting absence of an expected first identifier with respect to a corresponding second identifier to detect whether scan passing has occurred.

18. The method of claim 1, further comprising suspending a transaction if differences have been detected.

19. The method of claim 1, wherein the set of first identifiers and the set of second identifiers consist of all identifiers pertaining to a same transaction.

20. The method of claim 1, wherein acquiring the first identifiers and acquiring the images occurs between a transaction start and a transaction end to allow the set of first identifiers and the set of second identifiers to consist of all identifiers pertaining to a same transaction.

21. The method of claim 1, wherein comparing the acquired images with the database of item information comprises performing normalized image correlation computation to measure correlation between the acquired images and the item information of the database of item information.

22. The method of claim 1, wherein the reporting detected differences between the set of first identifiers and the set of second identifiers based on pricing considerations, comprises:

determining whether a price of an item associated with the set of second identifiers exceeds a price of the item associated with the set of first identifiers.

23. A detection method comprising:

acquiring first identifiers of items to be transacted during retail checkout;

acquiring images of the items to be transacted during retail checkout;

comparing the acquired images with a database of item information to obtain second identifiers of items associated with the acquired images;

detecting differences between a set of said first identifiers and a set of said second identifiers by comparing the first identifiers with the second identifiers, wherein the detecting is adapted to be performed identifier by identifier or between the sets as a whole; and

when the detecting is performed between the sets as a whole;

finding a maximal subset of pairings between the set of the first identifiers and the set of the second identifiers; and

detecting the presence of unpaired first identifiers and/or second identifiers.

24. The method of claim 23, wherein the detection is fraud detection.

25. A method of detecting discrepancies in identifying items at retail checkout, the method comprising:

reading optical codes from items during an item-identifier acquisition process performed by an operator at retail checkout to define a first set of identifiers corresponding to items identified with an optical code reader;

visually recognizing items represented in image data to define a second set of identifiers corresponding to items recognized via object recognition;

comparing the first and second sets of identifiers to determine which, if any, of the identifiers in one of the first and second sets of identifiers is without a corresponding identifier in the other set of identifiers, and to detect non-corresponding item(s) between the item-identifier acquisition process and the object recognition; and

determining a type of discrepancy based on the detected non-corresponding item(s).

26. The method of claim 25, in which the type of discrepancy is characterized by:

an identifier of the second set of identifiers indicating a recognized item does not correspond to the items identified with the optical code reader.

27. The method of claim 26, further comprising:

providing an alert including information indicating that the items identified with the optical code reader correspond to the items recognized via object recognition.

28. The method of claim 27, further comprising:

providing an alert including information indicating that the recognized item has been omitted from the item-identifier acquisition process.

29. The method of claim 26, in which the type of discrepancy is further characterized by:

an identifier of the first set of identifiers indicating an identified item does not correspond to items recognized via the object recognition.

30. The method of claim 29, further comprising:

providing an alert including information indicating that the identified item has had its optical code substituted for another optical code corresponding to a different item.

31. The method of claim 25, in which the type of discrepancy is characterized by:

a first total number of the items identified with the optical code reader that do not correspond to the items recognized via the object recognition; and

a second total number of the items recognized via the object recognition that do not correspond to the items identified with the optical code reader, and the first total number is less than the second total number.

32. The method of claim 31, further comprising:

providing an alert including information indicating that the first total number corresponds to items that have had optical codes substituted, and indicating that a difference between the second and first total numbers corresponds to items that have been omitted from the item-identifier acquisition process.

33. A system for detecting discrepancies in identifying items at retail checkout, the system comprising:

an optical code reader;

an imager to acquire image data of items during retail checkout; and

circuitry configured to;

read optical codes from items during an item-identifier acquisition process performed by an operator at retail checkout to define a first set of identifiers corresponding to items identified with the optical code reader;

visually recognize items represented in the image data to define a second set of identifiers corresponding to items recognized via object recognition;

compare the first and second sets of identifiers to determine which, if any, of the identifiers in one of the first and second sets of identifiers is without a corresponding identifier in the other set of identifiers, and to detect non-corresponding item(s) between the item-identifier acquisition process and the object recognition; and

determine a type of discrepancy based on the detected non-corresponding item(s).