Method of preventing fraud and theft during automated teller machine transactions and related system

• US 10,460,300 B2
• Filed: 06/01/2016
• Issued: 10/29/2019
• Est. Priority Date: 06/01/2016
• Status: Active Grant

• Current Assignee: ArcSoft, Inc.
• Original Assignee: Multimedia Image Solution Limited
• Inventors: Xu, LianBo, Deng, Hui, Wang, Jin
• Primary Examiner(s): Walsh, Daniel I
• Application Number:
  US15/169,765
• Publication Number:
  US 20170352015A1
• Time in Patent Office: 1,245 Days
• CPC Class Codes: G06Q 20/1085 involving automatic teller machines [ATMs]
• CPC Class Codes: G06Q 20/40145 Biometric identity checks
• CPC Class Codes: G06V 10/273 removing elements interfering with the pattern to be recognised
• CPC Class Codes: G06V 40/113 Recognition of static hand signs
• CPC Class Codes: G06V 40/171 Local features and components; Facial parts eye characteristics G06V40/18; Occluding parts, e.g. glasses; Geometrical relationships
• CPC Class Codes: G07F 19/207 Surveillance aspects at ATMs
• CPC Class Codes: H04N 7/188 Capturing isolated or intermittent images triggered by the occurrence of a predetermined event, e.g. an object reaching a predetermined position signal generation from motion picture films H04N5/253

Abstract

A method of preventing fraud and theft during automated teller machine (ATM) transactions includes recording a video stream using a camera mounted on or near the ATM, the camera being positioned to record the face of a user of the ATM and a background behind the user, providing a facial model database containing images of a large number of people taken from different angles, the facial model database containing images of unobscured faces as well as obscured faces, and receiving insertion of a bank card into the ATM. The method further includes comparing images captured from the recorded video stream with images contained in the facial model database, and producing a corresponding first face comparison result, and issuing a notice for the user to uncover the user'"'"'s face when the first face comparison result indicates that the user'"'"'s face is obscured.

Claims

1. A method of preventing fraud and theft during automated teller machine (ATM) transactions, the method comprising:

recording a video stream using a camera mounted on or near the ATM, the camera being positioned to record the face of a user of the ATM and a background behind the user;

providing a facial model database containing images of a large number of people taken from different angles, the facial model database containing images of unobscured faces as well as obscured faces;

receiving insertion of a bank card into the ATM;

comparing images captured from the recorded video stream with images contained in the facial model database, and producing a corresponding first face comparison result;

issuing a notice for the user to uncover the user'"'"'s face when the first face comparison result indicates that the user'"'"'s face is obscured;

analyzing the recorded video stream to monitor a background behind the user;

detecting at least one unidentified person in the background;

recording the face of the at least one unidentified person;

comparing images of the at least one unidentified person with images contained in the facial model database, and producing a corresponding second face comparison result and

issuing a warning when the second face comparison result indicates that the at least one unidentified person'"'"'s face is obscured.

2. The method of claim 1, further comprising preventing the user from withdrawing or transferring money through the ATM when the first face comparison result indicates that the user'"'"'s face is still obscured after issuing the notice for the user to uncover the user'"'"'s face.

3. The method of claim 1, further comprising recording images of the user'"'"'s face and associating the recorded images with an account corresponding to the bank card inserted into the ATM.

4. The method of claim 3, further comprising:

comparing recorded images of the user'"'"'s face with other facial images previously recorded and associated with the account corresponding to the bank card inserted into the ATM; and

alerting authorities when the recorded images of the user'"'"'s face do not match the other facial images previously recorded and associated with the account corresponding to the bank card inserted into the ATM.

5. The method of claim 3, further comprising:

comparing recorded images of the user'"'"'s face with facial images previously recorded of people included on a watch list; and

alerting authorities when the recorded images of the user'"'"'s face match facial images of one or more people included on the watch list.

6. The method of claim 1, further comprising providing a body gesture model database containing images of a large number of different body gestures, with some of the body gestures in the body gesture model database indicating a first type of behavior and other body gestures in the body gesture model database indicating a second type of behavior.

7. The method of claim 6, further comprising:

comparing images of the user with images contained in the body gesture model database, and producing a corresponding gesture comparison result; and

alerting authorities when the gesture comparison result indicates that the user is exhibiting the second type of behavior.

8. The method of claim 1, further comprising issuing a notice for the at least one unidentified person to keep a safe distance from the user upon detecting the at least one unidentified person.

9. The method of claim 1, further comprising:

comparing images of the at least one unidentified person with images contained in the body gesture model database, and producing a corresponding gesture comparison result; and

alerting authorities when the gesture comparison result indicates that the at least one unidentified person is exhibiting the second type of behavior.

10. The method of claim 1, further comprising alerting authorities when the second face comparison result indicates that the at least one unidentified person'"'"'s face is obscured.

11. The method of claim 1, further comprising:

analyzing the recorded video stream to monitor the ATM and a surrounding area of the ATM; and

alerting authorities when detecting that the ATM or the surrounding area of the ATM have been damaged.

12. The method of claim 1, further comprising:

analyzing the recorded video stream to determine if the camera is being blocked; and

preventing the user from withdrawing or transferring money through the ATM when determining that the camera is being blocked.

13. A system of preventing fraud and theft during automated teller machine (ATM) transactions, the system comprising:

an ATM, the ATM comprising;

a first processor for controlling operation of the ATM;

a card slot for receiving insertion of a bank card into the card slot; and

a user interface;

a camera mounted on or near the ATM, the camera recording a video stream and being positioned to record the face of a user of the ATM and a background behind the user;

a facial model database containing images of a large number of people taken from different angles, the facial model database containing images of unobscured faces as well as obscured faces;

a monitoring device comprising a second processor, the monitoring device comparing images captured from the recorded video stream with images contained in the facial model database, and producing a corresponding first face comparison result wherein the user interface of the ATM issues a notice for the user to uncover the user'"'"'s face when the first face comparison result indicates that the user'"'"'s face is obscured;

analyzing the recorded video stream to monitor a background behind the user;

detecting at least one unidentified person in the background;

recording the face of the at least one unidentified person;

comparing images of the at least one unidentified person with images contained in the facial model database, and producing a corresponding second face comparison result; and

issuing a warning when the second face comparison result indicates that the at least one unidentified person'"'"'s face is obscured.

14. The system of claim 13, wherein the user interface prevents the user from withdrawing or transferring money through the ATM when the first face comparison result indicates that the user'"'"'s face is still obscured after issuing the notice for the user to uncover the user'"'"'s face.

15. The system of claim 13, further comprising:

a user face database containing facial images previously recorded and associated with the account corresponding to the bank card inserted into the ATM;

wherein the monitoring device compares recorded images of the user'"'"'s face with other facial images stored in the user face database associated with the account corresponding to the bank card inserted into the ATM, and alerts authorities when the recorded images of the user'"'"'s face do not match the other facial images stored in the user face database associated with the account corresponding to the bank card inserted into the ATM.

16. The system of claim 13, further comprising:

a body gesture model database containing images of a large number of different body gestures, with some of the body gestures in the body gesture model database indicating a first type of behavior and other body gestures in the body gesture model database indicating a second type of behavior;

wherein the monitoring device compares the images captured from the recorded video stream with images contained in the body gesture model database, produces a corresponding gesture comparison result, and alerts authorities when the gesture comparison result indicates that the user or that at least one unidentified person in a background behind the user is exhibiting the second type of behavior.

17. The system of claim 13, further comprising:

a watch list database comprising names and associated facial images of people included on a watch list;

wherein the monitoring device compares recorded images of the user'"'"'s face with facial images contained in the watch list database, and alerts authorities when the recorded images of the user'"'"'s face match facial images of one or more people included on the watch list.