PREDICTIVE THEFT NOTIFICATION FOR THE PREVENTION OF THEFT

• US 20140254890A1
• Filed: 03/05/2013
• Published: 09/11/2014
• Est. Priority Date: 03/05/2013
• Status: Active Grant

• Current Assignee: Sensormatic Electronics LLC (Johnson Controls International plc)
• Original Assignee: David R. Noone
• Inventors: Bergman, Adam S., Noone, David R.
• Granted Patent: US 9,135,499 B2
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G08B 13/19697 Arrangements wherein non-video detectors generate an alarm themselves
• CPC Class Codes: G08B 13/248 EAS system combined with another detection technology, e.g. dual EAS and video or other presence detection system
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data

Abstract

Predictive theft notifications are used to coordinate appropriate responses to persons who are likely to commit acts of theft. Image data is generated and processed in a computer processing device to recognize the presence of a facial image comprising a face of a person. An analysis is performed of data representative of the facial image to determine a biometric match relative to one or more biometric models of facial images stored in a database. Based on this analysis, at least one predictive notification is generated with regard to a future potential theft of merchandise from the secured facility. The predictive notification is generated based upon a determination of the biometric match.

Claims

1. A method for predictive theft intervention at a secured facility, comprising:

generating image data using at least one imaging device;

processing the image data in a computer processing device to recognize the presence of a facial image comprising a face of a person within the image data;

performing an analysis of data representative of the facial image to determine a biometric match relative to at least one of a plurality of biometric models of facial images stored in a database; and

generating at least one predictive notification of a future potential theft of merchandise from the secured facility responsive to a determination of the biometric match.

2. The method according to claim 1, wherein the processing to recognize the presence of said facial image is performed at an EAS pedestal.

3. The method according to claim 2, wherein the analysis to determine a biometric match is performed at an EAS server at a location remote from the EAS pedestal.

4. The method according to claim 1, further comprising storing at least one said biometric model in the database responsive to a determination that an EAS tag has been detected in an EAS detection zone.

5. The method according to claim 4, further comprising creating the at least one biometric model based upon a facial image which was captured during a time period associated with a detected presence of the EAS tag in the detection zone.

6. The method according to claim 1, further comprising storing in the database information concerning one or more occurrences of EAS tags being detected in an EAS detection zone and respectively associating each the occurrence with at least one of the biometric models.

7. The method according to claim 6, wherein the information specifies a quantity of the occurrences which are associated with each the biometric model.

8. The method according to claim 6, wherein the information specifies a merchandise item or class of merchandise which was attached to the EAS tag detected.

9. The method according to claim 6, wherein the information specifies a value of merchandise which was attached to an EAS tag detected during each the occurrence.

10. The method according to claim 1, further comprising calculating an EAS score for one or more of the biometric models stored in the database, the EAS score specifying a theft risk associated with a person identified by the biometric model.

11. The method according to claim 10, further comprising calculating the EAS score for each biometric model based on one or more theft risk factors attributed to the biometric model, the theft risk factors selected from the group consisting of a number of the EAS tag detection events, a number of store visits, and a value of merchandise indicated by the EAS tag detected.

12. The method according to claim 1, wherein the predictive notification includes at least one indicator of a relative level of theft risk associated with a particular person corresponding to the biometric model.

13. The method according to claim 1, wherein the predictive notification includes at least one indicator of a specific item or merchandise or class of merchandise at risk of theft.

14. A system for predictive theft intervention at a secured facility, comprising:

at least one imaging device arranged to generate image data;

at least one computer processing device configured to

recognize the presence of a facial image comprising a face of a person within the image data,

perform an analysis of data representative of the facial image to determine a biometric match relative to at least one of a plurality of biometric models of facial images stored in a database, and

generate at least one predictive notification of a future potential theft of merchandise from the secured facility responsive to a determination of the biometric match.

15. The system according to claim 14, wherein the at least one computer processing device which determines the presence of the facial image is located at an EAS pedestal.

16. The system according to claim 15, wherein at least a second computer processing device which is configured to perform the analysis is located at an EAS server at a location remote from the EAS pedestal.

17. The system according to claim 14, wherein the at least one computer processing device processor is configured to store at least one the biometric model in the database responsive to a determination that an EAS tag has been detected in an EAS detection zone.

18. The system according to claim 17, wherein the at least one processor is configured to create the at least one biometric model based upon a facial image which was captured during a time period associated with a detected presence of the EAS tag in the detection zone.

19. The system according to claim 14, wherein the at least one processor is configured to store in the database information concerning one or more occurrences of EAS tags being detected in an EAS detection zone and to respectively associate each the occurrence with at least one of the biometric models.

20. The system according to claim 19, wherein the information specifies a quantity of the occurrences which are associated with each the biometric model.

21. The system according to claim 19, wherein the information specifies a merchandise item or class of merchandise which was attached to the EAS tag detected.

22. The system according to claim 19, wherein the information specifies a value of merchandise which was attached to an EAS tag detected during each the occurrence.

23. The system according to claim 14, wherein the at least one processor is configured to calculate an EAS score for one or more of the biometric models stored in the database, the EAS score specifying a theft risk associated with a person identified by the biometric model.

24. The system according to claim 23, wherein the at least one processor is configured to calculate the EAS score for each biometric model based on one or more theft risk factors attributed to the biometric model, the theft risk factors selected from the group consisting of a number of the EAS tag detection events, a number of store visits, and a value of merchandise indicated by the EAS tag detected.

25. The system according to claim 14, wherein the predictive notification includes at least one indicator of a relative level of theft risk associated with a particular person corresponding to the biometric model.

26. The system according to claim 14, wherein the predictive notification includes at least one indicator of a specific item or merchandise or class of merchandise at risk of theft.

27. A method for predictive theft intervention at a secured facility, comprising:

providing a database comprising a plurality of biometric models corresponding to faces of persons who have triggered an EAS alarm on at least one occasion;

generating image data using at least one imaging device at said secured facility;

processing the image data in a computer processing device to recognize the presence of a facial image comprising a face of a person within the image data;

performing an analysis of data representative of the facial image to determine a biometric match relative to at least one of the plurality of biometric models stored in the database; and

generating at least one predictive notification of a future potential theft of merchandise from the secured facility responsive to a determination of the biometric match.