System and process for automatically analyzing currency objects

• US 10,504,073 B2
• Filed: 01/19/2012
• Issued: 12/10/2019
• Est. Priority Date: 01/19/2011
• Status: Active Grant

• Current Assignee: Alon Atsmon, Dan Atsmon
• Original Assignee: Alon Atsmon, Dan Atsmon
• Inventors: Atsmon, Alon, Atsmon, Dan
• Primary Examiner(s): Borlinghaus, Jason
• Assistant Examiner(s): Alladin, Ambreen A.
• Application Number:
  US13/353,791
• Publication Number:
  US 20120185393A1
• Time in Patent Office: 2,882 Days
• Field of Search: 705 44
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06Q 20/10 specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
• CPC Class Codes: G06Q 20/3276 using a pictured code, e.g. barcode or QR-code, being read by the M-device
• CPC Class Codes: G06Q 20/389 Keeping log of transactions for guaranteeing non-repudiation of a transaction
• CPC Class Codes: G06Q 20/40 Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
• CPC Class Codes: G07D 11/30 Tracking or tracing valuable papers or cassettes
• CPC Class Codes: G07D 7/12 Visible light, infrared or ultraviolet radiation

Abstract

A method, system, and computer program product for analyzing images of visual objects, such as currency and/or payment cards, captured on a mobile device. The analysis allows determining the authenticity and/or total amount of value of the currency and/or payment cards. The system may be used to verify the authenticity of hard currency, to count the total amount of the currency captured in one or more images, and to convert the currency using real time monetary exchange rates. The mobile device may be used to verify the identity of a credit card user by analyzing one or more images of the card holder'"'"'s face and/or card holder'"'"'s signature, card holder'"'"'s name on the card, card number, and/or card security code.

Claims

1. A system for conducting a content analysis of an image depicting a plurality of currency objects, the system comprising a server in network communication with a mobile device, the server comprising:

a hardware processor;

a non-transitory computer readable medium having embodied thereon code instructions that in response to execution by a hardware processor of the server, cause the server to;

receive over a network, a single image captured by at least one camera of the mobile device, the single image depicting at least one currency object of each of a plurality of types of currency objects denoting respective denominations of major world currencies, and location data indicative of location of the mobile device computed by a location based analysis of output of a location data sensor;

conduct a content analysis of the single image, wherein said content analysis comprises;

identifying each of the plurality of types of currency objects,

computing a plurality of keypoint descriptors as a set of orientation histograms on neighboring pixels of said plurality of types of currency objects;

convoluting the captured image with Gaussian filters at different scales to create a plurality of successive Gaussian-blurred images;

wherein the orientation histograms are relative to the orientation of the plurality of keypoints, wherein the orientation data for the orientation histograms is derived from the Gaussian image closest in scale to the scale of each respective keypoint of the plurality of keypoints;

computing a quantity of each currency object of the plurality of types of currency objects;

convert each of the plurality of identified types of currency objects to a common monetary currency in use at the location of the mobile device;

create a currency inventory report comprising a total monetary value of the plurality of types of currency objects when converted to the common monetary currency; and

transmit from the server over the network to said mobile device, the currency inventory report for presentation on a display of said mobile device.

2. The system of claim 1, wherein said content analysis further comprises an analysis of a member selected from a group consisting of the image'"'"'s captured text, visual and symbol data from said captured image, a history of images captured using said mobile device and at least one currency object from a database of known fake currency objects.

3. The system of claim 1, wherein said content analysis further comprises:

calculating a face value of the plurality of types of currency objects, and

calculating a total value by summing the value of each of said plurality of types of currency objects.

4. The system of claim 1, wherein said at least one camera comprises an array of cameras of said mobile device and wherein said capturing is conducted to construct a three dimensional (3D) representation of said plurality of types of currency objects.

5. The system of claim 1, wherein said content analysis comprises performing an authentication of each currency object of said plurality of types of currency objects.

20. The system of claim 1, wherein said plurality of types currency objects include a plurality of types of coins, and said content analysis identifies said plurality of types of coins.

21. The system of claim 1, wherein computing the plurality of keypoints comprises computing the plurality of keypoints as maxima and minima of the differences of the successive Gaussian-blurred images.

22. The system of claim 1, wherein said currency inventory report is presented on said display of said mobile device at the same time as said single image.

23. The system of claim 1, wherein the currency inventory report in the common monetary currency is generated in real time, according to a real time location of the mobile device computed based on said output of the location data sensor and based on the single image captured in real time by the camera of the mobile device.

6. A computer implemented method for utilizing a mobile device to analyze the authenticity and monetary value of currency deposited into a bank account, the method performed by a server in network communication with the mobile device, comprising:

a) receiving by the server over a network, a single image captured by at least one camera of the mobile device, the single image depicting at least one currency object of each of a plurality of types of currency objects denoting respective denominations of major world currencies, and location data indicative of location of the mobile device computed by a location based analysis of output of a location data sensor;

b) conducting by the server a content analysis of said single image, wherein said analysis comprises;

identifying each of the plurality of types of currency objects,

computing a plurality of keypoint descriptors as a set of orientation histograms on neighboring pixels of said plurality of types of currency objects;

convoluting the captured image with Gaussian filters at different scales to create a plurality of successive Gaussian-blurred images;

wherein the orientation histograms are relative to the orientation of the plurality of keypoints, wherein the orientation data for the orientation histograms is derived from the Gaussian image closest in scale to the scale of each respective keypoint of the plurality of keypoints;

computing a quantity of each currency object of the plurality of types of currency objects;

c) converting each of the plurality of identified types of currency objects to a common monetary currency in use at the location of the mobile device;

d) calculating a total monetary value of the plurality of types of currency objects when converted to the common monetary currency;

e) temporarily depositing the total monetary value into a user'"'"'s bank account according to the common monetary currency; and

f) authenticating the plurality of currency objects after receiving an indication of a physical deposit of the plurality of currency objects in the user'"'"'s bank to convert the temporarily deposited monetary value to a permanent deposit.

7. The method of claim 6, wherein said verifying is performed by utilizing light to check for watermarks and UV or signs.

8. The method of claim 6, wherein said content analysis further comprises an analysis of a member selected from a group consisting of the image'"'"'s captured text, currency and symbol data from said captured image, a history of images captured using said mobile device and at least one currency object from a database of known fake currency objects.

9. The method of claim 6, wherein said content analysis further comprises calculating the value of the plurality of types of currency objects in said image by summing the value of each of said plurality of types of currency objects in said image.

10. The method of claim 6, wherein said at least one camera comprises an array of cameras of said mobile device and wherein said capturing is conducted to construct a three dimensional (3D) representation of said plurality of types of currency objects.

11. A non-transitory computer readable medium having embodied thereon code instructions that, when executed by one or more hardware processors of a server in network communication with at least one mobile device, cause the one or more hardware processors of the server to:

a) receive a single image captured using at least one camera of the mobile device, the single image comprising at least one currency object of each of a plurality of types of currency objects denoting respective denominations of major world currencies, and location data indicative of location of the mobile device computed by a location based analysis of output of a location data sensor;

b) conduct a content analysis of the single image, wherein said content analysis comprises;

identifying each of the plurality of types of currency objects;

computing a plurality of keypoint descriptors as a set of orientation histograms on neighboring pixels of said plurality of types of currency objects;

convoluting the captured image with Gaussian filters at different scales to create a plurality of successive Gaussian-blurred images;

wherein the orientation histograms are relative to the orientation of the plurality of keypoints, wherein the orientation data for the orientation histograms is derived from the Gaussian image closest in scale to the scale of each respective keypoint of the plurality of keypoints;

computing a quantity of each currency object of the plurality of types of currency objects;

c) convert each of the plurality of identified types of currency objects to a common monetary currency in use at the location of the mobile device;

d) create a currency inventory report comprising a total monetary value of the plurality of types of currency objects when converted to the common monetary currency; and

e) transmit to said mobile device, the currency inventory report for presentation on a display of said mobile device.

12. The non-transitory computer readable medium of claim 11, wherein said content analysis further comprises an analysis of a member selected from a group consisting of the image'"'"'s captured text, visual and symbol data from said captured image, a history of images captured using said mobile device and at least one currency object from a database of known fake currency objects.

13. The non-transitory computer readable medium of claim 11, wherein said conducting further comprises:

calculating a face value of the plurality of types of currency objects, and

calculating a total value by summing the value of each of said plurality of types of currency objects.

14. The non-transitory computer readable medium of claim 11, wherein said at least one camera comprises an array of cameras of said mobile device and wherein said capturing is conducted to construct a three dimensional (3D) representation of said plurality of types of currency objects.

15. The non-transitory computer readable medium of claim 11, wherein said content analysis comprises performing an authentication of each currency object of said plurality of types of currency objects.

16. The non-transitory computer readable medium of claim 11, wherein said content analysis further comprises comparing differences and similarities between at least one reference image object of a reference image and said image.

17. An internet based system for quantifying and analyzing the authenticity of a plurality of types of currency objects, the system comprising:

a mobile device comprising;

at least one hardware processor;

a non-transitory computer readable medium having embodied thereon code instructions that in response to execution by the at least one hardware processor of the mobile device, cause the mobile device to;

capture a single image that images at least one currency object of each of a plurality of types of currency objects denoting respective denominations of major world currencies, using a camera or a video recorder of a respective said mobile device, and provide location data indicative of location of the mobile device computed by a location based analysis of output of a location data sensor;

a database storing a plurality of reference denominations of major world currencies;

a processor;

non-transitory storage coupled to the processor and storing code that, when executed by the processor, cause the processor to;

apply a decision function to the plurality of types of currency objects to yield an analysis of authenticity of each member of said type of currency object according to a match with said plurality of denominations of major world currencies, wherein a match exists when the decision function is above a designated threshold for authenticity;

wherein the decision function comprises;

identifying each of the plurality of types of currency objects,

computing a plurality of keypoint descriptors as a set of orientation histograms on neighboring pixels of said plurality of types of currency objects;

convoluting the captured image with Gaussian filters at different scales to create a plurality of successive Gaussian-blurred images;

wherein the orientation histograms are relative to the orientation of the plurality of keypoints, wherein the orientation data for the orientation histograms is derived from the Gaussian image closest in scale to the scale of each respective keypoint of the plurality of keypoints;

computing a quantity of each currency object of the plurality of types of currency objects;

convert each of the plurality of identified types of currency objects to a common monetary currency in use at the location of the mobile device;

create a currency inventory report comprising a total monetary value of the plurality of types of currency objects when converted to the common monetary currency; and

generate a currency inventory report and transmit said currency inventory report to said user mobile device for presentation on a display of said mobile device.

18. The system of claim 17, wherein said content analysis further includes determining the authenticity of each currency object of said plurality of types of currency objects based on a content match, wherein said match exists when the content analysis is above a designated threshold for authenticity.

19. The system of claim 17 wherein said plurality of types of currency objects comprises a payment card.