Method and system for verifying user identity using card features

• US 10,248,954 B2
• Filed: 06/15/2015
• Issued: 04/02/2019
• Est. Priority Date: 08/14/2014
• Status: Active Grant

• Current Assignee: Advanced New Technologies Company Limited (Ant Group Co., Ltd.)
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Jin, Weian, Zhang, Jie
• Primary Examiner(s): Trotter, Scott S
• Application Number:
  US14/739,711
• Publication Number:
  US 20160048837A1
• Time in Patent Office: 1,387 Days
• Field of Search: 705 76
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06F 2218/08 Feature extraction
• CPC Class Codes: G06F 2218/12 Classification; Matching
• 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 20/4014 Identity check for transactions
• CPC Class Codes: G06Q 20/409 Device specific authentication in transaction processing
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/513 Sparse representations
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching

Abstract

One embodiment of the present invention provides a system that facilitates identity verification based on various features of a card. During operation, a server receives a request for identity verification, where the request corresponds to an account and includes an image of a verifiable card. The server extracts a card feature from the verifiable card image for use as a verifiable card feature. In response to determining that the verifiable card feature matches a corresponding card feature of a registered card of the account, the server determines successful identity verification.

Claims

1. A computer-implemented method for verifying identity, the method comprising:

registering, by an authorized user, a physical card for subsequent verification by a server by submitting a digital image of the physical card;

receiving, by the server, a request for identity verification of a user for an online transaction, wherein the request corresponds to an account and includes a digital image of a verifiable physical card;

extracting, based on an image-processing technique, a first card feature from the verifiable card image, wherein an extracted card feature includes a physical feature associated with a physical card or private information of the user;

extracting, based on the image-processing technique, a second card feature from a digital image of a registered physical card which corresponds to the account, wherein the second card feature is encrypted based on an encryption algorithm;

decrypting the encrypted second card feature based on a decryption algorithm which corresponds to the encryption algorithm; and

in response to determining that the first card feature matches the decrypted second card feature, determining successful identity verification,

which causes the user to proceed with the online transaction based on the verifiable physical card.

2. The method of claim 1, further comprising:

receiving the digital image of the registered card; and

storing the extracted second card feature.

3. The method of claim 1, wherein a card feature extracted from a corresponding card image of the verifiable card or the registered card is one or more of:

a number feature;

a pattern feature;

a material feature; and

a graphic feature, wherein the graphic feature is one or more of;

a character feature;

a logo feature; and

a signature feature; and

wherein the method further comprises;

determining that each of one or more verifiable card features matches a corresponding one or more registered card features.

4. The method of claim 3, wherein the extracted card feature is a number feature which includes number information associated with the corresponding card image,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

converting the card image into a grayscale image;

determining a rectangular image area from the grayscale image that includes the number information; and

identifying the number information in the rectangular image area; and

in response to determining that the number information from the verifiable card feature matches the number information from the registered card feature, determining that the number feature of the verifiable card matches the number feature of the registered card.

5. The method of claim 4, wherein determining the rectangular image area comprises one or more steps of:

identifying a template which corresponds to the card image, and determining the rectangular image area based on area and position information from the template;

and

segmenting the card image horizontally based on an edge detection algorithm, and determining the rectangular image area based on the segmented card image.

6. The method of claim 4, wherein identifying the number information in the rectangular image area comprises:

segmenting the rectangular image area vertically based on an edge detection algorithm;

determining a plurality of images of numbers based on the segmented rectangular image area, wherein each of the number images is an identifiable number image that includes an identifiable number;

identifying one or more feature values for each identifiable number image;

for each of one or more sample number images stored by the server, calculating a logical distance between the feature value for a respective identifiable number image and a corresponding feature value for the sample number image based on a classification algorithm; and

in response to selecting one of the sample number images based on a shortest calculated logical distance, wherein the selected sample number image includes a number, determining that the identifiable number included in the identifiable number image is the number included in the selected sample number image.

7. The method of claim 3, wherein the extracted card feature is a pattern feature,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

normalizing a size of the card image based on a predetermined size;

extracting a predetermined number of image blocks from the normalized card image based on a predetermined position and a predetermined size;

assigning a pixel value for each of the predetermined number of image blocks based on a sample set normalization for a respective image block;

determining a local feature for the respective image block based on a dictionary learning method; and

identifying an image feature of the card image based on the local feature and a pooling technology;

calculating a logical distance between the pattern feature of the verifiable card and the pattern feature of the registered card, wherein the logical distance indicates a similarity of pattern images which correspond to the verifiable card pattern feature and the registered card pattern feature; and

in response to determining that the calculated logical distance is greater than a predetermined threshold, determining that the pattern feature of the verifiable card matches the pattern feature of the registered card.

8. The method of claim 7, wherein extracting the pattern feature from the corresponding card image further comprises one or more steps of:

converting the card image into a grayscale image; and

performing a whitening process on the respective image block, wherein the whitening process removes a correlation between neighboring pixel values.

9. The method of claim 3, wherein the extracted card feature is a pattern feature,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

extracting one or more feature points of the card image based on an image detection algorithm; and

generating one or more corresponding feature vectors of the card image based on the image detection algorithm;

for each of the feature points of the pattern feature of the verifiable card;

calculating a logical distance between the corresponding vector of the verifiable card and a vector of the registered card that corresponds to the respective feature point of the pattern feature of the registered card; and

in response to determining that a feature point of the verifiable card matches a feature point of the registered card based on the calculated logical distance, increasing a count of successfully matched feature points; and

in response to determining that the count of successfully matched feature points is greater than a predetermined threshold, determining that the pattern feature of the verifiable card matches the pattern feature of the registered card.

10. The method of claim 3, wherein the extracted card feature is a material feature which includes data related to the card material from the corresponding card image,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

identifying an image area from the card image based on a predetermined position and a predetermined size, wherein the image area includes a plurality of pixel points; and

extracting component values of hue, saturation, and luminance from each of the pixel points included in the image area;

generating a discrete sample curved surface based on the component values extracted from the pixel points corresponding to the registered card, wherein one component value is predetermined to be a vertical coordinate and the remaining component values are predetermined to be horizontal coordinates;

smoothing the discrete sample curved surface to obtain a continuous curved surface;

for each of the pixel points included in the image area corresponding to a verifiable card;

calculating a minimum distance between the component value of a respective pixel point and the continuous curved surface; and

in response to determining that the calculated minimum distance is greater than a predetermined threshold;

determining that the respective pixel point matches the material feature of the registered card; and

increasing a count of successfully matched pixel points; and

in response to determining that the count of successfully matched pixel points is greater than a predetermined threshold, determining that the material feature of the verifiable card matches the material feature of the registered card.

11. The method of claim 10, wherein the component value of saturation is the predetermined vertical coordinate.

12. The method of claim 3, wherein the extracted card feature is a graphic feature,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

identifying a template which corresponds to the card image; and

determining an image in the image area corresponding to the graphic feature in the card image based on area and position information from the template;

adjusting a size of the determined image corresponding to the graphic feature of the verifiable card, wherein the adjusted size is equal to a size of the corresponding image of the registered card;

for each of one or more pixel points in the adjusted size image of the verifiable card, in response to determining that a pixel value for a respective pixel point is equal to a pixel value for a corresponding pixel point in the corresponding image of the registered card, increasing a count of successfully matched pixel points; and

in response to determining that the count of successfully matched pixel points is greater than a predetermined threshold, determining that the graphic feature of the verifiable card matches the graphic feature of the registered card.

13. A computer-implemented method for verifying identity, the method comprising:

registering, by an authorized user, a physical card for subsequent verification by a server by submitting a digital image of the physical card;

obtaining, by a client computing device, a digital image of a verifiable physical card, wherein the verifiable card image is used for identity verification of a user for an online transaction;

sending a request to a server for identity verification, wherein the request includes the digital image of the verifiable physical card and corresponds to an account; and

in response to the request, receiving a response from the server, wherein the response indicates successful identity verification, which causes the user to proceed with the online transaction based on the verifiable physical card, or unsuccessful identity verification, which blocks the user from proceeding with the online transaction based on the verifiable physical card.

14. The method of claim 13, further comprising:

obtaining a digital image of the registered physical card, wherein the registered card image is used for identity verification and corresponds to the account; and

sending the digital image of the registered physical card to the server.

15. A computer system for facilitating identity verification, the computer system comprising:

a processor;

a memory coupled to the processor and storing instructions, which when executed by the processor cause the processor to perform a method, the method comprising;

registering, by an authorized user, a physical card for subsequent verification by a server by submitting a digital image of the physical card;

receiving, by the server, a request for identity verification of a user for an online transaction, wherein the request corresponds to an account and includes a digital image of a verifiable physical card;

extracting, based on an image-processing technique, a first card feature from the verifiable card image, wherein an extracted card feature includes a physical feature associated with a physical card or private information of the user;

extracting, based on the image-processing technique, a second card feature from a digital image of a registered card which corresponds to the account, wherein the second card feature is encrypted based on an encryption algorithm;

decrypting the encrypted second card feature based on a decryption algorithm which corresponds to the encryption algorithm; and

in response to determining that the first card feature matches the decrypted second card feature, determining successful identity verification,

which causes the user to proceed with the online transaction based on the verifiable physical card.

16. The computer system of claim 15, wherein the method further comprises:

receiving the digital image of the registered card; and

storing the extracted second card feature.

17. The computer system of claim 15, wherein a card feature extracted from a corresponding card image of the verifiable card or the registered card is one or more of:

a number feature;

a pattern feature;

a material feature; and

a graphic feature, wherein the graphic feature is one or more of;

a character feature;

a logo feature; and

a signature feature; and

wherein the method further comprises;

determining that each of one or more verifiable card features matches a corresponding one or more registered card features.

18. The computer system of claim 17, wherein the extracted card feature is a number feature which includes number information associated with the corresponding card image,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

converting the card image into a grayscale image;

determining a rectangular image area from the grayscale image that includes the number information; and

identifying the number information in the rectangular image area; and

in response to determining that the number information from the verifiable card feature matches the number information from the registered card feature, determining that the number feature of the verifiable card matches the number feature of the registered card.

19. The computer system of claim 18, wherein determining the rectangular image area comprises one or more of:

identifying a template which corresponds to the card image, and determining the rectangular image area based on area and position information from the template;

and

segmenting the card image horizontally based on an edge detection algorithm, and determining the rectangular image area based on the segmented card image.

20. The computer system of claim 18, wherein identifying the number information in the rectangular image area comprises:

segmenting the rectangular image area vertically based on an edge detection algorithm;

determining a plurality of images of numbers based on the segmented rectangular image area, wherein each of the number images is an identifiable number image that includes an identifiable number;

identifying one or more feature values for each identifiable number image;

for each of one or more sample number images stored by the server, calculating a logical distance between the feature value for a respective identifiable number image and a corresponding feature value for the sample number image based on a classification algorithm; and

in response to selecting one of the sample number images based on a shortest calculated logical distance, wherein the selected sample number image includes a number, determining that the identifiable number included in the identifiable number image is the number included in the selected sample number image.

21. The computer system of claim 17, wherein the extracted card feature is a pattern feature,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

normalizing a size of the card image based on a predetermined size;

extracting a predetermined number of image blocks from the normalized card image based on a predetermined position and a predetermined size;

assigning a pixel value for each of the predetermined number of image blocks based on a sample set normalization for a respective image block;

determining a local feature for the respective image block based on a dictionary learning method; and

identifying an image feature of the card image based on the local feature and a pooling technology;

calculating a logical distance between the pattern feature of the verifiable card and the pattern feature of the registered card, wherein the logical distance indicates a similarity of pattern images which correspond to the verifiable card pattern feature and the registered card pattern feature; and

in response to determining that the calculated logical distance is greater than a predetermined threshold, determining that the pattern feature of the verifiable card matches the pattern feature of the registered card.

22. The computer system of claim 17, wherein the extracted card feature is a pattern feature,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

extracting one or more feature points of the card image based on an image detection algorithm; and

generating one or more corresponding feature vectors of the card image based on the image detection algorithm;

for each of the feature points of the pattern feature of the verifiable card;

calculating a logical distance between the corresponding vector of the verifiable card and a vector of the registered card that corresponds to the respective feature point of the pattern feature of the registered card; and

in response to determining that a feature point of the verifiable card matches a feature point of the registered card based on the calculated logical distance, increasing a count of successfully matched feature points; and

in response to determining that the count of successfully matched feature points is greater than a predetermined threshold, determining that the pattern feature of the verifiable card matches the pattern feature of the registered card.

23. The computer system of claim 17, wherein the extracted card feature is a material feature which includes data related to the card material from the corresponding card image,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

identifying an image area from the card image based on a predetermined position and a predetermined size, wherein the image area includes a plurality of pixel points; and

extracting component values of hue, saturation, and luminance from each of the pixel points included in the image area;

generating a discrete sample curved surface based on the component values extracted from the pixel points corresponding to the registered card, wherein one component value is predetermined to be a vertical coordinate and the remaining component values are predetermined to be horizontal coordinates;

smoothing the discrete sample curved surface to obtain a continuous curved surface;

for each of the pixel points included in the image area corresponding to a verifiable card;

calculating a minimum distance between the component value of a respective pixel point and the continuous curved surface; and

in response to determining that the calculated minimum distance is greater than a predetermined threshold;

determining that the respective pixel point matches the material feature of the registered card; and

increasing a count of successfully matched pixel points; and

in response to determining that the count of successfully matched pixel points is greater than a predetermined threshold, determining that the material feature of the verifiable card matches the material feature of the registered card.

24. The computer system of claim 17, wherein the extracted card feature is a graphic feature,

wherein extracting the first card feature and the second card feature from the corresponding card image based on the image-processing technique further comprises:

identifying a template which corresponds to the card image; and

determining an image in the image area corresponding to the graphic feature in the card image based on area and position information from the template;

adjusting a size of the determined image corresponding to the graphic feature of the verifiable card, wherein the adjusted size is equal to a size of the corresponding image of the registered card;

for each of one or more pixel points in the adjusted size image of the verifiable card, in response to determining that a pixel value for a respective pixel point is equal to a pixel value for a corresponding pixel point in the corresponding image of the registered card, increasing a count of successfully matched pixel points; and

in response to determining that the count of successfully matched pixel points is greater than a predetermined threshold, determining that the graphic feature of the verifiable card matches the graphic feature of the registered card.

25. A computer system for facilitating identity verification, the computer system comprising:

a processor;

a memory coupled to the processor and storing instructions, which when executed by the processor cause the processor to perform a method, the method comprising;

registering, by an authorized user, a physical card for subsequent verification by a server by submitting a digital image of the physical card;

obtaining, by a client computing device, a digital image of a verifiable physical card, wherein the verifiable card image is used for identity verification of a user for an online transaction;

sending a request to a server for identity verification, wherein the request includes the digital image of the verifiable physical card and corresponds to an account; and

in response to the request, receiving a response from the server, wherein the response indicates successful identify verification, which causes the user to proceed with the online transaction based on the verifiable physical card, or unsuccessful identity verification, which blocks the user from proceeding with the online transaction based on the verifiable physical card.

26. The computer system of claim 25, wherein the method further comprises:

obtaining a digital image of the registered physical card, wherein the registered card image is used for identity verification and corresponds to the account; and

sending the digital image of the registered physical card to the server.