Identifying payment card categories based on optical character recognition of images of the payment cards

Patent metadata

Field	Value
Publication number	US-2016019530-A1
Application number	US-201414551991-A
Country	US
Kind code	A1
Filing date	Nov 24, 2014
Priority date	Jul 15, 2014
Publication date	Jan 21, 2016
Grant date	—

Abstract

A user captures an image of a payment card via a user computing device camera. An optical character recognition system receives the payment card image from the user computing device. The system performs optical character recognition and visual object recognition algorithms on the payment card image to extract text and visual objects from the payment card image, which are used by the system to identify a payment card type. The system may categorize the payment card as a credit card or a non-credit card. In an example embodiment, the system determines that the payment card type is a credit card and transmits fee structure to the user. The user selects a second payment card for use in the transaction and the transaction is processed using financial account information associated with the second payment card.

First claim

What is claimed is:

1 . A computer-implemented method to categorize payment cards, comprising:
receiving, by one or more computing devices and from a user computing device, an image comprising an image of a payment card; extracting, by the one or more computing devices, one or more text objects and one or more visual objects from the image of the payment card; retrieving, by the one or more computing devices and for each of the extracted one or more visual objects, a text description corresponding to the extracted one or more visual objects; receiving, by the one or more computing devices and from the user computing device, a request to process a transaction and an input of a selection of the payment card for use in the transaction; determining, by the one or more computing devices and based on the one or more extracted text objects and the one or more retrieved text descriptions corresponding to the extracted one or more visual objects, a categorical designation for the payment card as a credit card; retrieving, by the one or more computing devices, a fee structure associated with the determined categorical designation; and transmitting, by the one or more computing devices and to the user computing device, the retrieved fee structure and a request for an input selecting a payment card other than the user's selected payment card, wherein the fee structure and the request are displayed via the user computing device.

2 . The method of claim 1 , further comprising:
receiving, by the one or more computing devices and from the user computing devices, a selection of the second payment card; and processing, by the one or more computing devices, a transaction using financial account information associated with the second payment card.

3 . The method of claim 2 , further comprising:
determining, by the one or more computing devices and based on the one or more extracted text objects and the one or more retrieved text descriptions corresponding to the extracted one or more visual objects, a categorical designation for the payment card as a non-credit card; and in response to determining a categorical designation for the payment card as a non-credit card, processing, by the one or more computing devices, the transaction requested by the user.

4 . The method of claim 1 , further comprising:
receiving, by the one or more computing devices and from the user computing devices, a second image comprising an image of a second payment card; extracting, by the one or more computing devices, one or more text objects and one or more visual objects from the second image; and retrieving, by the one or more computing devices and for each of the extracted one or more visual objects, a text description corresponding to the extracted one or more visual objects.

5 . The method of claim 1 , wherein the user computing device captures the image of the payment card using a camera device communicating with the user computing device via a network.

6 . The method of claim 1 , wherein determining a categorical designation for the payment card as a credit card is further based on one or more visual features of the payment card image, such as color, brightness, pattern, lines, shapes, shading, a holographic nature of an object, or other appropriate or relevant features of the payment card image.

7 . A computer program product, comprising:
a non-transitory computer-readable storage device having computer-executable program instructions embodied thereon that when executed by a computer cause the computer to categorize payment cards, the computer-readable instructions comprising: computer-readable program instructions to extract one or more text objects and one or more visual objects from one or more images of a payment card; computer-readable program instructions to retrieve, for each of the extracted one or more visual objects, a text description corresponding to the extracted one or more visual objects; computer-readable program instructions to receive, from the user computing device, an input of a request to process a transaction and a selection of the payment card for use in the transaction; computer-readable program instructions to determine, based on the one or more extracted text objects and the one or more retrieved text descriptions corresponding to the extracted one or more visual objects, a categorical designation for the payment card as a credit card; computer-readable program instructions to retrieve, a fee structure associated with the determined categorical designation; and computer-readable program instructions to transmit, to the user computing device, the retrieved fee structure and a request for an input requesting a payment card other than the user's selected payment card, wherein the fee structure and the request are displayed by the user computing device.

8 . The computer program product of claim 7 , further comprising, computer-readable program instructions to receive, from a user computing device, one or more images of the payment card.

9 . The computer program product of claim 7 , further comprising:
computer-readable program instructions to receive, from the user computing devices, a selection of the second payment card; and computer-readable program instructions to process a transaction using financial account information associated with the second payment card.

10 . The computer program product of claim 9 , further comprising:
computer-readable program instructions to determine, based on the one or more extracted text objects and the one or more retrieved text descriptions corresponding to the extracted one or more visual objects, a categorical designation for the payment card as a non-credit card; and computer-readable program instructions to process, in response to determining a categorical designation for the payment card as a non-credit card, the transaction requested by the user.

11 . The computer program product of claim 7 , further comprising:
computer-readable program instructions to receive, from the user computing device, one or more images of a second payment card; computer-readable program instructions to extract one or more text objects and one or more visual objects from the one or more images of the second payment card; and computer-readable program instructions to retrieve, for each of the extracted one or more visual objects, a text description corresponding to the extracted one or more visual objects.

12 . The computer program product of claim 8 , wherein the user computing device captures the image of the payment card via a camera device communicating with the user computing device via a network.

13 . The computer program product of claim 7 , wherein determining a categorical designation for the payment card as a credit card is further based on one or more visual features of the payment card image, such as color, brightness, pattern, lines, shapes, shading, a holographic nature of an object, or other appropriate or relevant features of the payment card image.

14 . A system to categorize payment cards, comprising:
a storage device; and a processor communicatively coupled to the storage device, wherein the processor executes application code instructions that are stored in the storage device to cause the system to:
extract one or more text objects and one or more visual objects from one or more images of a payment card;
retrieve, for each of the extracted one or more visual objects, a text description corresponding to the extracted one or more visual objects;
receive, from the user computing device, a request to process a transaction and an input of a selection of t

Assignees

• Google Inc

Inventors

• Wang Xiaohang
• Berntson Glenn

Classifications

• H04N23/57

  Mechanical or electrical details of cameras or camera modules specially adapted for being embedded in other devices · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/00442

  Physics · mapped topic

• G06Q20/34 Primary

  using cards, e.g. integrated circuit [IC] cards or magnetic cards · CPC title

• G06K9/18

  Physics · mapped topic