Extracting card identification data using card types

Patent metadata

Field	Value
Publication number	US-2016019431-A1
Application number	US-201414550878-A
Country	US
Kind code	A1
Filing date	Nov 21, 2014
Priority date	Jul 15, 2014
Publication date	Jan 21, 2016
Grant date	—

Abstract

Extracting card information comprises a server at an optical character recognition (“OCR”) system that interprets data from a card. The OCR system performs an optical character recognition algorithm an image of a card and a data recognition algorithm on a machine-readable code on the image of the card. The OCR system compares a series of extracted alphanumeric characters obtained via the optical character recognition process to data extracted from the machine-readable code via the data recognition process and matches the alphanumeric series of characters to a particular series of characters extracted from the machine-readable code. The OCR system determines if the alphanumeric series and the matching series of characters extracted from the machine-readable code comprise any discrepancies and corrects the alphanumeric series of characters. The OCR system may also determine a card type and use a card format associated with the card type to improve the data extraction.

First claim

1 . A computer-implemented method to extract card information, comprising:
determining, by one or more computing devices, a card type of a digital representation of a card; determining, by the one or more computing devices, from data related to the card type, that the card comprises a machine-readable code and a text portion that each identify a particular data set on the card; determining, by the one or more computing devices, an expected accuracy for a result from performing a data recognition algorithm on the machine-readable code of the digital representation of the card; determining, by the one or more computing devices, an expected accuracy for a result from performing an optical character recognition algorithm on the text portion of the digital representation of the card; identifying, by the one or more computing devices, a method of extracting the particular set of data from the digital representation of the card that has the highest expected accuracy by comparing the expected accuracy for the result from performing the data recognition algorithm on the machine-readable code of the digital representation of the card to the expected accuracy for the result from performing the optical character recognition algorithm on the text portion of the digital representation of the card; and extracting, by the one or more computing devices, the particular set of data from the digital representation of the card using the identified method.

2 . The method of claim 1 , wherein the method of extracting data from the card that has the highest expected accuracy is performed by the data recognition algorithm on a machine-readable code.

3 . The method of claim 1 , wherein the method of extracting data from the card that has the highest expected accuracy is performed by the optical character recognition algorithm.

4 . The method of claim 2 , wherein the machine-readable code is a barcode.

5 . The method of claim 1 , wherein the card type is determined by comparing, by the one or more computing devices, the identified text to a database of card types.

6 . The method of claim 1 , wherein the particular set of data is an identification code for an account of a user associated with the card.

7 . The method of claim 1 , further comprising identifying, by the one or more computing devices, images in the digital representation of the card that identify the card type, based on a result of an image recognition algorithm being applied to the digital representation of the card.

8 . A computer program product, comprising:
a non-transitory computer-readable storage device having computer-readable program instructions embodied thereon that when executed by a computer cause the computer to extract card information, the computer-readable program instructions comprising:
computer-readable program instructions to determine a card type of a digital representation of a card;
computer-readable program instructions to determine, from data related to the card type, that the card comprises a machine-readable code and a text portion that each identify a particular data set on the card;
computer-readable program instructions to determine an expected accuracy for a result from performing a data recognition algorithm on the machine-readable code of the digital representation of the card;
computer-readable program instructions to determine an expected accuracy for a result from performing an optical character recognition algorithm on the text portion of the digital representation of the card;
computer-readable program instructions to identify a method of extracting the particular set of data from the digital representation of the card that has the highest expected accuracy by comparing the expected accuracy for the result from performing the data recognition algorithm on the machine-readable code of the digital representation of the card to the expected accuracy for the result from performing the optical character recognition algorithm on the text portion of the digital representation of the card; and
computer-readable program instructions to extract the particular set of data from the digital representation of the card based on the identification of the method.

9 . The computer program product of claim 8 , wherein the method of extracting data from the card that has the highest expected accuracy is performed by the data recognition algorithm on a machine-readable code.

10 . The computer program product of claim 8 , further comprising computer-readable program instructions to identify images in the digital representation of the card to identify a card type, based on a result of an image recognition algorithm being applied to the digital representation of the card.

11 . The computer program product of claim 8 , wherein the method of extracting data from the card that has the highest expected accuracy is performed by an optical character recognition algorithm.

12 . The computer program product of claim 9 , wherein the machine-readable code is a barcode.

13 . The computer program product of claim 8 , wherein the card type is determined by comparing the identified text to a database of card types.

14 . The computer program product of claim 8 , wherein the particular set of data is an identification code for an account of a user associated with the card.

15 . A system to extract card information, 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:
determine the card type of a digital representation of a card;
determine, from data related to the card type, that the card comprises a machine-readable code and a text portion that each identify a particular data set on the card;
determine an expected accuracy for a result from performing at a recognition algorithm on the machine-readable code of the digital representation of the card;
determine an expected accuracy for a result from performing an optical character recognition algorithm on the text portion of the digital representation of the card;
identify a method of extracting the particular set of data from the digital representation of the card that has the highest expected accuracy by comparing the expected accuracy for the result from performing the data recognition algorithm on the machine-readable code of the digital representation of the card to the expected accuracy for the result from performing the optical character recognition algorithm on the text portion of the digital representation of the card; and
extract the particular set of data from the digital representation of the card based on the identification of the method.

16 . The system of claim 15 , wherein the method of extracting data from the card that has the highest expected accuracy is performed by the data recognition algorithm on a machine-readable code.

17 . The system of claim 15 , further comprising application code instructions to cause the system to identify images in the digital representation of the card that identifies a card type, based on a result of an image recognition algorithm being applied to the digital representation of the card.

18 . The system of claim 15 , wherein the method of extracting data from the card that has the highest expected accuracy is performed by an optical character recognition algorithm.

19 . The system of claim 15 , wherein the card type is determined by comparing the identified text to a database of card types.

Assignees

• Google Inc

Inventors

• Wang Xiaohang
• Scheiner Justin
• Berntson Glenn

Classifications

• G06V30/1444 Primary

  Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields · CPC title

• G06V30/224

  of printed characters having additional code marks or containing code marks · CPC title

• G06F18/28

  Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries · CPC title

• G06V30/274

  Syntactic or semantic context, e.g. balancing · CPC title

• G06V30/10

  Character recognition · CPC title