Payment card ocr with relaxed alignment

Patent metadata

Field	Value
Publication number	US-2016267345-A1
Application number	US-201615158520-A
Country	US
Kind code	A1
Filing date	May 18, 2016
Priority date	Jun 30, 2013
Publication date	Sep 15, 2016
Grant date	—

Abstract

Extracting financial card information with relaxed alignment comprises a method to receive an image of a card, determine one or more edge finder zones in locations of the image, and identify lines in the one or more edge finder zones. The method further identifies one or more quadrilaterals formed by intersections of extrapolations of the identified lines, determines an aspect ratio of the one or more quadrilateral, and compares the determined aspect ratios of the quadrilateral to an expected aspect ratio. The method then identifies a quadrilateral that matches the expected aspect ratio and performs an optical character recognition algorithm on the rectified model. A similar method is performed on multiple cards in an image. The results of the analysis of each of the cards are compared to improve accuracy of the data.

First claim

1 . A computer-implemented method for to extract financial card information, comprising:
associating, by the one or more computing devices, expected aspect ratios for each of a plurality of card types in a database, the card types having different expected aspect ratios; identifying, by the one or more computing devices, a plurality of quadrilaterals formed by intersections of extrapolations of identified lines in an image of a card; adjusting, by the one or more computing devices, a perspective of the one or more quadrilaterals until the one or more quadrilaterals are fronto-parallel; determining, by the one or more computing devices, an aspect ratio of each of the plurality of quadrilaterals; identifying, by the one or more computing devices, the particular card type in the database and an expected aspect ratio that is associated with the particular card type in the database; comparing, by the one or more computing devices, the determined aspect ratio for each of the plurality of quadrilaterals to the expected aspect ratio for the particular card type to identify, a particular quadrilateral that matches the expected aspect ratio as a preferred card boundary; cropping, by the one or more computing devices, the image to only a portion of the particular quadrilateral that comprises the account information; and performing, by the one or more computing devices, an optical character recognition algorithm on the cropped portion of the particular quadrilateral that comprises account information.

2 . The method of claim 1 , further comprising:
determining, by the one or more computing devices, a location on the particular quadrilateral comprising account information, the location being based at least in part on a type of card represented in the image; and performing, by the one or more computing devices, the optical character recognition algorithm on only the determined location.

3 . The method of claim 1 , further comprising converting, by the one or more computing devices, the image to grayscale.

4 . (canceled)

5 . The method of claim 1 , further comprising:
detecting, by the one or more computing devices, blur in the image; and performing, by the one or more computing devices, a configured action to remove the blur from the image.

6 . The method of claim 1 , wherein the card type comprises a credit card, a debit card, an identification card, a loyalty card, or an access card.

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 extract financial card information, the computer-executable program instructions comprising: computer-executable program instructions to associate expected aspect ratios for each of a plurality of card types in a database; computer-executable program instructions to identify a plurality of quadrilaterals formed by intersections of extrapolations of identified lines in an image of a card; computer-executable program instructions to determine an aspect ratio of each of the plurality of quadrilateral; computer-executable program instructions to identify the particular card type in the database and an expected aspect ratio that is associated with the particular card type in the database; computer-executable program instructions to compare the determined aspect ratio for each of the plurality of quadrilaterals to the expected aspect ratio for the particular card type to identify, a particular quadrilateral that matches the expected aspect ratio as a preferred card boundary; computer-executable program instructions to crop the image to only a portion of the particular quadrilateral that comprises account information; and computer-executable program instructions to perform an optical character recognition algorithm on the cropped portion of the particular quadrilateral that comprises the account information.

8 . The computer program product of claim 7 , the computer-executable program instructions further comprising:
computer program instructions to model a region of the image encompassed by the particular quadrilateral in three dimensions;

9 . (canceled)

10 . The computer program product of claim 7 , further comprising computer program instructions to convert the image to grayscale.

11 . (canceled)

12 . The computer program product of claim 7 , the computer-executable program instructions further comprising:
computer program instructions to blur in the image; and computer program instructions to perform a configured action to remove the blur from the image.

13 . The computer program product of claim 7 , wherein the card type comprises a credit card, a debit card, an identification card, a loyalty card, or an access card.

14 . A system to extract financial card information, the system comprising:
a storage device; 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:
associate expected aspect ratios for each of a plurality of card types in a database;
identify a particular card type in the database and an expected aspect ratio that is associated with the particular card type in the database;
compare a determined aspect ratio for each of a plurality of quadrilaterals associated with edges of a card in a card image to the expected aspect ratio for the particular card type to identify, a particular quadrilateral that matches the expected aspect;
crop the image to only a portion of the particular quadrilateral that comprises account information; and
perform an optical character recognition algorithm on the cropped portion of the particular quadrilateral that comprises the account information.

15 . The system of claim 14 , the processor executing further application code instructions that are stored in the storage device to cause the system to:
model a region of the image encompassed by the particular quadrilateral in three dimensions;

16 . The system of claim 14 , the processor executing further application code instructions that are stored in the storage device to cause the system to convert the image to grayscale.

17 . (canceled)

18 . (canceled)

19 . The system of claim 14 , the processor executing further application code instructions that are stored in the storage device to and that cause the system to:
detect blur in the image; and perform a configured action to remove the blur from the image.

20 . The system of claim 14 , wherein the card type comprises a credit card, a debit card, an identification card, a loyalty card, or an access card.

Assignees

• Google Inc

Inventors

• Wang Xiaohang
• Shamsi Farhan
• Okshtein Yakov
• Kumar Sanjiv
• Rowley Henry Allan
• Mitchell Marcus Quintana
• Repenning Debra Lin
• Bissacco Alessandro
• Scheiner Justin
• Palm Leon

Classifications

• G06V30/1478

  of characters or characters lines · CPC title

• G06V30/416 Primary

  Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/3283 Primary

  Physics · mapped topic

• G06K9/00469

  Physics · mapped topic