Hierarchical classification in credit card data extraction

Patent metadata

Field	Value
Publication number	US-9984313-B2
Application number	US-201514934983-A
Country	US
Kind code	B2
Filing date	Nov 6, 2015
Priority date	Jun 28, 2013
Publication date	May 29, 2018
Grant date	May 29, 2018

Abstract

Embodiments herein provide computer-implemented techniques for allowing a user computing device to extract financial card information using optical character recognition (“OCR”). Extracting financial card information may be improved by applying various classifiers and other transformations to the image data. For example, applying a linear classifier to the image to determine digit locations before applying the OCR algorithm allows the user computing device to use less processing capacity to extract accurate card data. The OCR application may train a classifier to use the wear patterns of a card to improve OCR algorithm performance. The OCR application may apply a linear classifier and then a nonlinear classifier to improve the performance and the accuracy of the OCR algorithm. The OCR application uses the known digit patterns used by typical credit and debit cards to improve the accuracy of the OCR algorithm.

First claim

What is claimed is:

1. A computer-implemented method to extract card information, comprising:
identifying, by the one or more computing devices, a first area of an image, the first area being selected as a potential location of a digit on the card in the image and of a size that will encompass not more than a single complete digit, the potential location and the size of the first area being identified from a comparison of the image to a database of card layouts stored on the one or more computing devices;
determining, by the one or more computing devices, that the first area does not encompass a single complete digit upon determining that a confidence level of a first result of an application of a classification algorithm to the first area is below a configured threshold;
based upon determining that the first area does not encompass a single complete digit, identifying, by the one or more computing devices, a second area of the image, the second area encompassing at least a portion of a different location from the first area and of a size that will encompass not more than a single complete digit;
determining, by the one or more computing devices, that the second area encompasses a single complete digit upon determining that a confidence level of a second result of an application of the classification algorithm to the second area is over a configured threshold; and
performing, by the one or more computing devices, an optical character recognition algorithm on the second area upon a determination that the second area encompasses the single complete digit.

2. The method of claim 1 , wherein the second area is shifted horizontally from the first area.

3. The method of claim 1 , wherein the second area is shifted vertically from the first area.

4. The method of claim 1 , wherein the classification algorithm is a support vector machine.

5. The method of claim 1 , wherein the card comprises one or more of a credit card, a debit card, an identification card, a loyalty card, an access card, or a stored value card.

6. 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 card information, the computer-executable program instructions comprising:
computer-executable program instructions to identify a first area of an image, the first area being selected as a potential location of a digit on the card in the image and of a size that will encompass not more than a single complete digit, the potential location and the size of the first area being identified from a comparison of the image to a database of card layouts stored on the non-transitory computer-readable storage device;
computer-executable program instructions to determine that the first area does not encompass a single complete digit upon determining that a confidence level of a first result of an application of a classification algorithm to the first area is below a configured threshold;
computer-executable program instructions to identify a second area of the image, the second area encompassing at least a portion of a different location from the first area and of a size that will encompass not more than a single complete digit;
computer-executable program instructions to determine that the second area encompasses a single complete digit upon determining that a confidence level of a second result of an application of the classification algorithm to the second area is over a configured threshold; and
computer program instructions to perform an optical character recognition algorithm on the second area upon a determination that the second area encompasses the single complete digit.

7. The computer program product of claim 6 , wherein the second area is shifted horizontally from the first area.

8. The computer program product of claim 6 , wherein the second area is shifted vertically from the first area.

9. The computer program product of claim 6 , wherein the classification algorithm is a support vector machine.

10. The computer program product of claim 6 , wherein the card comprises one or more of a credit card, a debit card, an identification card, a loyalty card, an access card, or a stored value card.

11. A system to extract card information; 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:
identify a first area of an image, the first area being selected as a potential location of a digit on the card in the image and of a size that will encompass not more than a single complete digit, the potential location and the size of the first area being identified from a comparison of the image to a database of card layouts stored on the storage device;
determine that the first area does not encompasses a single complete digit upon determining that a confidence level of a first result of an application of a classification algorithm to the first area is under a configured threshold;
identify a second area of the image, the second area encompassing at least a portion of a different location from the first area and of a size that will encompass not more than a single complete digit;
determine that the second area encompasses a single complete digit upon determining that a confidence level of a second result of an application of a classification algorithm to the second area is over a configured threshold; and
perform an optical character recognition algorithm on the second area upon a determination that the second area encompasses the single complete digit.

12. The system of claim 11 , wherein the second area is shifted horizontally from the first area.

13. The system of claim 11 , wherein the second area is shifted vertically from the first area.

14. The system of claim 11 , wherein the card comprises one or more of a credit card, a debit card, an identification card, a loyalty card, an access card, or a stored value card.

15. The system of claim 11 , wherein the classification algorithm is a support vector machine.

Assignees

• Google Llc

Inventors

• Kumar Sanjiv
• Rowley Henry Allan
• Wang Xiaohang
• Rodrigues Jose Jeronimo Moreira

Classifications

• G06Q20/227 Primary

  characterised in that multiple accounts are available, e.g. to the payer · CPC title

• G06F2218/12

  Classification; Matching · CPC title

• G06F18/2411

  based on the proximity to a decision surface, e.g. support vector machines · CPC title

• G06F18/24

  Classification techniques · CPC title

• G06V30/10

  Character recognition · CPC title