Client side filtering of card OCR images

Patent metadata

Field	Value
Publication number	US-9740929-B2
Application number	US-201715457946-A
Country	US
Kind code	B2
Filing date	Mar 13, 2017
Priority date	Nov 15, 2013
Publication date	Aug 22, 2017
Grant date	Aug 22, 2017

Abstract

The technology of the present disclosure includes computer-implemented methods, computer program products, and systems to filter images before transmitting to a system for optical character recognition (“OCR”). A user computing device obtains a first image of the card from the digital scan of a physical card and analyzes features of the first image, the analysis being sufficient to determine if the first image is likely to be usable by an OCR algorithm. If the user computing device determines that the first image is likely to be usable, then the first image is transmitted to an OCR system associated with the OCR algorithm. Upon a determination that the first image is unlikely to be usable, a second image of the card from the digital scan of the physical card is analyzed. The optical character recognition system performs an optical character recognition algorithm on the filtered card.

First claim

What is claimed is:

1. A computer-implemented method to filter images before transmission to optical character recognition systems to reduce unnecessary communications and processing of unusable images, comprising:
analyzing, by the mobile computing device, features of a first image of a card captured in a digital scan to determine whether the first image is likely to be usable by an optical character recognition algorithm operating on an optical character recognition system;
selecting, by the mobile computing device, a second image of the card captured in the digital scan in response to determining that the first image is not likely to be usable by an optical character recognition algorithm operating on an optical character recognition system;
analyzing, by the mobile computing device, features of the second image to determine whether the second image is likely to be usable by an optical character recognition algorithm operating on the optical character recognition system; and
transmitting, by the mobile computing device, the second image to the optical character recognition system associated with the optical character recognition algorithm in response to determining that the second image is likely to be usable by the optical character recognition algorithm; and
receiving, by the mobile computing device, the relevant data from the optical character recognition system.

2. The computer-implemented method of claim 1 , wherein a third image is captured upon receiving, by the one or more computer devices and from the optical character recognition system, an indication that the optical character recognition algorithm produced results that were below a configured threshold confidence level.

3. The computer-implemented method of claim 1 , wherein the analyzing step comprises:
detecting, by the one or more computing devices, blur in the image; and
determining, by the one or more computing devices, that the image is likely to be usable by an optical character recognition algorithm upon a determination that an amount of blur detected in the image is below a configured threshold.

4. The computer-implemented method of claim 1 , wherein the analyzing step comprises:
detecting, by the one or more computing devices, a level of brightness in the image; and
determining, by the one or more computing devices, that the image is likely to be usable by an optical character recognition algorithm upon a determination that the level of brightness detected in the image is between configured thresholds.

5. The computer-implemented method of claim 1 , wherein the analyzing step comprises:
detecting, by the one or more computing devices, text in the image; and
determining, by the one or more computing devices, that the image is likely to be usable by an optical character recognition algorithm upon a determination that an amount of text detected in the image is above a configured threshold.

6. The computer-implemented method of claim 5 , further comprising determining, by the one or more computing devices, that the image is likely to be usable by an optical character recognition algorithm upon a determination that the text detected in the image is in a location of the image that corresponds to a configured expected location.

7. The computer-implemented method of claim 1 , wherein the card is a credit card, a debit card, an identification card, a loyalty card, an access card, or a stored value card.

8. 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 filter images before transmission to optical character recognition systems to reduce unnecessary communications and processing, the computer-executable program instructions, comprising:
computer-executable program instructions to analyze features of the first image of a card captured in a digital scan to determine whether the first image is likely to be usable by an optical character recognition algorithm;
computer-readable program instructions to select a second image of the card captured in the digital scan in response to determining that the first image is not likely to be usable;
computer-readable program instructions to analyze features of the second image to determine whether the second image is likely to be usable by an optical character recognition algorithm;
computer-executable program instructions to transmit the second image to an optical character recognition system associated with the optical character recognition algorithm in response to determining that the second image is likely to be usable by an optical character recognition algorithm.

9. The computer program product of claim 8 , wherein a third image is selected upon receiving, from the optical character recognition system, an indication that the optical character recognition algorithm produced results that were below a configured threshold confidence level.

10. The computer program product of claim 8 , wherein the analyzing step comprises:
computer-executable program instructions to detect blur in the image; and
computer-executable program instructions to determine the image is likely to be usable by an optical character recognition algorithm upon a determination that an amount of blur detected in the image is below a configured threshold.

11. The computer program product of claim 8 , wherein the analyzing step comprises:
computer-executable program instructions to detect a level of brightness in the image; and
computer-executable program instructions to determine that the image is likely to be usable by an optical character recognition algorithm upon a determination that the level of brightness detected in the image is between configured thresholds.

12. The computer program product of claim 8 , wherein the analyzing step comprises:
computer-executable program instructions detect text in the image; and
computer-executable program instructions to determine that the image is likely to be usable by an optical character recognition algorithm upon a determination that an amount of text detected in the image is above a configured threshold.

13. The computer program product of claim 12 , further comprising computer-readable program instructions that cause the system to determine that the image is likely to be usable by an optical character recognition algorithm upon a determination that the text detected in the image is in a location of the image that corresponds to a configured expected location.

14. A system to filter images, the system comprising:
a storage resource;
a processor communicatively coupled to the storage resource, wherein the processor is configured to execute computer-readable instructions that are stored in the storage resource and that cause the system to:
analyze features of a first image of a card captured in a digital scan to determine whether the first image is likely to be usable by an optical character recognition algorithm operating on an optical character recognition system;
capture a second image of the card in response to determining that the first image is not likely to be usable;
analyze features of the second image to determine whether the second image is likely to be usable by an optical character recognition algorithm; and
transmit the second image to an optical character recognition system associated with the optical character recognition algorithm in response to determining that the second image is likely to be usable by an optical character recognition algorithm; and
receive the relevant data from the optical character recognition s

Assignees

• Google Inc

Inventors

• Wang Xiaohang
• Bissacco Alessandro
• Berntson Glenn Merlind
• Nazif Marria
• Scheiner Justin
• Shih Sam
• Snyder Mark Leslie
• Talavera Daniel

Classifications

• G06V30/133 Primary

  Evaluation of quality of the acquired characters · CPC title

• G06V30/414 Primary

  Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/00463 Primary

  Physics · mapped topic

• G06K9/4647

  Physics · mapped topic