Method and system for identifying and addressing imaging artifacts to enable a software system to provide financial services based on an image of a financial document

Patent metadata

Field	Value
Publication number	US-9836664-B1
Application number	US-201615167434-A
Country	US
Kind code	B1
Filing date	May 27, 2016
Priority date	May 27, 2016
Publication date	Dec 5, 2017
Grant date	Dec 5, 2017

Abstract

A method and system identifies and addresses imaging artifacts in an image of a financial document to enable a software system to provide financial services based on the image of the financial document. The method and system receive document image data, extract image features from the document image data, and apply the image features to an analytics model to generate an image classification, according to one embodiment. The method and system use the image classification to determine whether the document image data contains one or more particular image artifacts (e.g., Moiré patterns), according to one embodiment. If the software system determines that it is likely that the document image data contains one or more particular image artifacts, then the software system applies a filter (e.g., a median filter) to the document image data to reduce and/or remove the one or more particular image artifacts, according to one embodiment.

First claim

What is claimed is:

1. A computer system implemented method for identifying and addressing imaging artifacts to enable a software system to provide financial services that are at least partially based on an image of a financial document, comprising:
providing, with one or more computing systems, a software system;
receiving, with the software system, image data for a financial document, the image data for the financial document representing an image of the financial document;
storing the image data in one or more sections of memory associated with the one or more computing systems;
providing an analytics model to identify one or more imaging artifacts in the image of the financial document, the analytics model being trained with artifact imaging data representing a plurality of imaging artifacts, to enable the analytics model to identify the one or more imaging artifacts in the image of the financial document;
applying the image data for the financial document to the analytics model to generate image classification data that represents an image classification, the image classification indicating a likelihood that the image of the financial document includes the one or more imaging artifacts;
comparing the image classification data to a predetermined threshold;
if the image classification data exceeds the predetermined threshold, applying a filter to the image data to at least partially reduce the one or more imaging artifacts in the image data;
applying the image data to an optical character recognition engine to identify content data that represents content of the financial document; and
populating one or more fields in a data structure maintained by the software system, with the content data, to support a financial service provided by the software system to a user, and to reduce a manual entry of the content data from the financial document and into the software system by the user.

2. The computer system implemented method of claim 1 , wherein the software system is selected from a group of software systems consisting of: a tax return preparation system; a personal finances management system; and a business finances management system.

3. The computer system implemented method of claim 1 , wherein the one or more computer systems are selected from a group of computing systems consisting of: a mobile computing system, a cloud computing environment, and a server computing system.

4. The computer system implemented method of claim 1 , wherein the one or more imaging artifacts are one or more patterns from Moiré effect.

5. The computer system implemented method of claim 1 , wherein the one or more imaging artifacts result from capturing an image of a computer monitor with an image sensor.

6. The computer system implemented method of claim 5 , wherein the computer monitor is a cathode ray tube (“CRT”) computer monitor.

7. The computer system implemented method of claim 5 , wherein the image sensor is part of a camera of a mobile device or a digital camera.

8. The computer system implemented method of claim 1 , further comprising:
using at least some of the content data to electronically prepare a tax return for the user.

9. The computer system implemented method of claim 1 , further comprising:
training the analytics model by applying one or more machine learning algorithms to existing image data for plurality of documents that include the one or more imaging artifacts.

10. The computer system implemented method of claim 9 , wherein the one or more machine learning algorithms include gradient boosted decision trees.

11. The computer system implemented method of claim 1 , wherein applying the image data for the financial document to the analytics model includes:
extracting image features data from the image data for the financial document, the image features data representing one or more image features for the financial document; and
applying the image features data to the analytics model.

12. The computer system implemented method of claim 11 , wherein the one or more image features for the financial document include one or more of edges, corners, blobs, and ridges.

13. The computer system implemented method of claim 1 , wherein the filter is a median filter having a window that includes a window shape and a quantity of window elements.

14. The computer system implemented method of claim 13 , wherein applying the filter to the image data includes applying the median filter to the image data, wherein applying the median filter to the image data includes assigning a value to a central one of the quantity of window elements at least partially based on an average of values of those of the quantity of window elements that surround the central one of the quantity of window elements in the window.

15. The computer system implemented method of claim 13 , wherein the quantity of window elements are a quantity of pixels.

16. The computer system implemented method of claim 1 , wherein reducing the one or more imaging artifacts in the image data includes removing the one or more imaging artifacts from the image data.

17. The computer system implemented method of claim 1 , wherein the content data is selected from a group of user characteristics data consisting of:
data indicating a name of the user;
data indicating an age of the user;
data indicating an age of a spouse of the user;
data indicating a zip code;
data indicating a tax return filing status;
data indicating state income;
data indicating a home ownership status;
data indicating a home rental status;
data indicating a retirement status;
data indicating a student status;
data indicating an occupation of the user;
data indicating an occupation of a spouse of the user;
data indicating whether the user is claimed as a dependent;
data indicating whether a spouse of the user is claimed as a dependent;
data indicating whether another taxpayer is capable of claiming the user as a dependent;
data indicating whether a spouse of the user is capable of being claimed as a dependent;
data indicating salary and wages;
data indicating taxable interest income;
data indicating ordinary dividend income;
data indicating qualified dividend income;
data indicating business income;
data indicating farm income;
data indicating capital gains income;
data indicating taxable pension income;
data indicating pension income amount;
data indicating IRA distributions;
data indicating unemployment compensation;
data indicating taxable IRA;
data indicating taxable Social Security income;
data indicating an amount of Social Security income;
data indicating an amount of local state taxes paid;
data indicating whether the user filed a previous years' federal itemized deduction;
data indicating whether the user filed a previous years' state itemized deduction;
data indicating an annual income;
data indicating an employer's address;
data indicating contractor income;
data indicating a marital status;
data indicating a medical history;
data indicating dependents;
data indicating assets;
data indicating spousal information;
data indicating children's information;
data indicating an address;
data indicating a Social Security Number;
data indicating a government identification;
data indicating a date of birth;
data indicating educator expenses;
data indicating health savings account deductions;
data indicating moving expenses;
data indicating IRA deductions;
data indicating student loan interest deductions;
data indicating tuition and fees;
data indicating medical and den

Assignees

• Intuit Inc

Inventors

• Ramaswamy Pallavika
• Becker Richard J
• Moise Daniel Leontin
• Chan Horace

Classifications

• G06V30/164

  Noise filtering · CPC title

• G06V30/153

  using recognition of characters or words · CPC title

• G06N20/00 Primary

  Machine learning · CPC title

• G06Q40/123

  Tax preparation or submission · CPC title

• G06Q40/00

  Finance; Insurance; Tax strategies; Processing of corporate or income taxes · CPC title