Systems and methods for mobile image capture and processing
In several embodiments, methods, systems, and computer program products for processing digital images captured by a mobile device are disclosed. The techniques include detecting medical documents and/or documents relevant to an insurance claim by defining candidate edge points based on the captured image data and defining four sides of a tetragon based on at least some of the candidate edge points. In the case of an insurance claim process, the techniques also include determining whether the document is relevant to an insurance claim; and in response to determining the document is relevant to the insurance claim, submitting the image data, information extracted from the image data, or both to a remote server for claims processing. The image capture and processing techniques further facilitate processing of medical documents and/or insurance claims with a plurality of additional features that may be used individually or in combination in various embodiments.
1. A computer-implemented method for processing insurance claims, the method comprising:
capturing image data using a mobile device, the image data depicting a document; and
using at least one processor:
defining, based on the image data, a plurality of candidate edge points corresponding to the document;
defining four sides of a tetragon based on at least some of the plurality of candidate edge points; and
determining whether the document is relevant to an insurance claim; and
in response to determining the document is relevant to the insurance claim, submitting the image data, information extracted from the image data, or both to a remote server for claims processing; and
associating the image data, the information extracted from the image data, or both with a claim number prior to submitting the image data, the information extracted from the image data, or both to the remote server.
2. The method as recited in claim 1 , further comprising determining a document type corresponding to the document.
3. The method as recited in claim 2 , wherein the document type is selected from: a repair quote, an accident report, a driver license, a proof of insurance, a general correspondence, and a photo of a damaged vehicle.
4. The method as recited in claim 1 , comprising capturing additional data using the mobile device; and
wherein the additional data comprise a digital signature of an insured client.
5. The method as recited in claim 4 , comprising:
associating the digital signature of the insured client with the image data; and
submitting the digital signature of the insured client associated with the image data to the remote server along with the image data.
6. The method as recited in claim 1 , further comprising either:
determining, using the mobile device that additional data are required to process the insurance claim, or
receiving an indication at the mobile device, that the additional data are required to process the insurance claim.
7. The method as recited in claim 6 , further comprising, in response to determining that the additional data are required to process the insurance claim or receiving the indication that the additional data are required to process the insurance claim:
capturing the additional data using the mobile device, wherein the additional data comprise a digital signature of an insured client.
8. The method as recited in claim 1 , comprising authenticating an identity of a user using the mobile device prior to performing the capturing,
wherein the authenticating further comprises determining the user identity corresponds to an insurance claims adjuster.
9. The method as recited in claim 1 , comprising receiving an indication at the mobile device that an insurance claims adjuster is scheduled to inspect insured property in response to submitting the image data, the information extracted from the image data, or both to the remote server.
10. The method as recited in claim 1 , comprising receiving an indication at the mobile device, the indication providing either or both of a status of the insurance claim and a link to a summary of the insurance claim.
11. The method as recited in claim 1 , wherein defining the plurality of candidate edge points is based on identifying statistically significant differences between one or more statistical values representative of a small region of the image data and one or more corresponding distributions of statistics representative of a large region of the image data; and
wherein the small region of the image data is located within the large region of the image data.
12. The method as recited in claim 11 , wherein the distributions of statistics are representative of a background within the large region of the image data.
13. The method as recited in claim 1 , wherein defining the plurality of candidate edge points comprises:
defining one or more large analysis windows within a digital image;
defining a plurality of small analysis windows within the digital image;
estimating one or more distributions of statistics for each large analysis window;
calculating one or more statistics for each small analysis window;
determining whether a statistically significant difference exists between one or more of the statistics calculated for one of the small analysis windows and a corresponding distribution of statistics estimated for one of the large analysis windows; and
designating a point in the small analysis window as a candidate edge point upon determining the statistically significant difference exists.
14. A computer-implemented method for processing medical documents, the method comprising:
receiving or capturing image data using a mobile device, the image data depicting one or more medical documents; and
using at least one processor:
defining, based on the image data, a plurality of candidate edge points corresponding to at least one of the medical documents;
defining four sides of a tetragon based on at least some of the plurality of candidate edge points;
wherein defining the plurality of candidate edge points comprises:
defining one or more large analysis windows within a digital image;
defining a plurality of small analysis windows within the digital image;
estimating one or more distributions of statistics for each large analysis window;
calculating one or more statistics for each small analysis window;
determining whether a statistically significant difference exists between one or more of the statistics calculated for one of the small analysis windows and a corresponding distribution of statistics estimated for one of the large analysis windows; and
designating a point in the small analysis window as a candidate edge point upon determining the statistically significant difference exists.
15. The method as recited in claim 14 , wherein the image data are received from a mobile wireless scanner communicatively coupled to the mobile device.
16. The method as recited in claim 14 , wherein the image data are received in response to receiving user input at the mobile device, the user input being selected from a user interacting with a display of the mobile device, and the user giving a vocal command.
17. The method as recited in claim 14 , wherein the image data depict a plurality of medical documents each independently represented in a respective different digital image, and the method comprising independently defining the plurality of candidate edge points and the four sides of the tetragon for each of the plurality of medical documents represented in the respective different digital image.
18. The method as recited in claim 17 , comprising assembling the different digital images into a case corresponding to a patient, and storing the different digital images in association with the case.
19. The method as recited in claim 14 , wherein defining the plurality of candidate edge points is based on identifying statistically significant differences between one or more statistical values representative of a small region of the image data and one or more corresponding distributions of statistics representative of a large region of the image data; and
wherein the small region of the image data is located within the large region of the image data.