Systems and methods for enrollment and identity management using mobile imaging

Abstract

Systems and methods for automatic enrollment and identity verification based upon processing a captured image of a document are disclosed herein. Various embodiments enable, for example, a user to enroll in a particular service by taking a photograph of a particular document (e.g., his driver license) with a mobile device. One or more algorithms can then extract relevant data from the captured image. The extracted data (e.g., the person's name, gender, date of birth, height, weight, etc.) can then be used to automatically populate various fields of an enrollment application, thereby reducing the amount of information that the user has to manually input into his mobile device in order to complete the enrollment process. In some embodiments, a set of internal and/or external checks can be run against the data to ensure that the data is valid, has been read correctly, and is consistent with other data.

Description

BACKGROUND

1. Field of the Invention

Various embodiments described herein relate generally to the field of identity verification through image processing. More particularly, various embodiments are directed in one exemplary aspect to support automatic enrollment and identity verification upon processing a captured image of a document.

2. Related Art

Mobile phone adoption continues to escalate, including ever-growing smart phone adoption and tablet usage. Mobile imaging is a discipline where a consumer takes a picture of a document, and that document is processed, extracting and extending the data contained within it for selected purposes. The convenience of this technique is powerful and is currently driving a desire for this technology throughout Financial Services and other industries.

At the same time, consumers are looking for quicker and easier ways to enroll in new products and services. During a typical enrollment process, consumers must identify themselves, providing common personal and demographic data. However, since mobile devices are increasingly becoming the desired device for such purposes, typing such data into a mobile device can be cumbersome. Additionally, the institution providing the desired service must verify and validate the identity of the customer in order to manage their business risk. Presently, there is no means or mechanism for providing automatic enrollment and identity verification through mobile imaging.

SUMMARY

Disclosed herein are systems and methods for automatic enrollment and identity verification based on processing of a captured image of a document. Various embodiments enable, for example, a user to enroll in a particular service by taking a photograph of a particular document (e.g., a driver license) with a mobile device. One or more processes can then extract relevant identifying data from the captured image. The extracted identifying data (e.g., the person's name, gender, date of birth, height, weight, etc.) can then be used to automatically populate various fields of an enrollment application, thereby reducing the amount of information that the user has to manually input into the mobile device in order to complete an enrollment process. In some embodiments, a set of internal and/or external checks can be run against the data to ensure that the data is valid, has been read correctly, and is consistent with other data.

In a first exemplary aspect, a computer readable medium is disclosed. In one embodiment, the computer readable medium contains instructions which, when executed by a computer, perform a process comprising: receiving an image of a document; preprocessing the image of the document in preparation for data extraction; extracting a set of identifying data from the image of the document; and automatically populating fields of an enrollment form based at least in part upon the extracted set of identifying data.

Other features and advantages should become apparent from the following description of the preferred embodiments, taken in conjunction with the accompanying drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

Various embodiments disclosed herein are described in detail with reference to the following figures. The drawings are provided for purposes of illustration only and merely depict typical or exemplary embodiments. These drawings are provided to facilitate the reader's understanding and shall not be considered limiting of the breadth, scope, or applicability of the embodiments. It should be noted that for clarity and ease of illustration these drawings are not necessarily made to scale.

FIG. 1 is a block diagram illustrating an exemplary network topology that may be used for automatic enrollment and identity management according to embodiments.

FIG. 2 is a block diagram illustrating an exemplary server adapted to perform automatic enrollment and identity management according to embodiments.

FIG. 3 is a flow diagram illustrating an exemplary method of performing automatic enrollment and identity management according to embodiments.

FIG. 4 is a block diagram that illustrates an embodiment of a computer/server system upon which an embodiment of the inventive methodology may be implemented.

The various embodiments mentioned above are described in further detail with reference to the aforementioned figured and the following detailed description of exemplary embodiments.

DETAILED DESCRIPTION

FIG. 1 is a block diagram illustrating an exemplary network topology that may be used for automatic enrollment and identity management according to embodiments. As shown by this figure, the network topology can comprise a mobile device 102, such as a cellular phone, smartphone, tablet, laptop, wearable device, etc. that is interfaced with a server 108 over a connected network 106. The mobile device 102 may be configured with an image capture device to capture one or more images 104 which are then used in the enrollment and identity verification process described below. One or more verification sources 110 may also be connected with the network 106 in order to communicate verification data to verify the extracted identifying data from the image, as will be described further herein. The following processing steps to process the image and extract the identifying data may be carried out on one or both of the mobile device and server 108.

FIG. 2 is a block diagram illustrating an exemplary server 108 adapted to perform automatic enrollment and identity management according to embodiments. As shown by this figure, server 108 may include a power supply module 202, a network interface module 206, one or more processors 204, and memory 208. Various modules such as a preprocessing module 210, data extraction module 212, data validation module 214, and data verification module 216 can be resident within memory.

FIG. 3 is a flow diagram illustrating an exemplary method of performing automatic enrollment and identity management according to embodiments. As depicted in this figure, the exemplary method can comprise five steps according to various embodiments. First, in step 302, an image of an identity document can be captured on a mobile device. Second, in step 304, the image can be preprocessed in order to prepare the image for data extraction. Third, in step 306, key identity-related data can be obtained from the image of the identity document. Fourth, in step 308, the extracted data can be validated in order to assess the quality of the data. Fifth, in step 310, the extracted data can be verified to assess identity risk using independent external data sources. Each of these steps is now discussed in further detail below.

In one embodiment, the results from the validating and verifying steps are organized into a Mobile Identity Risk Scorecard. This scorecard is a structured information model for presenting the risks associated with a proposed identity to Financial Services or other organizations. The exact contents of the scorecard can vary according to the intended use, but will generally include numeric indicators (0 to 1000), graphical indicators (red-yellow-green) or other patterned indicators which denote aspects of identity risk.

Document Capture

At block 302, an image of a document is captured. According to some embodiments, an application or browser session initiates the capture sequence on a mobile device or tablet. This can be implemented in the form of a library, embedded in a downloaded mobile application, a hybrid application invoked from within a mobile browser, or an automatic capture utility embedded in a mobile application. The capture sequence can guide the user through obtaining a mobile imaging-ready picture of the document. In some embodiments, one or more characteristics can be optimized before image capture, including, without limitation—focus, corner detection, lighting conditions, reflective properties, and closeness. Also, in some embodiments, feedback can provided to the user through an interactive set of visual cues, informing the user, for example, of how “well they are doing.”

In one form of the above, the consumer takes a picture of the front of their Driver's License. In another form, the MRZ line on a passport is read. In a third form, a full identity document is read, such as a government-issued ID or military ID.

Optionally, the user can also provide one or more “hints”—information which can be used to more accurately determine information on the document. For example, the user might provide their last name, which could be used to more accurately determine the location of the name and address on the document.

In some embodiments, the capture process can also read a barcode present on the identity document and extract key information relating to identity. This information can be used to cross-validate the information obtained during the Data Extraction process.

Pre-Processing

At block 304, the mobile image, once captured on the mobile device, can be preprocessed. Preprocessing can include a number of operations, including cropping, deskewing, and/or dewarping the image. Additionally, shadows can be eliminated, lighting issues can be enhanced, and the overall readability of the document image can be improved through one or more mathematical algorithms. The image can also be converted to a bitonal image in preparation for data extraction. Depending on the specific needs of the document type, multiple versions of the binarized image may be needed to handle document-specific readability issues, such as reverse text. In these cases, the preprocessing engine can create multiple bitonal images which can be used in combination during the data extraction process. In addition, a series of image quality and assurance (IQA) test scores can be calculated, indicating the quality of the original image.

Data Extraction

At block 306, relevant data can be extracted from the image of the document. A set of fields known to be available can be determined based on the document type. For example, in an Illinois Driver License, the fields known to be available can include a person's name, address, date of birth, height, weight, document expiration date, and other data.

In some embodiments, individual field confidence scores can also be calculated. For example, in one embodiment, confidence scores can be defined in a range from 0 to 1000, with 1000 representing high technical confidence in the readability of that field, and 0 representing low technical confidence. The confidence scores are calculated using a mathematical formula based on the ability to identify the characters included in each field, including such factors as sharpness. These statistical measures can be used when presenting the data to the user (for example, a low-confidence field can be highlighted, requesting that the user to confirm the data that has been extracted).

The confidence scores would be used by the application leveraging a Mobile Photo Account Opening and Identity Management solution, including applying thresholds to the confidence scores, highlighting those fields with a confidence score below a fixed value (example: highlight fields below 500). If a PDF417 barcode was scanned, the deconstructed string is parsed, identifying each of the relevant fields. A rules engine is applied, to handle a variety of exceptions in the content of the string, including missing fields, concatenated fields, abbreviated fields, and other state-level and local-level deviations. To date, more than 200 variations have been identified, so the use of a rules engine to organize the parsing of the string is a key component of the overall solution

Data Validation

At block 308, the extracted data can be validated using a variety of data validation techniques. As used herein, the term “validation” refers to the evaluation of data using rules and internally-consistent controls available within the mobile imaging process. These techniques can include, without limitation: validation that the information scanned from the PDF417 barcode matches the data obtained during data extraction, if available; validation that the information scanned using the barcode matches the data obtained during data extraction, if available; comparison of date fields to verify date format (This may be used to improve the data (for example, it is not possible to have a 13^th month) or to validate the document (for example, exceptions would be flagged, such as expiration dates in the past, birthdates less than 16 years ago, birthdates over 100 years ago, etc.); validation that the expiration date is greater than today; validation that the date of birth is some date earlier than today; validation of data fields to known masks (example: zip code—(either XXXXX or XXXXX-XXXX) in the United States. Exceptions may be able to be corrected, by using a USPS database, or flagged as low-confidence); and validation of data fields to known minimum and maximum field lengths (ex. Validation of state field to defined set of 2-character abbreviations. Exceptions may be able to be corrected, by using a USPS database, or flagged as low-confidence). A myriad of other techniques for validation are possible in accordance with the scope of various embodiments.

Data Verification

At block 310, the extracted data can then be verified using a variety of data verification techniques. As used herein, the term “verification” refers to the evaluation of data using external data sources (110 in FIG. 1) or external verification logic. These techniques may include, without limitation: establishing that a person exists with the extracted name; determining if a unique individual can be determined given the extracted data; determining if a social security number can be identified with the given data; attempting to match an address to a United States Postal Service (USPS) database of known addresses; verifying that the individual has lived at the extracted address; verifying that the name matches the name associated with the extracted driver license number; verifying that the name matches a name associated with an extracted social security number. A myriad of other techniques for verification are possible in accordance with the scope of various embodiments.

Applications

In one embodiment, a Mobile Photo Account Opening and Identity Management solution may allow a consumer to fund the account once the information from the identity document is used to create a new account. To do this, the consumer would do one of the following: take a picture of a completed check, depositing it in the new account; take a picture of a blank check, to collect the routing and account number from the MICR line, to facilitate an ACH transfer; automatically scan a credit card, using an automatic capture utility, by holding the card in front of the camera of the mobile device, automatically detecting the 15-digit or 16-digit account number on the face of the card. This information is used by the calling application to pre-fill the information needed to complete a credit card funding transaction.

Multiple embodiments of potential applications are now provided herein.

In one embodiment, a system of automatically scanning a credit card, using an automatic capture utility, by holding the card in front of the camera of the mobile device, automatically detecting the 15-digit or 16-digit account number on the face of the card.

A system of Mobile Photo Account Opening and Identity Management, including the following: US Driver's License Capture (front of document), US Driver's License PDF417 scan (on back of document), Preprocessing of image, Data extraction from image, Deconstruction of PDF417 contents using a rules engine, Validation, including comparison of PDF417 contents to extracted data and Funding

A system of Mobile Photo Account Opening and Identity Management, including the following: US Driver's License Capture (front of document), Preprocessing of image, Data extraction from image, Validation, Funding,

A system of Mobile Photo Account Opening and Identity Management, including the following: US Driver's License Capture (front of document), US Driver's License PDF417 scan (on back of document), Preprocessing of image, Data extraction from image, Deconstruction of PDF417 contents using a rules engine, Validation, including comparison of PDF417 contents to extracted data.

A system of Mobile Photo Account Opening and Identity Management, including the following: US Driver's License Capture (front of document), Preprocessing of image, Data extraction from image, Validation.

A system of Mobile Photo Account Opening and Identity Management, including the following: Passport Capture (MRZ contents), Preprocessing of image, Data extraction from MRZ, Validation, Funding.

A system of Mobile Photo Account Opening and Identity Management, including the following: Passport Capture (MRZ contents), Preprocessing of image, Data extraction from MRZ, Validation.

A system of Mobile Photo Account Opening and Identity Management, including the following: Government or other identity document capture, Preprocessing of image, Data extraction, Validation, Funding.

A system of Mobile Photo Account Opening and Identity Management, including the following: Government or other identity document capture, Preprocessing of image, Data extraction, Validation.

Computer-Enabled Embodiment

For the purposes of the embodiments described herein, the term “computer” as used throughout this disclosure may be implemented as any computing device, including a mobile phone or a tablet.

FIG. 4 is a block diagram that illustrates an embodiment of a computer/server system 400 upon which an embodiment of the inventive methodology may be implemented. The system 400 includes a computer/server platform 401 including a processor 402 and memory 403 which operate to execute instructions, as known to one of skill in the art. The term “computer-readable storage medium” as used herein refers to any tangible medium, such as a disk or semiconductor memory, that participates in providing instructions to processor 402 for execution. Additionally, the computer platform 401 receives input from a plurality of input devices 404, such as a keyboard, mouse, touch device or verbal command. The computer platform 401 may additionally be connected to a removable storage device 405, such as a portable hard drive, optical media (CD or DVD), disk media or any other tangible medium from which a computer can read executable code. The computer platform may further be connected to network resources 406 which connect to the Internet or other components of a local public or private network. The network resources 406 may provide instructions and data to the computer platform from a remote location on a network 407. The connections to the network resources 406 may be via wireless protocols, such as the 802.11 standards, Bluetooth® or cellular protocols, or via physical transmission media, such as cables or fiber optics. The network resources may include storage devices for storing data and executable instructions at a location separate from the computer platform 401. The computer interacts with a display 408 to output data and other information to a user, as well as to request additional instructions and input from the user. The display 408 may therefore further act as an input device 404 for interacting with a user.

While various embodiments have been described above, it should be understood that they have been presented by way of example only, and not of limitation. The breadth and scope should not be limited by any of the above-described exemplary embodiments. Where this document refers to technologies that would be apparent or known to one of ordinary skill in the art, such technologies encompass those apparent or known to the skilled artisan now or at any time in the future. In addition, the described embodiments are not restricted to the illustrated example architectures or configurations, but the desired features can be implemented using a variety of alternative architectures and configurations. As will become apparent to one of ordinary skill in the art after reading this document, the illustrated embodiments and their various alternatives can be implemented without confinement to the illustrated example. One of ordinary skill in the art would also understand how alternative functional, logical or physical partitioning and configurations could be utilized to implement the desired features of the described embodiments.

Furthermore, although items, elements or components may be described or claimed in the singular, the plural is contemplated to be within the scope thereof unless limitation to the singular is explicitly stated. The presence of broadening words and phrases such as “one or more,” “at least,” “but not limited to” or other like phrases in some instances shall not be read to mean that the narrower case is intended or required in instances where such broadening phrases may be absent.

Claims

1. A method comprising using at least one hardware processor to: receive an image of a document captured by a camera, wherein the document has a plurality of fields;preprocess the image of the document;receive content of at least one of the plurality of fields in the document via manual entry by a user;use the content to determine a location of the at least one field in the document;automatically determine locations of a plurality of other fields in the image of the document based on the determined location of the at least one field for which the content was manually entered by the user;extract identity data, associated with an individual, from the preprocessed image of the document, based on the determined locations of the plurality of fields;automatically populate fields of an enrollment form for a transaction based at least in part upon the identity data;create a new financial account based on the enrollment form; andfund the new financial account by receiving an image of a check or credit card captured by the camera,extracting at least an account number from the image of the check or credit card, andinitiating a transfer of funds to the new financial account from an existing financial account associated with the extracted account number.

2. The method of claim 1, further comprising using the at least one hardware processor to: validate the identity data to assess a quality of the identity data; andverify the identity data to assess an identity risk of the individual to a financial services organization, wherein the identity risk is a risk that the identity data of the individual is unreliable.

3. The method of claim 2, further comprising using the at least one hardware processor to organize results of the validation and verification into a mobile identity risk scorecard, wherein the mobile identity risk scorecard comprises a structured information model that indicates risks associated with the set of identity data and comprises one or more indicators which denote aspects of identity risk.

4. The method of claim 3, wherein the one or more indicators comprise one or more numeric indicators which denote identity risk.

5. The method of claim 3, wherein the one or more indicators comprise one or more graphical indicators which denote identity risk.

6. The method of claim 1, wherein the method is implemented as a software library executed by the at least one hardware processor.

7. The method of claim 6, wherein the software library is embedded in a mobile application.

8. The method of claim 1, wherein the document is a government-issued identity document.

9. The method of claim 8, wherein the government-issued identity document is a driver's license.

10. The method of claim 8, wherein the government-issued identity document is a passport.

11. The method of claim 8, wherein the government-issued identity document is a military identification card.

12. The method of claim 1, wherein preprocessing comprises cropping the image of the document.

13. The method of claim 1, wherein preprocessing comprises de-skewing the image of the document.

14. The method of claim 1, wherein preprocessing comprises de-warping the image of the document.

15. The method of claim 1, wherein preprocessing comprises converting text in the image of the document into reverse text.

16. The method of claim 1, wherein preprocessing comprises creating one or more bi-tonal images from the image of the document.

17. The method of claim 1, wherein extracting the identity data comprises: calculating a confidence score for each of a plurality of fields; andindividually highlighting each of the plurality of fields for which the calculated confidence score is below a fixed value.

18. The method of claim 1, wherein extracting the identity data comprises: reading a barcode in the preprocessed image of the document to produce a string;parsing the string to identify one or more barcode fields, while applying a rules engine to handle exceptions in the string; andcross-validating content of the plurality of fields with content of the one or more barcode fields.

19. A system comprising: at least one hardware processor; andone or more software modules that are configured to, when executed by the at least one hardware processor, receive an image of a document captured by a camera, wherein the document has a plurality of fields,preprocess the image of the document,receive content of at least one of the plurality of fields in the document via manual entry by a user,use the content to determine a location of the at least one field in the document,automatically determine locations of a plurality of other fields in the image of the document based on the determined location of the at least one field for which the content was manually entered by the user,extract identity data, associated with an individual, from the preprocessed image of the document, based on the determined locations of the plurality of fields,automatically populate fields of an enrollment form for a transaction based at least in part upon the identity data,create a new financial account based on the enrollment form, andfund the new financial account by receiving an image of a check or credit card captured by the camera,extracting at least an account number from the image of the check or credit card, andinitiating a transfer of funds to the new financial account from an existing financial account associated with the extracted account number.

20. A non-transitory computer-readable medium having instructions stored thereon, wherein the instructions, when executed by a processor, cause the processor to: receive an image of a document captured by a camera, wherein the document has a plurality of fields;preprocess the image of the document;receive content of at least one of the plurality of fields in the document via manual entry by a user;use the content to determine a location of the at least one field in the document;automatically determine locations of a plurality of other fields in the image of the document based on the determined location of the at least one field for which the content was manually entered by the user;extract identity data, associated with an individual, from the preprocessed image of the document, based on the determined locations of the plurality of fields;automatically populate fields of an enrollment form for a transaction based at least in part upon the identity data;create a new financial account based on the enrollment form; andfund the new financial account by receiving an image of a check or credit card captured by the camera,extracting at least an account number from the image of the check or credit card, andinitiating a transfer of funds to the new financial account from an existing financial account associated with the extracted account number.