Government ID card validation systems

Patent metadata

Field	Value
Publication number	US-10242283-B1
Application number	US-201816150772-A
Country	US
Kind code	B1
Filing date	Oct 3, 2018
Priority date	Oct 3, 2018
Publication date	Mar 26, 2019
Grant date	Mar 26, 2019

Abstract

Systems and methods for pre-validating a digital image of an identification (ID) card (e.g., a government-issued passport, driver's license, etc.) are disclosed. A mobile computing device captures image(s) of an ID card. In response, a pre-validation system in communication with the mobile computing device analyzes one or more quality features of the image(s), which includes determining, utilizing a trained neural network (trained using a dataset including images that have been accepted by a post-validation platform and images that have been rejected by the post-validation platform) and based on the one or more quality features, whether at least a first image of the captured image(s) is usable by a remote post-validation process. Responsive to the determining that the at least a first image is usable, the mobile computing device transmits the first image to a remote server for post-validation of the identification card.

First claim

The invention claimed is:

1. A computer-implemented method for pre-validation of identification images prior to transfer of the images to a remote server for post-validation, the method comprising:
capturing, by a mobile computing device, one or more images of an identification card;
analyzing, by a pre-validation system in communication with the mobile computing device, one or more quality features of the one or more images, wherein the analyzing comprises:
determining, utilizing a trained neural network and based on the one or more quality features, whether at least a first image of the one or more captured images is usable by a remote post-validation process, the neural network having been trained using a dataset including images that have been accepted by a post-validation platform and images that have been rejected by the post-validation platform; and

responsive to the determining that the at least a first image is usable, transmitting, by the mobile computing device, the first image to a remote server for post-validation of the identification card.

2. The method of claim 1 , wherein analyzing the one or more quality features of the one or more images comprises determining a ratio of a size of the captured one or more images of the identification card to a full size of the captured image.

3. The method of claim 1 , wherein the identification card comprises one or more of: a government-issued identification card, a credit card, a debit card, a loyalty card, an access card, and a stored value card.

4. The method of claim 1 , wherein analyzing the one or more quality features of the one or more images comprises determining a distance between the mobile computing device and the identification card during capture of the one or more images.

5. The method of claim 1 , further comprising outputting, to a display of the mobile computing device, feedback information related to the one or more analyzed quality features.

6. The method of claim 1 , wherein the one or more quality features comprise one or more of: fill ratio, blur, framing, rotation, keystone, sharpness, brightness, contrast, color, presence of an image of a human face, and whether the one or more images were captured live by the mobile computing device.

7. The method of claim 1 , wherein determining whether at least a first image of the one or more captured images is usable by the remote post-validation process further comprises analyzing the first image for the presence of one or more indicia.

8. The method of claim 1 , wherein the mobile computing device is in communication with the pre-validation system via a web application.

9. A system comprising:
a computing device in communication with a remote server, the computing device comprising:
one or more processors;
memory in communication with the one or more processors;
an image capture component configured to capture one or more images of an identification card and store the one or more captured images in the memory;
a trained neural network in communication with the memory, and configured to analyze one or more quality features of the one or more images;
instructions stored in the memory that, when executed by the one or more processors, cause the computing device to:
determine whether at least a first image of the one or more captured images is usable by a remote post-validation process based at least in part on the one or more analyzed quality features; and
responsive to determining that the at least a first image is usable, transmitting, by the computing device, the first image to the remote server for post validation of the identification card.

10. The system of claim 9 , wherein the computing device further includes one or more sensors configured to determine a distance between the computing device and the identification card.

11. The system of claim 10 , further comprising outputting, to a display of the computing device, feedback information related to the determined distance.

12. The system of claim 9 , wherein the identification card comprises one or more of: a government-issued identification card, a credit card, a debit card, a loyalty card, an access card, and a stored value card.

13. The system of claim 9 , wherein the instructions further cause the one or more processor to output, to a display of the computing device, feedback information related to the one or more analyzed quality features.

14. The system of claim 9 , wherein the one or more quality features comprise one or more of: fill ratio, distance between the image and the capture component, blur, framing, rotation, keystone, sharpness, brightness, contrast, color, presence of an image of a human face, and whether the one or more images were captured live by the image capture component.

15. The system of claim 9 , wherein determining whether at least one of the one or more captured images is usable by a remote post-validation process further comprises analyzing the one or more images for the presence of one or more indicia.

16. A system comprising:
a trained neural network configured to analyze one or more quality features associated with one or more images of an identification card, the neural network having been trained using a dataset including images that have been accepted by a post-validation platform and images that have been rejected by the post-validation platform; and
a computing device in communication with the trained neural network, the computing device comprising:
one or more processors;
memory in communication with the one or more processors;
instructions stored in the memory that, when executed by the one or more processors, cause the computing device to:
determine whether at least a first image of the one or more images is usable by a remote post-validation process based at least in part on the one or more analyzed quality features;

wherein the trained neural network is further configured to determine whether at least the first image is usable by the remote post-validation process.

17. The system of claim 16 , wherein the computing device further comprises the trained neural network and an image capture component configured to capture one or more images of the identification card and store the one or more captured images in the memory.

18. The system of claim 16 , wherein the computing device is configured to detect a distance between the computing device and an identification card.

19. The system of claim 16 , wherein the computing device is in communication with the trained neural network via a web application.

20. The system of claim 16 , wherein the trained neural network is configured to determine whether at least the first image is usable by the post-validation process based on one or more quality features comprising on or more of: distance between the image and the capture component, fill ratio, blur, framing, rotation, keystone, sharpness, brightness, contrast, color, presence of an image of a human face, and whether the one or more images were captured live by the mobile computing device.

Assignees

• Capital One Services Llc

Inventors

• Jain Chintan
• Fox Ryan
• Boyle Monika Valiramani

Classifications

• G06V10/255

  Detecting or recognising potential candidate objects based on visual cues, e.g. shapes · CPC title

• G06F18/2178

  based on feedback of a supervisor · CPC title

• G06F18/22

  Matching criteria, e.g. proximity measures · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06V10/40

  Extraction of image or video features · CPC title