Systems and methods for mobile image capture and content processing of driver's licenses

Patent metadata

Field	Value
Publication number	US-9298979-B2
Application number	US-201313844476-A
Country	US
Kind code	B2
Filing date	Mar 15, 2013
Priority date	Jan 18, 2008
Publication date	Mar 29, 2016
Grant date	Mar 29, 2016

Abstract

Systems and methods are provided for processing and extracting content from an image of a driver's license captured using a mobile device. In one embodiment, an image of a driver's license (DL) is captured by a mobile device and corrected to improve the quality of the image. The corrected image is then further processed by cropping the image, identifying the format and layout of the DL, binarizing the image and extracting the content using optical character recognition (OCR). Multiple methods of image cropping may be implemented to accurately assess the borders of the DL, and a secondary layout identification process may be performed to ensure that the content being extracted is properly classified.

First claim

What is claimed is:

1. A method of processing an image of a driver's license captured by a mobile device, comprising:
receiving a first image of a document captured by a mobile device;
cropping the first image around the document to produce a cropped image of the document, wherein cropping the first image includes using a rounded corner detection test;
determining whether the document is a driver's license based on whether one or more rounded corners are identified when cropping the first image using the rounded corner detection test, wherein the rounded corner detection test comprises approximating connected points of edge pixels of the cropped image with a spline and estimating a curvature of the spline; and
if the document is determined to be a driver's license,
identifying a layout of the driver's license;
binarizing the cropped image to produce a binarized image; and
outputting the binarized image of the driver's license.

2. The method of claim 1 , further comprising cropping the image through a rectangular shape detection test.

3. The method of claim 1 , further comprising identifying the document in the first image by performing the rounded corner detection test to identify at least one rounded corner of the document.

4. The method of claim 1 , wherein cropping the first image around the document further comprises determining coordinates of four corners of the document based on results of: a rectangular shape detection test; a feature matching test; and the rounded corner detection test.

5. The method of claim 1 , if the document is determined to be a driver's license, the method further comprises determining an aspect ratio of the driver's license and comparing the aspect ratio of the driver's license to at least one stored aspect ratio of a driver's license.

6. The method of claim 1 , wherein binarizing the cropped image includes identifying a photo area from an array of vertical contours and an array of horizontal contours and removing the photo area on the driver's license prior to binarizing the cropped image.

7. The method of claim 1 , further comprising performing an optical character recognition on the binarized image to extract text from the driver's license.

8. A system of processing an image of a driver's license captured by a mobile device, comprising:
a receiving unit which receives a first image of a document captured by a mobile device;
a cropping unit which crops the first image around the document to produce a cropped image of the document, wherein cropping the first image includes using a rounded corner detection test;
a format determination unit which determines whether the document is a driver's license based on whether one or more rounded corners are identified when cropping the first image using the rounded corner detection test, wherein the rounded corner detection test comprises approximating connected points of edge pixels of the cropped image with a spline and estimating a curvature of the spline;
a layout identification unit which identifies a layout of the driver's license if the document is determined to be a driver's license;
a binarization unit which binarizes the cropped image to produce a binarized image; and
an output unit which outputs the binarized image of the driver's license.

9. The system of claim 8 wherein the cropping unit is further configured to crop the image through a rectangular shape detection test.

10. The system of claim 8 , wherein the cropping unit is configured to identify the document in the first image by performing the rounded corner detection test to identify at least one rounded corner of the document.

11. The system of claim 10 , wherein the cropping unit identifies the document in the first image by determining coordinates of four corners of the document based on results of: a rectangular shape detection test; a feature matching test; and the rounded corner detection test.

12. The system of claim 8 , wherein if the document is determined to be a driver's license, the format identification unit is further configured to determine an aspect ratio of the driver's license and compare the aspect ratio of the driver's license to at least one stored aspect ratio of a driver's license.

13. The system of claim 8 , wherein the binarization unit is further configured to identify a photo area from an array of vertical contours and an array of horizontal contours and removes the photo area prior to binarizing the image.

14. The system of claim 8 , further comprising a text extraction unit which performs an optical character recognition on the binarized image to extract text from the driver's license.

Assignees

• Mitek Systems Inc

Inventors

• Nepomniachtchi Grigori
• Strange Mike

Classifications

• G06V30/1475 Primary

  Inclination or skew detection or correction of characters or of image to be recognised · CPC title

• G06V30/166

  Normalisation of pattern dimensions · CPC title

• G06V30/162

  Quantising the image signal · CPC title

• G06V30/10

  Character recognition · CPC title

• G06K9/38

  Physics · mapped topic