Mobile Driver License Image Processing and OCR Extraction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

There is a need for a method to efficiently extract and verify information from a driver's license for electronic transactions, as existing methods lack the capability to accurately process and utilize the information contained in a driver's license captured by a mobile device.

Innovation Solution

A system and method for capturing and processing images of driver's licenses using a mobile device, which involves image correction, cropping, format and layout identification, binarization, and optical character recognition (OCR) to extract content from the images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If driver's license information is to be extracted for electronic transactions, then the capability to verify identity electronically is improved, but the complexity of processing and extracting information from the license increases

Engineering Contradiction:
Improveelectronic transaction capabilityVSAvoidinformation processing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The driver's license image is divided into multiple regions of interest (ROIs), each containing specific information such as name, address, date of birth, and license number. The system processes each region separately using targeted extraction methods, which simplifies the overall complex task of extracting all information from the license.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

An intermediary processing layer is introduced between the mobile device capture and the final electronic transaction verification. This intermediary system includes image correction, cropping, format identification, binarization, and OCR modules that work together to transform the raw image into structured data, making the complex extraction process manageable and automated.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Ease of operation

If mobile device capture is used for driver's license images, then ease of operation is improved, but image quality and processing accuracy deteriorate

Engineering Contradiction:
Improveuser convenienceVSAvoidimage quality and extraction accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs preliminary image correction operations immediately after capture, including geometric transformations to correct perspective distortion, contrast adjustment, and noise reduction. These preliminary actions prepare the image for subsequent processing steps, ensuring high accuracy despite the casual mobile capture method.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts processing parameters based on the captured image characteristics. Format identification determines the specific layout and orientation of the driver's license, and the system adapts its cropping and extraction parameters accordingly. This allows the system to maintain high accuracy across different capture scenarios by adjusting parameters to match the actual image properties.

Inventive Principle:
Principle #35Parameter changes

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables accurate extraction of important content from driver's licenses captured by mobile devices, improving user experience by allowing users to easily provide information to third parties through electronic transactions, such as insurance applications and identity verification.

Implementation Method 1

an image of a driver's license (DL) is captured by a mobile device

Methodology Applied
Scientific EffectPhotoelectric Effect: Photoelectric Effect

Implementation Method 2

binarizing the cropped image to produce a binarized image

Methodology Applied
Scientific EffectImage Processing: Image Processing

Implementation Method 3

extracting the content using optical character recognition (OCR)

Methodology Applied
Scientific EffectOptical Character Recognition:

Data Source

PatentUS10303937B2Systems and methods for mobile image capture and content processing of driver's licenses
Publication Date: 2019.05.28 MITEK SYSTEMS INC
  • US10303937B2 patent drawing
  • US10303937B2 patent drawing
  • US10303937B2 patent drawing

AI summary

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