Mobile Identity Verification via Multi-Source Image Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for verifying user identity on mobile devices, especially for accessing restricted services, face challenges in reliably matching low-quality images from identity documents with higher-quality images captured by devices, leading to inefficiencies and potential security risks.
Innovation Solution
A method that involves capturing images of an identity document and the device user, comparing these images with a digital image stored on an integrated circuit, and forming an association to verify the user's identity, which can be used for secure access and subsequent authentication events, improving reliability through three-way comparisons and image quality assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If a camera captures an image of an identity document for verification, then the verification process can be automated, but the image quality from identity documents is typically low which reduces matching accuracy
Solution Approach 1:
The patent combines multiple image sources (identity document image, live user image, and reference image from integrated circuit) into a unified verification process. The processing system merges these different image qualities and sources, using the reference image from the integrated circuit as a high-quality baseline to improve overall matching accuracy despite the low quality of the captured identity document image.
Solution Approach 2:
The reference image stored in the integrated circuit acts as an intermediary element. Instead of directly comparing the low-quality captured image with the identity document, the system uses the high-quality reference image as a mediator to establish accurate facial recognition, thereby bridging the quality gap between captured and stored images.
2Reliability
If the system compares multiple images (identity document image, live user image, and digital image from integrated circuit), then verification reliability improves, but the processing complexity increases
Solution Approach 1:
The verification process is segmented into distinct comparison stages: first comparing the captured identity document image with the reference image, then comparing the live user image with the reference image, and finally validating the association between user and device. This segmentation allows the complex multi-image verification to be broken down into manageable steps handled by dedicated processing modules.
Solution Approach 2:
The system creates a digital copy of the reference image from the integrated circuit and uses this copy for comparison operations. By working with digital copies rather than manipulating the original physical documents and multiple captured images simultaneously, the processing complexity is reduced while maintaining verification reliability.
3Reliability
If the system forms an association between previously authenticated user and mobile device, then security against suspicious behavior improves, but the system complexity increases
Solution Approach 1:
The system performs preliminary verification by comparing images and forming an association between the user and device before allowing access to restricted services. This preliminary action establishes a trusted relationship in advance, and the association is then used for subsequent authentication events, reducing the need for complex real-time verification while maintaining security.
Solution Approach 2:
Once the association is formed, the system uses this pre-established relationship to enable self-service authentication. The association data stored in the processing system allows the mobile device to autonomously verify user identity without requiring complex continuous verification processes, thereby reducing system complexity while maintaining security.
Data Source
AI summary
A method of determining whether a user of a mobile device corresponds to a previously authenticated user. The method comprises: acquiring a first image from the identity document, the first image being a photographic image and or a digital image; causing a camera connected to or integral with the mobile device to capture a second image, the second image corresponding to a user of the mobile device; comparing data indicative of the first image and data indicative of the second image, whereby to determine whether the first image and the second image represent the same user; and responsive to determining that the first image and the second image represent the same user, forming an association between the previously authenticated user and the mobile device.