Identity Authentication Verification Using Sequential Image Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing electronic transaction systems face challenges in verifying the authenticity of users, particularly in scenarios where unauthorized access occurs, as facial recognition may not distinguish between the authorized user and a submitted photograph, leading to potential fraud.

Innovation Solution

The system captures two images sequentially and compares them for similarity, using metadata such as time and location information, along with facial recognition, to determine if the images are from the same authentic source, thereby enhancing identity verification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If facial recognition is used for identity verification, then authentication speed is improved, but reliability deteriorates because it cannot distinguish between an authorized user and a submitted photograph

Engineering Contradiction:
Improveauthentication speedVSAvoididentity verification reliability
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system captures a second reference image immediately before capturing the first submission image, establishing a temporal sequence that prevents photo substitution attacks. This preliminary action creates a baseline that must be temporally consistent with the submission, adding a time-based verification layer that maintains fast authentication while preventing fraud

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system compares the first submission image with the second reference image to verify temporal consistency and detect whether the same photograph is being submitted. This feedback mechanism analyzes image similarity, metadata consistency, and temporal relationships to determine authentication validity, thereby improving reliability without significantly impacting authentication speed

Inventive Principle:
Principle #23Feedback

2Reliability

If multiple images are captured and compared for verification, then reliability is improved, but device complexity increases

Engineering Contradiction:
Improveidentity verification reliabilityVSAvoidverification system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The verification process is segmented into distinct phases: capturing the first submission image, capturing the second reference image, comparing the two images, and making an authentication decision. This segmentation allows each component to be independently optimized and managed, reducing overall system complexity while maintaining high reliability through systematic multi-image verification

Inventive Principle:
Principle #1Segmentation

3Measurement precision

If image comparison with metadata analysis is performed, then measurement precision is improved, but loss of time increases

Engineering Contradiction:
Improveimage source verification precisionVSAvoidverification time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs partial metadata analysis by focusing on critical fields such as timestamp, device ID, and location information rather than analyzing all possible metadata. This selective approach provides sufficient verification precision to detect photo substitution while minimizing the time overhead associated with comprehensive metadata processing

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS10579783B1Identity authentication verification
Publication Date: 2020.03.03 BLOCK INC
  • US10579783B1 patent drawing
  • US10579783B1 patent drawing
  • US10579783B1 patent drawing

AI summary

Systems and methods for identity authentication verification are disclosed. First image data corresponding to a first image is submitted in response to a request to authenticate the identity of a user of a device. A second image is captured shortly after the first image is captured. The first and second image data and/or metadata associated with the first and second image are compared and analyzed to determine if the first image is an authentic image captured by a camera of the device and if the person depicted in the first image is the user of the device.