Identity Document Face Image Screening Against Morphing Attacks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing identity document systems are vulnerable to image manipulation, such as morphing, which can compromise the reliability of automated access control systems and are difficult to prevent globally due to varying national standards and lack of digital signature verification.
Innovation Solution
Capture a high-quality digital reference facial image, analyze it for biometric features, and use manipulation indicators to detect image manipulation, converting the image to a lower resolution for storage in identity documents, with optional neural network evaluation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a single digital reference facial image is created from multiple individuals using image manipulation, then the image can match all individuals during manual and automated inspection, but the reliability of automated access control systems deteriorates
Solution Approach 1:
The patent applies preliminary action by performing manipulation detection on the digital reference facial image during the application process, before the image is stored in the identity document. This proactive approach prevents manipulated images from being accepted in the first place, rather than detecting them later during verification
Solution Approach 2:
The patent replaces manual inspection with automated manipulation detection systems that use technical analysis of the digital image itself. This substitution enables more consistent and reliable detection of manipulated images while maintaining efficiency
2Reliability
If manipulation detection is implemented during the application process, then the reliability of identity documents improves, but the complexity of the personalization process increases
Solution Approach 1:
The manipulation detection system analyzes the digital reference facial image automatically without requiring manual intervention. The system self-evaluates the image for manipulation artifacts, reducing the need for complex human review processes while maintaining high reliability
Solution Approach 2:
The patent extracts only the necessary manipulation detection analysis from the overall personalization process. By focusing specifically on detecting manipulation in the digital reference facial image rather than reworking the entire personalization workflow, the added complexity is minimized while security is enhanced
3Measurement precision
If high-resolution digital reference facial images are used for manipulation detection, then the detection accuracy improves, but the storage requirements and processing time increase
Solution Approach 1:
The patent performs manipulation detection on the high-resolution digital reference facial image during the application process, before the image is converted to lower resolution for storage. This ensures that the full-resolution image is available for accurate analysis, while the stored version in the identity document uses standard lower resolution
Solution Approach 2:
The manipulation detection system focuses analysis on specific local features and regions of the face image where manipulation artifacts are most likely to appear. This localized approach maintains high detection accuracy while reducing the overall computational burden and processing time
Data Source
Figure 1
Figure 2
AI summary
The invention relates to a device (100) for personalizing a person's identity document. The device (100) comprises an image acquisition device (101) configured to acquire a first digital reference facial image of the person, wherein the first digital reference facial image has a first reference image resolution. The device (100) further comprises a tamper detection device (103) configured to acquire a biometric reference feature in the first digital reference facial image, to compare the biometric reference feature with a biometric comparison reference feature in order to obtain a tamper indicator, and to detect image manipulation in the first digital reference facial image based on the tamper indicator.The device (100) further comprises an image generation unit (105) which is configured, if no image manipulation is detected, to generate a second digital reference face image based on the first digital reference face image, wherein the second digital reference face image has a second reference image resolution. The device (100) further comprises a personalization unit (107) which is configured to store the second digital reference face image in the person's identity document.