IR Reader Face Counting for Identity Document Forgery Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for detecting forgeries in identification documents with facial images containing IR-absorbing components are inadequate, particularly when the facial image is overprinted or pasted with additional IR-absorbing images, as they rely solely on the presence of IR-absorbing components to distinguish authenticity.

Innovation Solution

A method involving IR reader data processing to determine the number of recognized faces using face recognition software, generating a test signal if more than one face is detected, indicating potential forgery, thereby leveraging both original and forged IR data for more accurate detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If only the presence of IR-absorbing components is checked to detect forgeries, then the detection method is simple, but it fails to detect forgeries where the facial image is overprinted or pasted with additional IR-absorbing images

Engineering Contradiction:
Improveforgery detection accuracyVSAvoiddetection method complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the IR-absorbing components into multiple facial images by applying face recognition software to the IR data. Instead of treating the IR absorption as a single binary presence/absence feature, the system divides it into distinct face instances, allowing detection of multiple faces which indicates potential forgery through overprinting or pasting.

Inventive Principle:
Principle #1Segmentation

2Reliability

If facial recognition software is applied to IR data to count faces, then forgery detection accuracy improves, but processing time and computational complexity increase

Engineering Contradiction:
Improveforgery detection accuracyVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent performs preliminary face recognition processing on the IR-absorbing components before making the forgery determination. By pre-processing the IR data to identify and count distinct faces, the system prepares the critical information in advance, enabling faster final decision-making and reducing overall processing time while maintaining high detection accuracy.

Inventive Principle:
Principle #10Preliminary action

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

This approach enhances forgery detection accuracy by identifying multiple faces in IR data, providing a reliable and error-reduced method to alert for potential manipulations in facial images, such as overprinting or pasting, beyond simple IR absorption checks.

Implementation Method 1

Reading the IR-absorbing components of the facial image with an IR reader

Methodology Applied
Scientific EffectInfrared radiation detection: Infrared Radiation

Data Source

PatentEP3302994B1Method for recognizing counterfeits of identity documents, where the photo portrait image contains ir-absorbers
Publication Date: 2021.10.06 BUNDESDRUCKEREI GMBH
  • EP3302994B1 patent drawingFigure 1~2

AI summary

The invention relates to a method for recognising forgeries of identification documents containing a facial image with IR-absorbent components. The method comprises the following steps: (i) reading out the IR-absorbent components of the facial image using an IR reader; (ii) determining a number of recognised faces using facial recognition software, on the basis of the read-out IR-absorbent components of the facial image; and (iii) if the number of recognised faces is greater than 1, generating a test signal.