IR Depth Analysis for Spoofing Detection in Identity Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automated systems for authenticating identity and verifying age for restricted goods and services struggle to effectively detect spoofing attempts, where an individual presents an image of another person, leading to potential unauthorized access.

Innovation Solution

The implementation of infrared (IR) imaging to detect liveness by capturing both color and IR images of an individual presenting identification, analyzing facial landmarks, and determining depth values to differentiate between real and spoofed presentations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional authentication systems use only color imaging to verify identity, then the system is simple and cost-effective, but the system cannot detect spoofing attempts where an individual presents an image of another person

Engineering Contradiction:
Improveauthentication accuracyVSAvoidimaging system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent transitions from 2D color imaging to 3D depth imaging by capturing infrared images and calculating depth values for facial landmarks. This dimensional change enables the system to detect spoofing attempts by analyzing the physical depth structure of the face, which cannot be replicated in flat images or videos.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent replaces traditional visual recognition methods with infrared imaging and depth calculation mechanisms. By using infrared sensors to capture thermal or structural information and computing depth values through coordinate transformation and depth mapping, the system achieves spoofing detection capability that goes beyond conventional color-based authentication.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If the system captures and processes both color and infrared images with depth analysis, then spoofing detection accuracy improves, but processing time and computational resources increase

Engineering Contradiction:
Improveliveness detection precisionVSAvoidauthentication processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary processing by capturing both color and infrared images simultaneously and pre-calculating facial landmark coordinates in the color image space. The system also pre-establishes the transformation relationship between color and infrared coordinate systems, so that depth values can be quickly computed without extensive real-time processing.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates a depth map as a simplified representation of the 3D facial structure by mapping infrared intensity values to depth values at facial landmark positions. This copied depth information serves as a compact feature set that captures essential liveness characteristics without requiring full 3D reconstruction, reducing computational overhead.

Inventive Principle:
Principle #26Copying

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 enables accurate detection of spoofing attempts, ensuring that only the actual individual represented in the identification can access age-restricted goods and services, thereby enhancing security and authenticity in automated authentication systems.

Implementation Method 1

using infra-red (IR) imaging to detect liveness of an individual that is presenting identification for authentication

Methodology Applied
Scientific EffectInfrared radiation detection: Infrared Radiation

Data Source

PatentEP3869395B1Identity and liveness verification
Publication Date: 2025.06.04 ACCENTURE GLOBAL SOLUTIONS LTD
  • EP3869395B1 patent drawingFigure 1A~1B
  • EP3869395B1 patent drawingFigure 2A~2B
  • EP3869395B1 patent drawingFigure 3

AI summary

Implementations of the present disclosure include receiving a color image and an IR image, the IR image taken contemporaneously with the color image, providing a set of facial landmarks depicted in the color image, determining a depth value for each facial landmark in the set of color landmarks, depth values being provided from the IR image, determining an average depth difference based on at least a sub-set of facial landmarks in the set of facial landmarks, comparing the average depth difference to a difference threshold to provide a comparison, and selectively authenticating the person based on the comparison.