Finger Verifier Using Projected Fringe Pattern Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for verifying the authenticity of fingerprints, such as those using three-dimensional reconstruction, are time-consuming and prone to fraud detection issues due to the need for precise calibration and are not suitable for contactless verification.

Innovation Solution

A method employing a projection device to project parallel lines onto the finger, capturing the image, extracting fringes, calculating physical characteristics like variance and deflection, and comparing them with reference values to determine authenticity, without requiring three-dimensional reconstruction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If three-dimensional reconstruction methods are used for finger verification, then detection accuracy is improved, but calculation time increases significantly

Engineering Contradiction:
Improvedetection accuracyVSAvoidcalculation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts only the essential two-dimensional fringe pattern information from the projected lines, eliminating the need for complex three-dimensional reconstruction. By focusing solely on analyzing the 2D fringe characteristics (curvature, spacing, orientation) directly captured by the camera, the system achieves sufficient detection accuracy while dramatically reducing calculation time and computational complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of projecting lines and then performing complex 3D reconstruction to analyze surface geometry, the patent inverts the approach by directly analyzing the 2D fringe patterns formed by the projected lines. This inversion allows the system to detect finger authenticity through simpler 2D image processing of fringe characteristics rather than through time-consuming 3D reconstruction algorithms.

Inventive Principle:
Principle #13The other way round (Inversion)

2Measurement precision

If precise calibration between projector and camera is performed, then measurement precision is improved, but device complexity increases

Engineering Contradiction:
Improvecalibration precisionVSAvoidcalibration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent makes the verification system universally applicable by eliminating the need for precise calibration between the projector and camera. The method works with various projector-camera configurations without requiring complex calibration procedures, making the system easier to deploy and maintain while maintaining sufficient measurement precision for fraud detection.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent adopts a pragmatic approach by using standard, easily obtainable projectors and cameras without requiring precision calibration equipment or procedures. The system accepts that the calibration may not be perfectly precise but demonstrates that this level of precision is sufficient for the intended application of finger verification, thereby reducing device complexity and cost.

Inventive Principle:
Principle #27Cheap short-living objects (Disposable)

3Ease of operation

If contactless verification is implemented, then ease of operation is improved, but detection reliability decreases

Engineering Contradiction:
Improvecontactless operationVSAvoidfraud detection reliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent maintains reliable fraud detection in contactless mode by analyzing the two-dimensional spatial characteristics of the fringe patterns. The curvature, spacing, and orientation of the fringes captured in the 2D image plane provide sufficient information to distinguish real fingers from fake ones, even without physical contact. This 2D analysis compensates for the lack of tactile feedback while preserving detection reliability.

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

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 faster and more effective detection of fraud, including decoys like latex or paper, by analyzing two-dimensional data, reducing calculation time and improving contactless verification accuracy.

Implementation Method 1

a projection device designed to project a test pattern consisting of a plurality of lines parallel to each other on the finger

Methodology Applied
Scientific EffectLight reflection: Reflection

Implementation Method 2

a capture device provided for capturing an image of the finger and of the crosshairs

Methodology Applied
Scientific EffectPhotoelectric effect: Photoelectric Effect

Data Source

PatentEP3320481B1Method for verifying the veracity of a finger
Publication Date: 2023.01.18 IDEMIA IDENTITY & SECURITY FRANCE SAS
  • EP3320481B1 patent drawingFigure 1~5
  • EP3320481B1 patent drawingFigure 3a~4c
  • EP3320481B1 patent drawingFigure 6~7

AI summary

The invention relates to a method for verifying (200) the veracity of a finger by a verification device comprising a projection device projecting a pattern of lines which are parallel and orthogonal to the longitudinal direction of the finger, a capture device capturing an image of the finger and the pattern, and a processing unit, the method comprising: a lighting step (201) in which the projection device lights up the finger with the pattern, a contactless capture step (202) in which the capture device captures a pattern image of the projected pattern, a step of extracting fringes (206) in which the processing unit extracts fringes from the pattern image, a feature calculation step (208) in which the processing unit calculates a feature relative to the physical structure of the fringes, a comparison step (210) during which the processing unit compares the calculated feature with reference values, and a decision-making step (212) in which the processing unit makes a decision regarding the veracity of the finger.