3D Head Capture Using Guided Stimulus and Single-Camera Views

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for generating three-dimensional facial models for identity documents and access control systems are costly and require complex image processing, often resulting in inaccuracies, especially at the edges of the face, and necessitate the storage of both 3D and 2D images, which can be compromised by occlusions and equipment limitations.

Innovation Solution

A method involving optical capture of a person's head from multiple directions using a single camera, guided by a visual or auditory stimulus moving along a defined trajectory, generating high-quality three-dimensional models by combining two-dimensional data sets to determine depth information, with quality control for missing or defective pixels.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If multiple cameras are used to capture 3D models, then measurement precision and reliability are improved, but device complexity and cost increase

Engineering Contradiction:
Improveaccuracy in determining facial point positionsVSAvoidnumber of cameras and equipment complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the 360-degree head rotation into multiple discrete angular positions (e.g., 0°, 45°, 90°, 135°, 180°, 225°, 270°, 315°). At each position, a single camera captures a 2D image. These segmented views are then synthesized into a complete 3D model, avoiding the need for multiple simultaneous cameras while maintaining measurement precision.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent transitions from capturing multiple images simultaneously with multiple cameras to capturing sequential images with a single camera while rotating the head through different angular dimensions. This dimensional approach to rotation enables 3D reconstruction using one camera instead of multiple, reducing device complexity while preserving measurement accuracy.

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

2Reliability

If multiple cameras are used to capture 3D models, then reliability is improved through occlusion compensation, but manufacturing cost increases

Engineering Contradiction:
Improvecompensation for occlusionsVSAvoidequipment cost
Core Design Contradiction:
ReliabilityVSEase of manufacture

Solution Approach 1:

The patent segments the head rotation into multiple discrete angular positions, capturing images at each position with a single camera. By systematically rotating the head through these segmented angles, the system ensures complete coverage of all facial surfaces, including areas that might be occluded in any single view, thereby achieving reliable occlusion compensation with inexpensive equipment.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent employs continuous head rotation through multiple angular positions, with the camera capturing images at each position. This continuous sequential capture ensures that no facial area remains unobserved, providing comprehensive coverage and reliable occlusion compensation using a single camera system rather than multiple expensive cameras.

Inventive Principle:
Principle #20Continuity of useful action

3Device complexity

If a single camera is used to capture images from multiple directions, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improvenumber of camerasVSAvoidaccuracy of 3D model
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent compensates for the limitations of a single camera by introducing head rotation through multiple angular dimensions (0°, 45°, 90°, 135°, 180°, 225°, 270°, 315°). This dimensional approach allows the single camera to capture images from effectively multiple directions by rotating the subject, thereby maintaining measurement precision while reducing device complexity.

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

Solution Approach 2:

The patent uses continuous head rotation to capture images at multiple angular positions with a single camera. This continuous action ensures comprehensive coverage of the head surface, allowing the single camera to gather sufficient data for accurate 3D reconstruction, thus maintaining measurement precision despite using only one camera instead of multiple.

Inventive Principle:
Principle #20Continuity of useful action

4Adaptability or versatility

If 2D images are stored for access control systems, then backward compatibility is maintained, but security is compromised by potential forgery

Engineering Contradiction:
Improvebackward compatibility with existing systemsVSAvoidsecurity against image forgery
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent generates multiple 2D images from a single 3D model by projecting the 3D data at different angular positions (0°, 45°, 90°, 135°, 180°, 225°, 270°, 315°). This segmentation of the 3D model into multiple 2D views provides rich biometric data that is difficult to forge, while still maintaining compatibility with existing 2D-based access control systems through the generated 2D images.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates multiple 2D image copies from a single high-quality 3D model. These copied 2D images serve as reference data for access control while the underlying 3D model provides enhanced security. The 2D copies maintain backward compatibility with existing systems, while the 3D source prevents forgery by providing depth information and geometric accuracy that cannot be replicated in 2D.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4075396B1Method and assembly for optically detecting a head of a person
Publication Date: 2026.02.18 BUNDESDRUCKEREI GMBH
  • EP4075396B1 patent drawingFigure 1
  • EP4075396B1 patent drawingFigure 2~3
  • EP4075396B1 patent drawingFigure 4~5

AI summary

The invention relates to a method for optically capturing the head of a person (200), comprising the following steps: - Optically capturing a first image of the head of the person (200) from a first direction using a camera (102) and generating a first two-dimensional data set from the first image, - Moving an optical or acoustic stimulus along a trajectory (301) to a first stop (303), causing the person (200) to move their head to follow the stimulus to the first stop (303), - Optically capturing at least a second image of the head of the person (200) from a second direction using the camera (102) or using a second camera (112) and generating a second two-dimensional data set from the second image,and - determining depth information and/or a three-dimensional model by combining the data sets using an evaluation unit (108) of a processor unit (106). The invention also relates to an arrangement (100) for carrying out the method.