rPPG Liveness Detection via Time-Domain Waveform Analysis

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional liveness detection methods using remote photoplethysmography (rPPG) face challenges in distinguishing between real and fake images due to light source changes and motion interference, leading to misjudgments, especially with high-quality images and fixed frequency signals.

Innovation Solution

The method involves acquiring a full cycle of rPPG signals from a skin image, extracting waveform characteristics such as dicrotic notch, systolic, and diastolic waves, and determining liveness based on these features without requiring time-frequency transforms, thereby enhancing detection accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If time-frequency transform is used to analyze rPPG signals, then spectral stability is improved, but processing time increases and real-time operation becomes difficult

Engineering Contradiction:

Improvespectral stabilityVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent extracts only the essential waveform characteristics (peak positions, trough positions, interval times) directly from the time-domain rPPG signal, eliminating the need for time-frequency transform. This extraction approach maintains sufficient detection reliability while dramatically reducing processing time to enable real-time operation.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of transforming the signal from time domain to frequency domain (conventional approach), the patent inverts the approach by directly analyzing time-domain waveform characteristics. This inversion allows real-time processing while maintaining the ability to detect physiological signals.

Inventive Principle:

Principle #13The other way round (Inversion)

2Reliability

If conventional rPPG detection is used, then liveness detection capability is provided, but misjudgment occurs under fixed frequency light source changes or motion interference

Engineering Contradiction:

Improveliveness detection capabilityVSAvoiddetection accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent uses dynamic waveform characteristic analysis that adapts to varying conditions. By measuring interval times between peaks and troughs and analyzing waveform shapes dynamically, the system can distinguish real physiological signals from fake signals even under fixed frequency light source changes or motion interference.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent implements a verification mechanism where multiple waveform characteristics (peak-trough intervals, waveform shapes, temporal patterns) are analyzed together to verify liveness. This feedback-based verification reduces misjudgment by cross-checking multiple indicators before confirming liveness.

Inventive Principle:

Principle #23Feedback

3Reliability

If multiple rPPG signals are collected for time-frequency transform, then spectral stability is improved, but detection speed decreases

Engineering Contradiction:

Improvespectral stabilityVSAvoiddetection speed

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The patent extracts critical waveform features directly from individual or few rPPG signals without requiring extensive signal collection for spectral averaging. This extraction method maintains detection reliability while enabling fast processing of each signal, thus improving overall detection speed.

Inventive Principle:

Principle #2Taking out (Extraction)

4Reliability

If spectral disorder calculation is performed on rPPG spectrum, then liveness determination is made, but fixed frequency cycle signals cause misjudgment

Engineering Contradiction:

Improveliveness determinationVSAvoidliveness judgment accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

Instead of analyzing spectral disorder in the frequency domain, the patent inverts the approach by analyzing temporal patterns and waveform characteristics in the time domain. This allows accurate liveness judgment by examining the natural variability of waveform intervals and shapes, which fixed frequency cycle signals cannot replicate.

Inventive Principle:

Principle #13The other way round (Inversion)

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 effectively reduces misjudgments caused by light source changes and motion interference, providing improved liveness detection performance by directly analyzing rPPG waveform characteristics.

Implementation Method 1

rPPG is a non-contact detection method for detecting human heartbeat waveform and heart rate by using a camera, so as to determine whether a face in the captured image is a living face. The heart activity of the human body is used for producing a physiological signal, namely a change in the amount of subcutaneous microvessel congestion, which affects an absorption rate of light by the blood

Methodology Applied

Scientific EffectRemote photoplethysmography (rPPG): Absorption (EM radiation)

Data Source

PatentUS11074468B2Method of liveness detection and related device

Publication Date: 2021.07.27 FACEHEART INC

AI summary

A method of liveness detection for a computing device comprises acquiring at least one full cycle of a remote photoplethysmography, rPPG, signal from a skin image, extracting at least one rPPG waveform characteristic from the full cycle of the rPPG signal, and determining whether the skin image includes a life according to the extracted rPPG waveform characteristic.