Remote Deceit Detection Using Webcam Physiological Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current deceit detection systems require physical contact or proximity to the individual, making them unsuitable for remote evaluations, such as personnel recruitment or insurance claim processes, where physiological signals cannot be effectively analyzed from a distance.
Innovation Solution
A non-invasive remote deceit detection system using a webcam, microphone, and screen to capture photoplethysmographic signals, facial expressions, and acoustic signals, processed through machine learning algorithms to determine the probability of deceit without physical sensors, employing an avatar for interaction and visual/auditory stimuli.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If physical contact or proximity sensors are used to detect physiological signals, then measurement precision is improved, but device complexity and ease of operation worsen due to requiring physical connection
Solution Approach 1:
The patent replaces mechanical/physical contact-based sensing systems with optical sensing. Specifically, it uses a webcam to capture photoplethysmographic signals through remote photoplethysmography (rPPG), substituting the need for physical sensors attached to the body with non-contact optical imaging. This allows physiological signal detection without mechanical connection while maintaining measurement precision.
Solution Approach 2:
The patent introduces light as an intermediary medium to transfer physiological information from the subject to the detector. By using light reflection from the face to carry photoplethysmographic signals, the system creates an indirect measurement path that eliminates the need for direct physical contact between sensors and the body, enabling remote operation.
2Measurement precision
If specialized sensors are used to obtain physiological signals, then measurement precision is improved, but device complexity increases due to multiple sensors and physical connection requirements
Solution Approach 1:
The patent makes the webcam device universal by enabling it to perform multiple functions: standard video capture and photoplethysmographic signal detection. By processing different aspects of the same video feed, the system extracts both visual information and physiological data (heart rate, respiratory rate, blood oxygen saturation) from a single device, eliminating the need for multiple specialized sensors.
Solution Approach 2:
The patent replaces complex multi-sensor physical measurement systems with a simplified optical imaging system. Instead of using separate sensors for cardiac activity, electrodermal changes, and respiratory patterns, the system uses a single webcam to capture all these physiological signals through light reflection variations in the facial region.
3Reliability
If physical sensors are used to detect physiological signals, then reliability is improved, but ease of operation worsens in remote scenarios
Solution Approach 1:
The patent replaces mechanical sensor attachment systems with non-contact optical measurement, enabling reliable deceit detection in remote scenarios. The system maintains reliability by accurately detecting physiological indicators of deceit (heart rate variability, respiratory patterns, blood oxygen changes) without requiring physical presence or sensor attachment, thus resolving the contradiction between reliability and remote operability.
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
Enables remote detection of deceit probability by analyzing heart rate variability, vasoconstriction, and other physiological variables through image and audio processing, providing a reliable assessment without physical contact, suitable for various remote interaction scenarios.
Implementation Method 1
process remote photoplethysmographic signals acquired from sequenced images taken from the face of an evaluated individual
Implementation Method 2
In the acquisition of these signals, the screen in front of which the interviewed individual is located, and the ambient light are used as a light source
Data Source
AI summary
Non-invasive system and method to determine a probability of deceit based on the remote measurement of physiological changes that the evaluated individual presents when interacting with stimuli provided by the system after a pre-interview assisted by an avatar. The system comprises an interaction module, a face recognition and localization module, a processing module, and a deceit probability determination module. The system records the conscious responses of the evaluated individual and determines the physiological variables of the individual, and their changes caused by stress and cognitive load in response to the stimuli generated to calculate a probability of deceit in the conscious responses made by the individual.