Vehicle Occupant Identification Using Context-Aware Voice and Face Biometrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing biometric identification technologies in vehicles, such as voice and facial recognition, are unreliable due to contextual changes affecting performance, leading to frequent identification failures.
Innovation Solution
A method combining voice and facial biometrics with context-aware data clustering to determine the most suitable technology for identification, using contextual parameters to optimize biometric identification by creating data clusters that distinguish between contexts where identification works or fails, and adjusting reference fingerprints based on context to enhance reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single biometric identification technology (voice or facial recognition) is used, then the device complexity is reduced, but the reliability of identification deteriorates due to contextual changes
Solution Approach 1:
The patent combines two different biometric identification technologies (voice recognition and facial recognition) into a unified identification system. The system records both a voice fingerprint and a facial fingerprint for each user, and during identification, compares the current biometric data against both types of stored fingerprints. This merging of multiple identification methods resolves the contradiction by maintaining high reliability through diverse biometric modalities while managing system complexity through integrated processing architecture.
Solution Approach 2:
The patent changes the parameter of identification approach from single-modal to multi-modal biometric verification. By recording and comparing both voice and facial characteristics, the system transforms the identification process into a more robust parameter set that is less susceptible to contextual variations. This parameter change enables the system to maintain reliable identification even when one biometric modality is affected by environmental factors.
2Reliability
If biometric identification is performed without context adaptation, then the ease of operation is maintained, but the reliability deteriorates due to contextual factors affecting biometric data
Solution Approach 1:
The patent implements preliminary action by pre-recording multiple types of biometric fingerprints (voice and facial) during an enrollment phase before actual identification is needed. During operation, the system simply compares current biometric data against these pre-stored references without requiring complex real-time context analysis. This preliminary preparation resolves the contradiction by establishing reliable identification templates in advance, allowing the system to maintain both high reliability and operational simplicity during actual use.
3Reliability
If multiple biometric fingerprints are recorded and compared, then the reliability of identification is improved, but the loss of time increases due to additional comparison steps
Solution Approach 1:
The patent applies partial action by implementing a hierarchical comparison process where the system can perform identification using one biometric modality when conditions permit, and only resort to additional comparison steps when necessary. The system evaluates the quality and reliability of each biometric input and selectively engages additional verification methods only when needed, thus maintaining high reliability while minimizing unnecessary processing time.
Data Source
Figure 1
Figure 2
AI summary
The invention relates to a method for identifying an occupant (20) of a motor vehicle (10), wherein the following steps are provided: a) recording at least two biometric impressions of the occupant, b) comparing at least one of the two biometric impressions with at least one reference impression, and c) identifying the occupant in accordance with the result of the comparison. The invention further provides: - a step of acquiring at least one data item relating to the context of the recording, each data item being recorded in a database (15) in which previously acquired data items are already recorded, the set of recorded data items being distributed into four clusters associated with four situations which give information on the chances of identifying the occupant from each impression acquired, and - a step of recording in the database one of the recorded biometric impressions as a new reference impression if only one of the two impressions has allowed the occupant to be identified.