Multi-modal person recognition for vehicular applications

Keyphrases

• Modal 100%
• Gaussian Mixture Model 100%
• Person Recognition 100%
• Vehicular Applications 100%
• Driving Signal 66%
• Japan 33%
• Principal Coordinate Analysis (PCoA) 33%
• Face Recognition 33%
• Feature-based 33%
• Face Image 33%
• Sigmoid Function 33%
• Audio Signal 33%
• Background Modeling 33%
• Speech Signal 33%
• Recognition Performance 33%
• Nearest Neighbor Classifier 33%
• Time Derivative 33%
• Driving Behavior 33%
• Biometric Data 33%
• Biometrics 33%
• Brake Pedal 33%
• Mel Frequency Cepstral Coefficients 33%
• Nagoya University 33%
• Scenario Verification 33%
• Closed-set Identification 33%
• Model of Models 33%
• Mixture Gaussian 33%
• In-car 33%
• Feature Dimension 33%
• Open-set Identification 33%
• Speaker Recognition 33%
• Weighted Sum Rule 33%

Computer Science

• Gaussian Mixture Model 100%
• Vehicular Application 100%
• Face Recognition 33%
• Recognition Performance 33%
• Positive Effect 33%
• Driving Behavior 33%
• Biometric Data 33%
• Mel Frequency Cepstral Coefficient 33%
• Nearest Neighbors Classifier 33%
• Feature Dimension 33%
• Background Model 33%
• Speaker Recognition 33%
• Component Analysis 33%
• Principal Components 33%
• Sigmoid Activation Function 33%