17809438. SIMULATED CAPACITANCE MEASUREMENTS FOR FACIAL EXPRESSION RECOGNITION TRAINING simplified abstract (Microsoft Technology Licensing, LLC)

SIMULATED CAPACITANCE MEASUREMENTS FOR FACIAL EXPRESSION RECOGNITION TRAINING

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Jouya Jadidian of Los Gatos CA (US)

Calin Cristian of Iasi (RO)

Petre-Alexandru Arion of Timisoara (RO)

SIMULATED CAPACITANCE MEASUREMENTS FOR FACIAL EXPRESSION RECOGNITION TRAINING - A simplified explanation of the abstract

This abstract first appeared for US patent application 17809438 titled 'SIMULATED CAPACITANCE MEASUREMENTS FOR FACIAL EXPRESSION RECOGNITION TRAINING

Simplified Explanation

The abstract describes a method for training a neural network to recognize facial expressions using digital human face models and simulated capacitance measurements from an array of radio frequency antennas.

• The method involves recognizing multiple digital human face models.
• Simulated facial expressions are then generated for each of these face models.
• Simulated capacitance measurements are obtained for an array of radio frequency antennas for each simulated facial expression.
• These simulated capacitance measurements are used as input training data for a neural network.
• The neural network is designed to output facial expression parameters based on the input capacitance measurements.

Potential Applications

This technology has potential applications in various fields, including:

• Facial expression recognition systems for human-computer interaction.
• Emotion detection in virtual reality and augmented reality applications.
• Facial analysis in psychology and neuroscience research.
• Biometric identification systems for security and access control.

Problems Solved

The method addresses the following problems:

• Limited availability of labeled facial expression training data.
• Difficulty in capturing and measuring facial expressions accurately.
• Challenges in training neural networks to recognize subtle and complex facial expressions.

Benefits

The use of simulated facial expressions and capacitance measurements offers several benefits:

• Enables the generation of a large dataset for training facial expression recognition models.
• Provides a controlled and repeatable environment for capturing and analyzing facial expressions.
• Allows for the training of neural networks to recognize a wide range of facial expressions.
• Can improve the accuracy and robustness of facial expression recognition systems.

Original Abstract Submitted

A method for training a neural network for facial expression recognition includes recognizing a plurality of digital human face models. For each of the plurality of digital human face models, a plurality of simulated facial expressions are simulated. Simulated capacitance measurements for an array of simulated radio frequency (RF) antennas are found for each of the plurality of simulated facial expressions. The simulated capacitance measurements for each simulated facial expression are provided as input training data to a neural network configured to output facial expression parameters based on input capacitance measurements.