Enhancement of Patient Facial Recognition through Deep Learning Algorithm: ConvNet

Area of Science:

• Computer Science
• Artificial Intelligence
• Biomedical Engineering

Background:

• Facial expression recognition is crucial for patient monitoring.
• Deep learning, particularly convolutional neural networks (ConvNets), shows promise in this field.
• Existing methods can be computationally expensive.

Purpose of the Study:

• To present a computationally efficient deep learning technique for facial expression recognition.
• To improve the accuracy of facial expression recognition for healthcare applications.

Main Methods:

• Utilized a convolutional neural network (ConvNet) deep learning algorithm.
• Trained the model on the FER2013 dataset, which includes seven universal facial expressions.

Main Results:

• The proposed technique enhances facial expression recognition accuracy.
• The model achieves high accuracy without computationally expensive deep layers.
• The method offers a solution to the high computational cost issue.

Conclusions:

• Deep learning-enabled facial expression recognition improves accuracy and interpretation of facial features.
• This technique promotes efficiency and prediction in the health sector.
• The model provides accuracy comparable to state-of-the-art methods with reduced computational load.