Facial Expression Recognition: Utilizing Digital Image Processing, Deep Learning, and High-Performance Computing
Event Type
Student Paper
Machine Learning/Artificial Intelligence
Image Analysis
TimeTuesday, July 304pm - 4:30pm
LocationGold Coast
DescriptionThe purpose of this project was to analyze which image pre-processing technique was most beneficial in improving the performance of Facial Expression Recognition through Deep Learning and High-Performance Computing.
Contrary to our expectations, the results obtained in this work showed that deep learning does not significantly benefit from various commonly used image pre-processing techniques such as resizing, smooth, or edge detection. As generally expected, the results showed that an increase in accuracy was obtained by simply increasing the size of the training dataset. This study proceeds to show that the increase in training data size was easily handled by the High-Performance Computing (HPC) cluster provided by the Pittsburg Supercomputing Centered through XSEDE.