Performance Metric Estimation of Fast RCNN with VGG-16 Architecture for Emotional Recognition

Abstract

Faster R-CNN is a state-of-the-art universal object detection approach based on a convolutional neural network that offers object limits and objectness scores at each location in an image at the same time. To hypothesis object locations, state-of-the-art object detection networks rely on region proposal techniques. The accuracy of ML/DL models has been shown to be limited in the past due to a range of issues, including wavelength selection, spatial resolution, and hyper parameter selection and tuning. The goal of this study is to create a new automated emotional detection system based on the CK+ database. Fast R-CNN has lowered the detection network’s operating time, revealing region proposal computation as a bottleneck. We develop a Region Proposal Network (RPN) in this paper that shares full-image convolutional features with the detection network, allowing for almost cost-free region suggestions. The suggested VGG-16 Fast RCNN model obtained user accuracy close to 100 percent in the emotion class, followed by VGG-16 (99.79 percent), Alexnet (98.58 percent), and Googlenet (98.58 percent) (98.32 percent). After extensive hyper parameter tuning for emotional recognition, the generated Fast RCNN VGG-16 model showed an overall accuracy of 99.79 percent, far higher than previously published results.