Efficient Net-XGBoost: An Implementation for Facial Emotion Recognition Using Transfer Learning

Researchers are interested in Facial Emotion Recognition (FER) because it could be useful in many ways and has promising applications. The main task of FER is to identify and recognize the original facial expressions of users from digital inputs. Feature extraction and emotion recognition make up the majority of the traditional FER. Deep Neural Networks, specifically Convolutional Neural Network (CNN), are popular and highly used in FER due to their inherent image feature extraction process. This work presents a novel method dubbed as EfficientNet-XGBoost that is based on Transfer Learning (TL) technique. EfficientNet-XGBoost is basically a cascading of the EfficientNet and the XGBoost techniques along with certain enhancements by experimentation that reflects the novelty of the work. To ensure faster learning of the network and to overcome the vanishing gradient problem, our model incorporates fully connected layers of global average pooling, dropout and dense. EfficientNet is fine-tuned by replacing the upper dense layer(s) and cascading the XGBoost classifier making it suitable for FER. Feature map visualization is carried out that reveals the reduction in the size of feature vectors. The proposed method is well-validated on benchmark datasets such as CK+, KDEF, JAFFE, and FER2013. To overcome the issue of data imbalance, in some of the datasets namely CK+ and FER2013, we augmented data artificially through geometric transformation techniques. The proposed method is implemented individually on these datasets and corresponding results are recorded for performance analysis. The performance is computed with the help of several metrics like precision, recall and F1 measure. Comparative analysis with competent schemes are carried out on the same sample data sets separately. Irrespective of the nature of the datasets, the proposed scheme outperforms the rest with overall rates of accuracy being 100%, 98% and 98% for the first three datasets respectively. However, for the FER2013 datasets, efficiency is less promisingly observed in support of the proposed work.