A Hybrid Predictive Architecture Formulation Using Deep Learning And Histogram Of Gradients For Compound Emotion Recognition
Anjana Guru Prasad, Shruti Kulkarni, Vaishnavi Suresh Bhangennavar, Vineet Belagod, Vijayalakshmi Gopasandra Venkateshappa Mahesh, Alex Noel Joseph Raj
DOI: 10.15598/aeee.v22i1.5467
Abstract
Facial emotion recognition has gained attention of researchers all over the world in the past few decades. Initially, emotions were classified in the seven basic categories which included happy, sad, angry, etc. However, human emotions are rarely this simple. They are usually combinations of dominant and complimentary emotions and are known as Compound Emotions. Two different ways have been commonly adapted for the recognition of these emotions from facial images: firstly, by using handcrafted features, or by using deep learning networks. This research analyzes the performance of a much simpler designed deep learning model named as Sequential-Convolution Neural Network (S-CNN) and four predefined deep learning networks for the recognition of compound emotions from facial images. The objective of this paper is to replace sophisticated state-of-the-art prediction models with a straightforward but effective approach. Therefore, this research suggests a hybrid network that maintains the S-CNN model's design simplicity while boosting performance. The features extracted by the S-CNN model and the handcrafted features are combined in the hybrid S-CNN model. This process keeps the hybrid model's architecture simple while improving its metrics values and increasing its accuracy to 99.62% when compared to other state-of-the-art models. The source code for this research can be found in our GitHub repository: href{https://github.com/CompoundEmotion-Recognition/SCNN_Hybrid_model