Research Article
Face Emotion Recognition Based on Images Using the Haar-Cascade Front End Approach
@INPROCEEDINGS{10.1007/978-3-031-48888-7_28, author={G. Gowri Pushpa and Jayasri Kotti and Ch. Bindumadhuri}, title={Face Emotion Recognition Based on Images Using the Haar-Cascade Front End Approach}, proceedings={Cognitive Computing and Cyber Physical Systems. 4th EAI International Conference, IC4S 2023, Bhimavaram, Andhra Pradesh, India, August 4-6, 2023, Proceedings, Part I}, proceedings_a={IC4S}, year={2024}, month={1}, keywords={Haar-cascade frontal face algorithm FER-2013 Facial expression recognition Face detection Convolution neural network (CNN)}, doi={10.1007/978-3-031-48888-7_28} }- G. Gowri Pushpa
Jayasri Kotti
Ch. Bindumadhuri
Year: 2024
Face Emotion Recognition Based on Images Using the Haar-Cascade Front End Approach
IC4S
Springer
DOI: 10.1007/978-3-031-48888-7_28
Abstract
Facial expression recognition (FER) has emerged as a major research topic, with human-computer interactions. Nonverbal messages which are face expressions are crucial in our day-to-day life, which is an example of non-verbal communication. As a human, detecting facial expressions and understanding human emotions is a simple process, but doing it with the assistance of a machine is more challenging. With the remarkable success of deep learning, the different types of architectures of this technique are exploited to achieve a better performance with an accuracy of 87%. In this research, our proposed model shows how to identify and recognize facial emotions from images using neural networks with help of preprocessing techniques and the whole process comprises various stages of classifying the detected features, involving human face detection and classifying them then into any of the seven basic emotion classes using the convolutional neural networks (CNN). Haar-cascade frontal face algorithm was utilized in order to detect human faces from the images. Our model was trained and tested on the FER-2013 dataset.
