Home / Current Issue / Paper 1705299
Facial Emotion Recognition of Human Species by Using Deep Learning Techniques
Subject area: Science,Engineering and Technology · Area of research: Machine Learning, Deep Learning
Abstract
In this research paper, we delve into the realm of Human Facial Expression Recognition, a field critical for the advancement of computer vision and artificial intelligence. Our focus is on creating a robust Convolutional Neural Network (CNN) model capable of accurately identifying diverse human facial expressions, including anger, happiness, neutrality, sadness, and surprise. We leverage the power of TensorFlow and Keras to develop and train our CNN model. Our dataset, carefully curated to encompass a wide range of expressions, undergoes preprocessing using image data generators. This process includes augmentation and normalization, enhancing the model's adaptability to various facial expressions. The architecture of our CNN involves multiple convolutional and pooling layers, concluding with densely connected layers designed for effective classification. Training employs the RMSprop optimizer and categorical crossentropy loss function. The model undergoes extensive training across multiple epochs, with evaluation conducted on both the training and validation datasets. Our project highlights the achieved accuracy on an independent test set, demonstrating the model's proficiency. Furthermore, we apply the trained model to predict facial expressions in new images, offering practical insights into its real-world application. This project contributes to the evolving field of computer vision by providing a sophisticated deep-learning solution for the automatic recognition of human facial expressions. The demonstrated accuracy on the test set underscores the model's potential relevance in areas such as emotion analysis and human-computer interaction.
Keywords
Facial Expression Recognition, Convolution Neural Network, TensorFlow and Keras, Image Data Generators, Emotion Analysis.
References
[1] Fathallah A, Abdi L, Douik A. Facial expression recognition via deep learning. In2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA) 2017 Oct 30 (pp. 745-750). IEEE.
[2] Fan Y, Lam JC, Li VO. Multi-region ensemble convolutional neural network for facial expression recognition. InArtificial Neural Networks and Machine Learning–ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part I 27 2018 (pp. 84-94). Springer International Publishing
[3] Shin M, Kim M, Kwon DS. Baseline CNN structure analysis for facial expression recognition. In2016 25th IEEE international symposium on robot and human interactive communication (RO-MAN) 2016 Aug 26 (pp. 724-729). IEEE.
[4] Pranav E, Kamal S, Chandran CS, Supriya MH. Facial emotion recognition using deep convolutional neural network. In2020 6th International conference on advanced computing and communication Systems (ICACCS) 2020 Mar 6 (pp. 317-320). IEEE.
[5] Bodapati JD, Srilakshmi U, Veeranjaneyulu N. FERNet: a deep CNN architecture for facial expression recognition in the wild. Journal of the institution of engineers (India): series B. 2022 Apr;103(2):439-48.
How to cite this paper
@article{1705299,
author = {Amit Kumar Pandey, Dr. Santosh Singh, Ankush Sushil Singh, Ashwani Kumar Mishra},
title = {Facial Emotion Recognition of Human Species by Using Deep Learning Techniques},
journal = {Iconic Research And Engineering Journals},
year = {2023},
volume = {7},
number = {6},
pages = {147-152},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1705299.pdf},
abstract = {In this research paper, we delve into the realm of Human Facial Expression Recognition, a field critical for the advancement of computer vision and artificial intelligence. Our focus is on creating a robust Convolutional Neural Network (CNN) model capable of accurately identifying diverse human facial expressions, including anger, happiness, neutrality, sadness, and surprise. We leverage the power of TensorFlow and Keras to develop and train our CNN model. Our dataset, carefully curated to encompass a wide range of expressions, undergoes preprocessing using image data generators. This process includes augmentation and normalization, enhancing the model's adaptability to various facial expressions. The architecture of our CNN involves multiple convolutional and pooling layers, concluding with densely connected layers designed for effective classification. Training employs the RMSprop optimizer and categorical crossentropy loss function. The model undergoes extensive training across multiple epochs, with evaluation conducted on both the training and validation datasets. Our project highlights the achieved accuracy on an independent test set, demonstrating the model's proficiency. Furthermore, we apply the trained model to predict facial expressions in new images, offering practical insights into its real-world application. This project contributes to the evolving field of computer vision by providing a sophisticated deep-learning solution for the automatic recognition of human facial expressions. The demonstrated accuracy on the test set underscores the model's potential relevance in areas such as emotion analysis and human-computer interaction.},
keywords = {Facial Expression Recognition, Convolution Neural Network, TensorFlow and Keras, Image Data Generators, Emotion Analysis.},
month = {December},
}