FER-Sys: A Real-Time Facial Emotion Recognition System Using Deepface And CNN Frameworks

Authors

  • Akrisht Singh Department of Computer Science and Engineering, Central University of Rajasthan, Ajmer-305817-India.
  • Ravi Saharan Department of Computer Science and Engineering, Central University of Rajasthan, Ajmer-305817-India.

DOI:

https://doi.org/10.63278/mme.vi.1626

Keywords:

Facial Emotion Recognition, DeepFace, CNN, RealTime Detection, Human-Computer Interaction, Deep Learning.

Abstract

Facial Emotion Recognition (FER) is a crucial aspect of developing emotionally aware human-computer interfaces. Existing models have achieved significant milestones but often lack flexibility or real-time performance. In this paper, we present FER-Sys, a comparative implementation of two approaches: the DeepFace framework and a custom-built Convolutional Neural Network (CNN) using Keras. These models were trained and evaluated on standard datasets, integrated into real-time webcam applications, and benchmarked for performance. The system’s architecture enables facial alignment, emotion classification, and real-time prediction, with practical implications for emotionaware applications.

Downloads

How to Cite

Singh, Akrisht, and Ravi Saharan. 2025. “FER-Sys: A Real-Time Facial Emotion Recognition System Using Deepface And CNN Frameworks”. Metallurgical and Materials Engineering, May, 708-16. https://doi.org/10.63278/mme.vi.1626.

Issue

Vol. 31 No. 5 (2025)

Section

Research

License

Copyright (c) 2025 Akrisht Singh, Ravi Saharan

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  • Authors are permitted and encouraged to post their published articles online (e.g., in institutional repositories or on their website, social networks like ResearchGate or Academia), as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).

 

Creative Commons License
Except where otherwise noted, the content on this site is licensed under a Creative Commons Attribution 4.0 International License.