Detection Of Facial Paralysis In Human Beings Using Deep Auto Facialnet Clustering

Authors

  • Rajalakshmi S Asst Prof, Department of Computer Science and Engineering, Velammal Engineering College
  • Jayanthi A Asst Prof, Department of Computer Science and Engineering, Velammal Engineering College
  • Sridevi S Asst Prof, Department of Computer Science and Engineering, Velammal Engineering College
  • Padma S Asst Prof, Department of Electronics and Instrumentation Engineering, Velammal Engineering College

Keywords:

Facial Paralysis, Deep Learning, Auto FacialNet, Clustering, Diagnostic Tool

Abstract

Facial paralysis, characterized by the loss of voluntary muscle movement on one side of the face, poses significant challenges for timely diagnosis and treatment. Traditional methods for detecting facial paralysis often rely on subjective assessments, leading to a need for more objective and accurate diagnostic tools. The study introduces Deep Auto FacialNet Clustering, a novel approach that harnesses the power of deep learning for precise facial paralysis detection.Existing methods for facial paralysis detection lack the sophistication required to accurately analyze complex facial expressions, leading to misdiagnoses and delayed treatment. There is a critical research gap in the development of automated systems that can reliably identify subtle signs of facial paralysis through advanced facial feature analysis.The research addresses the gap in current methodologies by proposing a Deep Auto FacialNet Clustering model, which leverages deep learning techniques to automatically analyze facial expressions and identify potential indicators of facial paralysis. The proposed methodology involves the creation of a specialized deep neural network, Auto FacialNet, trained on a diverse dataset of facial expressions. The network is designed to autonomously cluster facial features associated with normal and paralyzed expressions. By utilizing unsupervised learning, the model becomes adept at discerning subtle differences that may escape human observation.Preliminary results indicate a high level of accuracy in facial paralysis detection, surpassing traditional methods. The Deep Auto FacialNet Clustering model demonstrates promising potential for early and reliable identification of facial paralysis, paving the way for timely medical intervention.

Downloads

Published

2023-10-25

How to Cite

Rajalakshmi S, Jayanthi A, Sridevi S, & Padma S. (2023). Detection Of Facial Paralysis In Human Beings Using Deep Auto Facialnet Clustering. Chinese Journal of Computational Mechanics, (5), 486–492. Retrieved from http://jslxxb.cn/index.php/jslxxb/article/view/4393

Issue

Section

Articles