Explainable Facial Emotion Recognition Through Hybrid Deep Learning And Attention-Based Feature ExtractionID: 4036 Abstract :Facial Expression Recognition (FER) Has Emerged As An Important Application Area Of Human-Computer Interaction (HCI) Which Aims To Automatically Interpret The State Of A Persons Face. In This Paper, A Deep Learning-based Framework Which Uses Convolutional Neural Networks (CNNs) And Bidirectional Long Short-Term Memory (Bi-LSTM) Networks Is Proposed To Improve The Classification Of Facial Expression. In The First Step, Cascaded CNN Are Used To Determine Facial Regions, After Which The Images Are Normalized And Resized To Have The Same Dimension. CNNs Are Used To Extract Spatial Information From Facial Images, While BLSIMs Are Used To Learn Temporal Information And The Dynamic Changes In Facial Expression. Extending The Proposed Framework, Data Sets With Three Basic Emotional Classes (happy, Sad, And Neutral) Are Used To Evaluate It. Multiple Epochs Of Training The Model To Optimize Feature Learning And Classification Performance. Experimental Observations Show The Recognition Accuracy Improvement Over The Conventional Approaches. The Proposed Approach Is An Effective Method For Tackling The Task Of Facial Expression Analysis By Integrating Spatial Feature Extraction With Temporal Sequence Modelling. Applications In Healthcare, Education, Security And Real-time Affective Computing Systems. |
Published:13-11-2026 Issue:Vol. 26 No. 11 (2026) Page Nos:105-111 Section:Articles License:This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. How to Cite |