What does this research mean for the field?

A multi-CNN feature fusion approach combining multiple pre-trained base models outperforms individual base models in facial expression recognition, achieving a classification accuracy of 69.03%. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This work aims to enhance the recognition of facial expressions through a novel multi-convolutional neural network approach.

June 6, 2026Journal of EngineeringOpen Access

A Multi-CNN Fusion Approach for Improved Facial Expression Recognition

View Full Paper

Ask AI

Bookmark

Authors

AAAhmed AhmedArtificial Intelligence in Medicine (Canada)YAYahya AhmedPresidency University SRSara RaedPLA Information Engineering University

Discussion

Member takes

Overview

Randomized trial demonstrates improved facial expression recognition accuracy using a multi-CNN approach, suggesting advancements in human-computer interaction.

Key Points

This work aims to enhance the recognition of facial expressions through a novel multi-convolutional neural network approach.
Developed three base CNN models for facial expression recognition.
Fused features from two pre-trained models to construct a fusion network.
Utilized max-score and mean-score fusion techniques for performance evaluation against a third pre-trained model.
Achieved 69.03% classification accuracy on the facial expression dataset.
Outperformed all base models across all evaluated metrics.

Cite This Study

Ahmed et al. (2026) studied this question.

synapsesocial.com/papers/6a23b89f71a5da9775e74b0a https://doi.org/10.31026/j.eng.2026.06.10

View Full Paper

Ask AI

Bookmark

June 6, 2026Journal of EngineeringOpen Access

A Multi-CNN Fusion Approach for Improved Facial Expression Recognition

View Full Paper

Ask AI

Bookmark

Authors

AAAhmed AhmedArtificial Intelligence in Medicine (Canada)YAYahya AhmedPresidency University SRSara RaedPLA Information Engineering University

Discussion

Member takes

Overview

Randomized trial demonstrates improved facial expression recognition accuracy using a multi-CNN approach, suggesting advancements in human-computer interaction.

Key Points

This work aims to enhance the recognition of facial expressions through a novel multi-convolutional neural network approach.
Developed three base CNN models for facial expression recognition.
Fused features from two pre-trained models to construct a fusion network.
Utilized max-score and mean-score fusion techniques for performance evaluation against a third pre-trained model.
Achieved 69.03% classification accuracy on the facial expression dataset.
Outperformed all base models across all evaluated metrics.

Cite This Study

Ahmed et al. (2026) studied this question.

synapsesocial.com/papers/6a23b89f71a5da9775e74b0a https://doi.org/10.31026/j.eng.2026.06.10

View Full Paper

Ask AI

Bookmark