Research Article
Emotion Detection using Enhanced CNN Model Through Virtual Assistance
@INPROCEEDINGS{10.4108/eai.28-4-2025.2357817, author={B. Yasaswini and Kamaluru Mahammad and T. Supriya and P Venkatakrishna and V Sai Shanth Kumar}, title={Emotion Detection using Enhanced CNN Model Through Virtual Assistance}, proceedings={Proceedings of the 4th International Conference on Information Technology, Civil Innovation, Science, and Management, ICITSM 2025, 28-29 April 2025, Tiruchengode, Tamil Nadu, India, Part I}, publisher={EAI}, proceedings_a={ICITSM PART I}, year={2025}, month={10}, keywords={emotion detection convolutional neural network (cnn) virtual assistance facial expression recognition google maps}, doi={10.4108/eai.28-4-2025.2357817} }- B. Yasaswini
Kamaluru Mahammad
T. Supriya
P Venkatakrishna
V Sai Shanth Kumar
Year: 2025
Emotion Detection using Enhanced CNN Model Through Virtual Assistance
ICITSM PART I
EAI
DOI: 10.4108/eai.28-4-2025.2357817
Abstract
A key aspect of human-computer interaction is emotion detection, where systems can detect and respond to the emotional state of users. A better CNN model for emotion detection from webcam-captured facial expressions is proposed in this paper. Our approach employs a proprietary Convolutional Neural Network (CNN) trained on the FER2013 dataset, unlike traditional models based on pretrained architectures. The model incorporates a virtual assistant that engages with people according to the emotions it detects and divides emotions into seven categories. Additionally, the system uses the Google Maps to recommend the closest psychiatrist in situations involving negative emotions like fear, sad or anger. Real-time emotional support and improved emotion recognition accuracy are the goals of the suggested system.
