Real Time Emotion Detection Using Deep Learning

Jaymon, Noel; Nagdeote, Sushma; Yadav, Aayush; Rodrigues, Ryan

doi:10.1109/icaect49130.2021.9392584

Cited by 6 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Evaluation of the facial emotion recognition model was based on criteria such as validation accuracy, computational complexity, detection rate, learning rate, validation loss, and computational time per step. Noel Jaymon, Sushma Nagdeote, Aayush Yadav and Ryan Rodrigues, et al [2], proposed a real time facial emotion detection system by analyzing valuable information which was obtained by mouth, eyes, eyebrows etc. The system was capable enough to detect 7 universally accepted and recognized emotions by implementing fасe deteсtiоn, fасiаl feature extrасtiоn аnd emotion reсоgnitiоn.…”

Section: Related Workmentioning

confidence: 99%

“…The humans tend to ignore the emotions of the people around them sometimes they are even had to notice, but due to advancement in technology building a smart solution to overcome this problem has now become a need which is feasible to achieve using the concept of artificial intelligence and machine learning by using deep learning based CNN. [2] The universally acknowledged and recognized emotions include anger, disgust, fear, happiness, sadness, neutrality, and surprise. An automatic real-time emotion recognition system typically involves three primary stages: face detection, extraction of facial features, and the actual emotion recognition process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Survey on Emotion Detection Using Machine Learning Techniques.

2023

IRJMETS

View full text Add to dashboard Cite

In today's digital age, computer vision technologies play a crucial role in the wide range of applications, from surveillance and human-computer interaction to entertainment and healthcare. This project introduces a robust real-time system for simultaneous face detection and emotion recognition, harnessing the capabilities of machine learning and the OpenCV library. Addressing the intricate research challenge of real-time multiple face recognition and human emotion detection in social communication, the project employs deep learning (DL) for emotion detection, exhibiting superior performance compared to traditional image processing methods. The proposed artificial intelligence (AI) system is designed to proficiently detect emotions by analyzing facial expressions, consisting of three primary phases: face detection, feature extraction, and emotion classification. Emphasizing convolutional neural networks (CNN) in its deep learning architecture, the system not only identifies faces but also utilizes a deep neural network for accurate emotion recognition. Through the analysis of facial expressions, the system classifies emotions into distinct categories such as happiness, sadness, anger, surprise, and more. This comprehensive emotional analysis enhances the system's comprehension of human interactions, paving the way for applications in diverse fields such as customer sentiment analysis, humancomputer interaction, and healthcare diagnostics.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%