International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 07 | July 2024
p-ISSN: 2395-0072
www.irjet.net
Facial Emotion Recognition in Real Time Using Deep Learning Dr.Laxmi Math1, Neha G2 1Dr.LaxmiMath & Associate Professor, Department of Artificial Intelligence & Data Science, Sharnbasva University
Kalaburagi, Karnataka, India
2 Neha G & Department of CSE Sharnbasva University Kalaburagi, Karnataka, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract -
employed for their powerful feature extraction capabilities, while RNNs are utilized to handle temporal dependencies and dynamics in the facial expressions2.
Facial emotion recognition (FER) is a critical area of research with applications spanning from human-computer interaction to security and healthcare. This paper presents a novel realtime facial emotion recognition system using deep learning techniques1. Leveraging the power of convolutional neural networks (CNNs) and recurrent neural networks (RNNs), our approach accurately identifies and classifies human emotions from live video feeds1. The proposed system integrates preprocessing steps including face detection and alignment, followed by emotion classification using a deep neural network model trained on a comprehensive dataset. The realtime performance is achieved through optimized model architecture and efficient processing pipelines 1. Extensive experiments demonstrate the system’s high accuracy and robustness in varied lighting conditions and with diverse facial expressions. Our results indicate that the proposed method outperforms existing state-of-the-art FER systems in both speed and accuracy, making it suitable for real-world applications1. This research contributes to the advancement of real-time emotion recognition technologies, providing a foundation for further innovations in the field1.
The primary objectives of this project are: 1. Designing an Optimized Model Architecture: We aim to create a hybrid CNN-RNN model that balances accuracy and computational efficiency, enabling real-time processing. 2. Implementing Efficient Pre-processing Pipelines: This includes developing methods for rapid and accurate face detection and alignment to ensure consistent input quality. 3. Evaluating System Performance: The system will be rigorously tested under various conditions, including different lighting environments and diverse facial expressions, to ensure robustness and reliability2.
Key Words: Facial Emotion Recognition, Real-time, Deep Learning, Convolutional Neural Networks, Recurrent Neural Networks, Human-Computer Interaction etc2.
Our approach involves a comprehensive process starting with data collection and pre-processing, followed by model training and optimization, and culminating in real-time system deployment and evaluation. The system is designed to handle the dynamic nature of live video feeds, providing immediate feedback and classification of emotions2.
1. INTRODUCTION
The expected outcomes of this project include:
Facial emotion recognition (FER) has emerged as a pivotal technology in various domains, including human-computer interaction, security, healthcare, and entertainment. The ability to accurately and efficiently interpret human emotions through facial expressions is crucial for enhancing user experience, improving communication, and facilitating advanced monitoring systems.1 Despite the progress made in this field, real-time FER remains a challenging task due to the inherent complexity and variability of human emotions, as well as the computational demands of processing live video feeds2.
- High Accuracy in Emotion Recognition: Achieving a high level of accuracy comparable to or surpassing existing stateof-the-art methods. -Real-Time Performance: Ensuring the system can process and classify emotions in real-time without significant delays. -Robustness and Generalizability: Demonstrating the system's ability to perform well across different scenarios and on varied datasets2. This research not only addresses the current limitations in real-time FER but also lays the groundwork for future advancements in the field. The successful implementation of this system has the potential to significantly impact areas such as interactive systems, surveillance, mental health monitoring, and more. By advancing the capabilities of realtime emotion recognition, we aim to contribute to the
This project aims to develop a robust and efficient real-time facial emotion recognition system utilizing state-of-the-art deep learning techniques. Our system leverages the strengths of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to process and analyse facial expressions from live video streams2. CNNs are
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 805