Artificial Intelligence based Facial Emotions Analysis for Depression Detection

PROJECT ABSTRACT:

In recent years, the integration of artificial intelligence (AI) and machine learning techniques has shown remarkable potential in various domains, including mental health assessment. This project presents a novel approach titled “Artificial Intelligence based Facial Emotions Analysis for Depression Detection,” aimed at leveraging AI and deep learning to detect and classify depression levels based on facial emotion analysis. The project utilizes the Matlab programming environment and employs the AlexNet Convolutional Neural Network (CNN) model for accurate emotion recognition. The primary objective of this research is to create a robust system capable of recognizing five primary emotions—Anger, Disgust, Happy, Neutral, and Sadness—by analyzing facial expressions in images. These emotions serve as vital indicators for assessing an individual’s mental state, particularly when it comes to depression detection. The developed system not only identifies emotions but also classifies depression into four distinct levels: No Depression, Mild Depression, Moderate Depression, and High Depression. This multi-class classification enables a more nuanced understanding of the individual’s mental health status. To achieve high accuracy in emotion recognition and depression classification, the AlexNet CNN model is employed. This model is renowned for its deep architecture and remarkable feature extraction capabilities, making it an ideal choice for complex image analysis tasks. Through an extensive training process using a diverse dataset containing facial expressions of various intensities, the system attains an impressive accuracy rate of 99%. The project’s contributions are twofold. Firstly, it provides a reliable method for automatically analyzing facial emotions, eliminating the subjectivity inherent in traditional assessment methods. Secondly, the integration of AI and deep learning with mental health assessment opens up new possibilities for early depression detection and intervention. By accurately classifying depression levels based on facial emotions, this project offers a potential tool for mental health professionals to identify individuals at risk and provide timely support. Our Proposed “Artificial Intelligence based Facial Emotions Analysis for Depression Detection” project introduces an innovative approach to mental health assessment. By harnessing the power of the Matlab environment and utilizing the AlexNet CNN model, the project achieves a remarkable 99% accuracy in recognizing emotions and classifying depression levels. This advancement holds promise for enhancing the field of mental health diagnosis and treatment through non-intrusive, AI-driven techniques.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

AlexNet CNN Model.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED.
Input Devices : Keyboard, Mouse.
Ram : 8 GB.

SOFTWARE REQUIREMENTS:

Operating system : Windows 10 Pro.
Coding Language : MATLAB
Tool : MATLABR2021A

REFERENCE:

Zixuan Shangguan, Zhenyu Liu , Member, IEEE, Gang Li, Qiongqiong Chen, Zhijie Ding, and Bin Hu , Senior Member, IEEE, “Dual-Stream Multiple Instance Learning for Depression Detection With Facial Expression Videos”, IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, VOL. 31, 2023.

Matlab IEEE Projects

Artificial Intelligence based Facial Emotions Analysis for Depression Detection