Authors : Bharati Gondhalekar; Suraj Mahato; Sahil Salian; Hrishikesh Adhau

Volume/Issue : Volume 9 - 2024, Issue 4 - April

Google Scholar : https://tinyurl.com/w8rsum5c

DOI : https://doi.org/10.38124/ijisrt/24apr1755

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : EmoDetect is an innovative online application de- signed to provide real-time emotion analysis and mental health monitoring through facial expression recognition. In today’s digi- tal age, where mental health concerns are increasingly prevalent, EmoDetect offers a user-friendly platform for individuals to gain insights into their emotional well-being. Leveraging state- of-the-art deep learning techniques and the Deep Face library, EmoDetect accurately detects and analyzes facial expressions to determine users’ emotional states. The application allows users to upload video files or utilize their webcam for real- time emotion analysis. EmoDetect calculates depression and anxiety scores based on detected emotions, providing users with personalized insights into their mental health status. Through intuitive visualizations, users can explore the distribution of emotions over time and gain a deeper understanding of their emotional patterns. EmoDetect not only empowers users to track their emotional well-being but also provides actionable recom- mendations, such as personalized music playlists, to uplift their mood. Furthermore, the application facilitates data storage and report generation, enabling users to track their emotional journey over time. In this paper, we present the architecture, methodology, and key features of EmoDetect, along with experimental results demonstrating its effectiveness in emotion analysis and mental health monitoring. We discuss the implications of our findings for mental health care and highlight potential avenues for future research and application development in this domain.

Keywords : Mental Health, Anxiety, Depression, Facial Ex- Pression Analysis, Machine Learning, Deep Face Library.

References :

1. Zhang H, Feng L, Li N, Jin Z, Cao L. Video-Based Stress Detection through Deep Learning. Sensors. 2020; 20(19):5552.
2. Gavrilescu, M.; Vizireanu, N. Predicting Depression, Anxiety, and Stress Levels from Videos Using the Facial Action Coding System. Sensors 2019, 19, 3693.
3. Zhang, Huijun, Ling Feng, Ningyun Li, Zhanyu Jin, and Lei Cao. 2020. ”Video-Based Stress Detection through Deep Learning” Sensors 20, no. 19: 5552.
4. Manju Lata Joshi and N. Kanoongo, Depression detection using emo- tional artificial intelligence and machine learning: A closer review, Materials Today:Proceedings,
5. Gavrilescu M, Vizireanu N. Predicting Depression, Anxiety, and Stress Levels from Videos Using the Facial Action Coding System. Sensors. 2019; 19(17):3693
6. Kroenke K., Spitzer R.L., Williams J.B. The PHQ-9: Validaity of a brief Depression Secerity Measure. J. Gen. Intern. Med. 2001;16:606–613.
7. Gavrilescu, Mihai, and Nicolae Vizireanu. 2019. ”Predicting Depression, Anxiety, and Stress Levels from Videos Using the Facial Action Coding System” Sensors 19, no. 17: 3693.
8. Lee J.H. Method of detecting eye and lip areas in facial images using high-speed R-CNN. J. Korea Converg. Soc. 2018;9:1–8. doi: 10.15207/J KCS .2018.9.8.001
9. Woon S., Lim J., Han C. Clinical evaluation tool for effective depression treatment. J. Korean Psychiatry. 2012;23:136–146.
10. Graham S., Depp C., Lee E.E., Nebeker C., Tu X., Kim H.-C., Jeste D.V. Artificial intelligence for mental health and mental illnesses: An overview. Curr Psychiatry Rep. 2019;21:116
11. Stubberud, J., Huster, R., Hoorelbeke, K., Hammar, A. & Hagen, B. Improved emotion regulation in depression following cognitive remedi- ation: A randomized controlled trial. Behav. Res. Ther. 147, 103991.
12. Cusi, A. M., Nazarov, A., MacQueen, G. M. & McKinnon, M. C. Theoryof mind deficits in patients with mild symptoms of major depressive disorder. Psychiatry Res. 210, 672–674.
13. Smith, J., Johnson, R., & Brown, A. (2020). Facial Expression Recog- nition Using Convolutional Neural Networks for Depression Detec- tion. IEEE Transactions on Affective Computing, 11(3), 385-395. doi:10.1109/TAF FC.2018.2877200
14. Wang, Y., Kosinski, M., & Stillwell, D. (2018). Deep neural networks are more accurate than humans at detecting sexual orientation from facial images. Journal of Personality and Social Psychology, 114(2), 246-257. doi:10.1037/pspa0 000098
15. Krafka, K., Khosla, A., Kellnhofer, P., Kannan, H., Bhandarkar, S., Matusik, W., & Torralba, A. (2016). Eye Tracking for Everyone. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2176-2184. doi:10.1109/CVP R.2016.246
16. Hu, X., & Yang, H. (2019). A Multi-task Learning Frame- work for Depression Detection from Facial Videos. Proceedings of the AAAI Conference on Artificial Intelligence, 33, 8482-8489. doi:10.1609/aaai.v33i01.33018482
17. Nguyen, T., & Mai, V. (2020). Depression detection through facial expression recognition using deep learning. Journal of Computer Science and Cybernetics, 36(3), 303-315. doi:10.15625/18 13-9663/36/3/15297.
18. Higuchi, Y., & Kimura, T. (2017). Emotion Recognition from Facial Expression and Physiology in Patients with Major Depressive Disorder. Frontiers in Psychology, 8, 1754. doi:10.3389/fpsyg.2017.01754
19. Lin, H., Wang, L., Luo, J., & Zhang, Y. (2018). Multi-level hybrid network model for depression detection based on facial expression. Mul- timedia Tools and Applications, 77(6), 7269-7285. doi:10.1007/s11042- 017-5414-0
20. Meng, L., Wang, D., Yang, J., & Zhang, Y. (2019). Depression detection by fusing high- and low-level features from multimodal data. Pattern Recognition Letters, 128, 353-360. doi:10.1016/j .patrec.2019.06.015
21. Gao, S., Calhoun, V., & Sui, J. (2018). Machine learning in major de- pression: From classification to treatment outcome prediction. CNS Neu- roscience & Therapeutics, 24(11), 1037-1052. doi:10.1111/cns.12951
22. [22] Kaur, M., Kumar, V., & Kaur, P. (2018). Automatic Depression Detection using Facial Expressions. Proceedings of the IEEE International Confer- ence on Power, Control, Signals and Instrumentation Engineering, 1-5. doi:10.1109/P CSI.2018.8629858