Trylia: A Web - Based Virtual dressing System Using OpenCV, CVZone, and Machine Learning

Abstract

This research paper introduces Trylia: Your Virtual Dressing Room system that helps the users to try on the clothes virtually before purchasing it and even on real time. This system uses their device camera for try on and the system for that selected cloth on user body and provide the size recommendation for that user if he/she is not sure about their cloth size alongwith the accuracy rate that tells the fitting rate of cloth on the user. This system uses camera vision, OpenCV, MediaPipe and more related python libraries. This feature helps the users for interactive online fashion visualization. It uses OpenCV for image processing and camera, CVZone to detect the human body keymarks. Also it tracks the human movements and for that cloth to the human body accurately. This system is so much useful and easy to use because it eliminates the use of 3D and online AI generated images. And it also provides the features of size recommendation and accuracy rate, which makes it more helpful for the users to use this system. This project is implemented as the full – stack web application which makes it smooth interaction to the user, fast processing and easy to use across all devices. It is user – friendly platform which enhances confidence since it is a combination of visualization, size recommendation and fitting accuracy rate.

Introduction

The text presents Trylia: Your Virtual Dressing Room, a business-to-business (B2B) virtual try-on (VTO) service designed for e-commerce platforms such as Amazon, Flipkart, and Meesho. Rather than interacting directly with end customers, Trylia is integrated into these companies’ platforms, enabling shoppers to virtually try on clothing in real time using their device camera. The primary goal of the system is to reduce the high return rates in online fashion retail by improving fit confidence through real-time try-on and size recommendation features.

The platform includes a web-based interface for partner companies, featuring system demonstrations, a live try-on preview, size accuracy metrics, client reviews, and a detailed contact and enquiry form. Once companies submit enquiries, automated email notifications facilitate follow-up and service integration. The system emphasizes accessibility, real-time performance, and practical deployment over heavy hardware-dependent solutions.

The literature review highlights the evolution of virtual try-on technologies, from basic 2D overlays to AI-driven systems using computer vision, pose estimation, deep learning, GANs, and AR. While advanced models offer high realism, they often require significant computational resources. This motivates Trylia’s lightweight, hybrid approach that balances accuracy, efficiency, and real-time usability, combined with ML-based size recommendation to further reduce return rates.

Trylia’s architecture uses OpenCV and CVZone for body landmark detection and garment overlay alignment, focusing on upper-body apparel. System evaluation shows strong real-time performance (20–30 FPS on mid-range hardware), pose detection accuracy of approximately 88–93%, and garment overlay accuracy of up to 95% for simple clothing. User feedback indicates good responsiveness and usability under standard indoor conditions.

Conclusion

The implementation of Trylia demonstrates that a real-time virtual try-on system can be achieved efficiently using OpenCV and CVZone for computer vision processing and machine learning for size recommendation. The system accurately detects body landmarks, aligns 2D garments, and operates smoothly on everyday hardware, making it practical for real-world online fashion and retail applications. By offering intuitive interaction, responsive performance, and personalized size suggestions, the system enhances user confidence in selecting appropriate apparel online.

References

[1] Marelli, D., Bianco, S., and Ciocca, G., “Designing an AI-based virtual try-on web application,” Sensors, vol. 22, no. 10, p. 3832, 2022. [2] Mohammadi, S.O., and Kalhor, A., “Smart fashion: A review of AI applications in virtual try-on and fashion synthesis,” Journal of Artificial Intelligence, vol. 3, no. 4, p. 284, 2021. [3] De Almeida, M.I.G., Consumers acceptance of artificial intelligence Virtual Try-On systems when shopping apparel online, Master’s thesis, ISCTE–Instituto Universitario de Lisboa, Portugal, 2021. [4] Dhatrak, M., Jadhav, S., Harkal, A., Kankrale, A., and Gupta, S., “AI-powered virtual try-on system: Enhancing fit prediction and user comfort through deep learning,” in 2024 5th International Conference on Communication, Computing & Industry 6.0 (C2I6), pp. 1–6, IEEE, 2024. [5] Fenanda, Z.I., Triwijayanti, A., and Wahyono, S.A., “Analysis of the effect of using virtual try-on based on artificial intelligence and augmented reality on purchase intention,” Journal of Sustainable Technology and Applied Science, vol. 5, no. 1, pp. 6–17, 2024. [6] Mihaila, R., “3D virtual garment simulation and AI virtual try-on technologies,” Journal of Research in Gender Studies, vol. 13, no. 2, pp. 54–68, 2023. [7] Islam, T., Miron, A., Liu, X., and Li, Y., “Deep learning in virtual try-on: A comprehensive survey,” IEEE Access, 2024. [8] Goel, P., Sharma, B., Kumari, A., Gupta, A.K., and Chhajed, P., “A review on virtual try-on,” in 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp. 1–5, IEEE, 2024. [9] Nawaz, M.Z., Guzman, F., and Nawaz, S., “Technology-enabled engagement process of brand virtual-try-on services,” Journal of Product & Brand Management, vol. 34, no. 1, pp. 44–60, 2025. [10] Hashmi, M.F., Ashish, B.K.K., Keskar, A.G., Bokde, N.D., and Geem, Z.W., “FashionFit: Analysis of mapping 3D pose and neural body fit for custom virtual try-on,” IEEE Access, vol. 8, pp. 91603–91615, 2020. [11] Aakash, V.B., Akmal, A., Chandrababu, A., Jose, A., and Vijay, A., “A comprehensive survey on AI-driven fashion technologies.” [12] Ghodhbani, H., Neji, M., Razzak, I., and Alimi, A.M., “You can try without visiting: A comprehensive survey on virtually try-on outfits,” Multimedia Tools and Applications, vol. 81, no. 14, pp. 19967–19998, 2022. [13] Samy, T.M., Asham, B.I., Slim, S.O., and Abohany, A.A., “Revolutionizing online shopping with FITMI: A realistic virtual try-on solution,” Neural Computing and Applications, pp. 1–20, 2025. [14] Bratu, S., “Digital clothing try-on apps, augmented reality beautification filters, and artificial intelligence-powered mood detectors in body image disturbance,” Journal of Research in Gender Studies, vol. 14, no. 1, pp. 86–100, 2024. [15] Dharmani, A., Kurade, A., and Nadar, J., “Enhancing virtual try-on: A study of methodological innovations and dataset effectiveness,” in 2024 2nd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), pp. 1360–1366, IEEE, 2024. [16] Gupta, S., Yadav, G., Wakodkar, M., Narsoo, A., and Gawner, S., “Towards realistic virtual try-on: A ML based approach,” Journal of Technical Education, p. 92. [17] Hsieh, C.W., Chen, C.Y., Chou, C.L., Shuai, H.H., Liu, X., and Cheng, W.H., “FashionOn: Semantic-guided image-based virtual try-on with detailed human and clothing information,” in Proceedings of the 27th ACM International Conference on Multimedia, pp. 275–283, 2019. [18] Vaishnavi, V.V., Narendra, G.O., Boovaraghavan, A., and Anbarasi, L.J., “Bridging the gap between online and in-store shopping: Fashion recommendations and virtual try-on,” in 2024 5th International Conference on Data Intelligence and Cognitive Informatics (ICDICI), pp. 463–470, IEEE, 2024. [19] Alzu’bi, A., Younis, L.B., and Madain, A., “An interactive attribute-preserving fashion recommendation with 3D image-based virtual try-on,” International Journal of Multimedia Information Retrieval, vol. 12, no. 2, p. 24, 2023. [20] Hareesh Kumar, U.R., and Ambeesh Mon, S., “Virtual Try On,” in Industry 4.0 and Climate Change, pp. 189, 2022.

Copyright

Copyright © 2025 Mr. Ankur Rao, Mr. Himanshu Kashyap, Ms. Kaushiki Mishra, Mr. Shivam Mani Tripathi, Asst. Prof. Chaynika Srivastava. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.