Copyright © 2025 Authors retain the copyright of this article. This article 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.

@article{165741,
        author = {Neeraj Kumar and Ashish Jha and Saniya Mulla and Aiden Samuel},
        title = {EthniTry: A Deep Learning Approach to Image-Based Virtual Try-On for Indian Ethnic Apparel},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {1},
        pages = {2122-2126},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=165741},
        abstract = {Online shopping for Indian ethnic attire like sarees, lehengas, and kurtas is challenging due to intricate styles and fits. EthniTry, an image-based virtual try-on system, addresses these challenges with deep learning technology. It segments body and clothing regions, then warps and overlays the clothing item on the user's image, preserving details like embroidery and patterns. EthniTry uses a diverse dataset of Indian ethnic wear, normalizes images, and employs data augmentation to enhance robustness. The system features a pre-trained DeepLabV3+ model for body segmentation and advanced warping techniques for intricate designs. User feedback mechanisms improve adaptability to various body types and garment styles. Evaluations show EthniTry enhances the online shopping experience for ethnic clothing, bridging traditional in-store shopping with modern e-commerce. This system empowers consumers, offering a reliable and engaging way to explore and purchase Indian ethnic wear online.},
        keywords = {Deep Learning (DL), DeepLabV3+ (DLV3+), Image Segmentation (IS), Virtual Try-On (VTO).},
        month = {June},
        }