Copyright © 2026 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{187332,
        author = {S LAKSHMI DURGA and SHASHI CHANDANA B S and T SHREYA and VARSHINI S and SURAJ KUMAR B P},
        title = {FASH-TRY – Deep Learning Enabled Virtual Try-On and Image-Based Clothing Recommendation System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {4446-4452},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=187332},
        abstract = {FASH-TRY is a deep learning–based virtual try-on and clothing recommendation system designed to enhance online shopping through realistic apparel visualization and intelligent product discovery. The system integrates Computer Vision and Image Processing techniques to allow users to upload their images and virtually try on selected garments. Using a multi-stage CP-VTON pipeline consisting of human parsing, pose estimation, and geometric cloth warping the system generates natural and photo-realistic try-on results while preserving body shape, texture, and alignment. Human parsing with a JPP Net-based model segments body regions, and Open Pose extracts key points for accurate cloth fitting. To support apparel discovery, FASH-TRY employs a Content-Based Image Retrieval (CBIR) module. ResNet50 is used to extract deep visual features from garments, and K-Nearest Neighbors (KNN) identifies visually similar items based on color, pattern, and texture. The backend is built using Flask and SQLite3, with OpenCV handling ONNX and Protobuf model integrations. Experimental evaluation demonstrates that FASH-TRY improves user interaction, increases visualization accuracy, and provides efficient similarity-based recommendations. The system offers a scalable and practical solution for modern e-commerce platforms seeking enhanced personalization and virtual try-on capabilities.},
        keywords = {},
        month = {November},
        }