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{172021,
        author = {Naveen Nishal Singuru and Kanumuri Nitin Varma and Macha Naga Sai Vignesh},
        title = {Human Pose Keypoint Detection for Apparel Sizing},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {1790-1799},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172021},
        abstract = {Automated apparel sizing is a crucial advancement for modern e-commerce and retail, aiming to enhance customer satisfaction by reducing size-related mismatches. This paper presents an innovative system for automated apparel sizing using state-of-the-art keypoint detection models, MoveNet and MediaPipe. The proposed system accurately estimates critical garment measurements, including sleeve length, shoulder width, and pant length, by leveraging precise human pose estimation and pixel-to-centimeter calibration. Experimental results demonstrate the system's high accuracy, with minimal errors compared to manual measurements, and its real-time efficiency, making it suitable for scalable deployment. This work bridges the gap between human pose detection and apparel sizing, offering a robust solution for the industry.},
        keywords = {Automated Apparel Sizing, Keypoint Detection, MoveNet, MediaPipe, Human Pose Estimation, Sleeve Length, Shoulder Width, Pant Length, Pixel-to-Centimeter Calibration.},
        month = {January},
        }