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{193740,
        author = {Mrs. S Prathima and Aragonda Anusha and Thathireddy Lokitha and Nimmakayala Hemanth Kumar and Puchakatla Mohan Krishna},
        title = {Automated Parcel Damage Detection Using Computer Vision And Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {1968-1975},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193740},
        abstract = {The inspection of parcel damage is one of the processes of logistics and supply chain systems because damaged shipment will lead to financial loss and customer dissatisfaction. The current inspection approaches are largely manual and conventional rule- based image processing which are slow, inconsistent, and have a sensitivity to changes in lighting and packaging conditions. This project is aimed at resolving these problems through offering an automated parcel damage detection system through the use of computer vision and deep learning methods. The method is based on the Convolutional Neural Network (CNN) and Restet-34 architecture, which is designed to automatically extract features that are considered significant of parcel images and categorize them as damaged or undamaged. Deep residual network (ResNet-34) contains skip connections that allow it to better extract features as well as avoids the vanishing gradient issues and boosts the classification accuracy. The system is able to detect visible forms of damage like cracks, scratches and deformation. The proposed System is more accurate, robust, and scalable in comparison to the traditional approaches, which is why it can be used in the modern logistics and e-commerce settings in real-time.},
        keywords = {Parcel Damage Detection, Computer Vision, Deep Learning, Convolutional Neural Network (CNN), ResNet- 34, Image Classification},
        month = {March},
        }