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{198077,
        author = {Sriraam H M and Subasri K and Sankar Balaji D and Priyadharsheni J M},
        title = {Vision-Based Size Evaluation and Box Selection System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {8060-8066},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198077},
        abstract = {In many small-scale and medium-scale packaging industries, the process of selecting an appropriate box for a product is still performed manually. Workers typically measure the product dimensions using simple tools and then choose a suitable packaging box based on estimation or experience. This traditional approach often leads to inaccurate measurements, improper box selection, material wastage, and increased processing time. Oversized boxes result in unnecessary use of cardboard and packaging fillers, while undersized boxes may damage the product or require repackaging. These issues reduce operational efficiency and increase overall packaging costs. To address these challenges, this project proposes a vision-based size evaluation and box selection system that automates the measurement and decision-making process. The main objective of the system is to accurately determine the dimensions of an object and automatically recommend the most appropriate box size for packaging. The proposed solution uses a Raspberry Pi- controlled edge detection system, where a camera captures the image of the object placed on a platform. Image processing techniques, particularly edge detection algorithms, are applied to identify the boundaries of the object and calculate its dimensions such as length, width, and height. Based on these calculated dimensions, the system evaluates the required packaging size and classifies it into predefined box categories such as small, medium, or large. The results are then displayed through a web- based interface for easy monitoring and verification. By automating the size evaluation and box selection process, the system significantly reduces manual effort, minimizes packaging material wastage, and decreases the time required for packaging operations. Additionally, it improves accuracy and consistency in box selection, thereby enhancing overall efficiency in the packaging workflow. The implementation of such an automated vision-based system can support industries in optimizing packaging resources, reducing operational costs, and improving productivity. Therefore, this project provides a practical and scalable solution that can greatly benefit the modern packaging industry.},
        keywords = {Raspberry Pi, Edge Detection, Computer Vision, Size Evaluation, Box Selection System, Packaging Automation, Image Processing, Industrial Packaging Efficiency.},
        month = {April},
        }