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{184347,
        author = {Chalapaka Mahendra and Dr. K. Venkata Ramana},
        title = {Food Quality Estimator for Fruits and Vegetables Using MobileNetV2 CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {4},
        pages = {1189-1193},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=184347},
        abstract = {Food loss and waste (FLW) of perishable fruits and vegetables is a major global issue. Inefficient quality assessment methods make this problem worse. This paper introduces a new, non-destructive food quality estimator designed specifically for fruits and vegetables. It uses the MobileNetV2 Convolutional Neural Network (CNN) model. MobileNetV2 features depthwise separable convolutions, inverted residuals, and linear bottlenecks. This design works well on devices with limited resources, like smartphones. It enables real-time, image-based quality assessment at various points in the supply chain. The approach emphasizes the need for high-quality, diverse datasets and strong pre-processing techniques, such as resizing, normalization, and extensive image augmentation. These steps ensure the model is precise and can adapt well. Additionally, transfer learning will be used to improve training efficiency and performance. The proposed system offers a scalable and affordable way to collect detailed quality data. This enhances supply chain efficiency, traceability, and risk management. For consumers, it leads to better food safety, reliable freshness, and smarter purchasing decisions. Overall, this research is crucial for global sustainability efforts by reducing food waste and improving food security, which contributes to a more resilient and fair food system.},
        keywords = {Food loss and waste (FLW), fruits and vegetables, MobileNetV2, Convolutional Neural Network, transfer learning, image augmentation, supply chain efficiency.},
        month = {September},
        }