Image Processing and Classification for Lemon Yield Optimization for smart farming

  • Unique Paper ID: 170148
  • Volume: 11
  • Issue: 6
  • PageNo: 3495-3498
  • Abstract:
  • This study focused on the automated classification of lemon ripeness using advanced deep learning techniques to support agricultural and food processing applications. A comprehensive dataset of lemon images was curated, with each image labeled as either "raw" or "ripe." The collection of data was divided into test, validation, and training categories to ensure robust model evaluation. Leveraging transfer learning, the VGG16 model that has already been trained, initially trained on the extensive Picture-net dataset, was adjusted for the binary classification of lemon ripeness. To enhance the model's functionality even more and generalization, various data augmentation methods—like flipping, scaling, and rotation—were used. After training, The model's accuracy was high, reaching of 97% on the test set, proving how well it works in distinguishing ripe lemons from unripe ones. This promising demonstrates how deep learning may be used to automating fruit classification processes, reducing labor and enhancing efficiency in agricultural workflows. Future research could investigate alternative deep learning architectures and hyperparameter optimization to achieve even higher accuracy and adaptability across different fruit types and conditions.

Copyright & License

Copyright © 2025 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.

BibTeX

@article{170148,
        author = {Shraddha Rani Sonkalihari and Deepak Sharma},
        title = {Image Processing and Classification for Lemon Yield Optimization for smart farming},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {3495-3498},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=170148},
        abstract = {This study focused on the automated classification of lemon ripeness using advanced deep learning techniques to support agricultural and food processing applications. A comprehensive dataset of lemon images was curated, with each image labeled as either "raw" or "ripe." The collection of data was divided into test, validation, and training categories to ensure robust model evaluation. Leveraging transfer learning, the VGG16 model that has already been trained, initially trained on  the extensive Picture-net dataset, was adjusted for the binary classification of lemon ripeness. To enhance the model's functionality even more and generalization, various data augmentation methods—like flipping, scaling, and rotation—were used. After training, The model's accuracy was high, reaching of 97% on the test set, proving how well it works in distinguishing ripe lemons from unripe ones. This promising demonstrates how deep learning may be used to automating fruit classification processes, reducing labor and enhancing efficiency in agricultural workflows. Future research could investigate alternative deep learning architectures and hyperparameter optimization to achieve even higher accuracy and adaptability across different fruit types and conditions.},
        keywords = {Lemon Ripeness Classification, Deep Learning, VGG16, Data Augmentation, Agricultural Automation},
        month = {December},
        }

Cite This Article

  • ISSN: 2349-6002
  • Volume: 11
  • Issue: 6
  • PageNo: 3495-3498

Image Processing and Classification for Lemon Yield Optimization for smart farming

Related Articles