A Comparative Analysis of Machine Learning Techniques for Fruit Defect Detection Systems

Year : 2024 | Volume : 11 | Issue : 03 | Page : 37 47
    By

    Suraj Mohit Yadav,

  • Tejaswini Sanjay Todkar,

  • Shivam Bhikaji Thorat,

  • Mohammad Jarjish Suleman Siddibapa,

  • Ashvini Gaikwad,

  • Rushikesh Nikam,

  1. Student, Computer Engineering, A.P. Shah Institute of Technology, Thane, Maharashtra, India
  2. Student, Computer Engineering, A.P. Shah Institute of Technology, Thane, Maharashtra, India
  3. Student, Computer Engineering, A.P. Shah Institute of Technology, Thane, Maharashtra, India
  4. Student, Computer Engineering, A.P. Shah Institute of Technology, Thane, Maharashtra, India
  5. Assistant Professor, Department of Computer Engineering, A.P. Shah Institute of Technology, Thane, Maharashtra, India
  6. Assistant Professor, Department of Computer Engineering, A.P. Shah Institute of Technology, Thane, Maharashtra, India

Abstract

With evolving technologies in machine learning, significant advancements have been made in the livestock industry, helping to reduce waste, increase yield, achieve cost savings, and improve competitiveness in the marketplace. Fruit defect detection models support precision agriculture by providing valuable data for decision-making and enhancing overall efficiency through automated inspection processes. This study implements and comparatively evaluates machine learning models including MobileNetV2, a custom-designed convolutional neural network (CNN) model, ResNet50, and VGG16 to improve the accuracy of defect detection in fruits such as bananas, apples, and oranges. MobileNetV2 achieves competitive accuracy while ensuring computational efficiency, making it well-suited for environments with limited resources. The custom CNN model addresses the specific intricacies of fruit defect detection, showcasing adaptability across various fruit types. ResNet50 and VGG16, with their deep architectures, exhibit robust performance in capturing intricate features for enhanced defect identification. Comparative analysis employs metrics such as precision, recall, and F1 score to quantitatively assess each model’s accuracy. This research contributes to the growing body of knowledge in fruit defect detection and serves as a valuable resource for practitioners implementing machine learning models tailored to specific fruit inspection needs, ultimately advancing precision agriculture and automated fruit quality assessment.

Keywords: MobileNetV2, ResNet50, VGG16, custom-made CNN model, fruit defect detection

[This article belongs to Journal of Image Processing & Pattern Recognition Progress ]

How to cite this article:
Suraj Mohit Yadav, Tejaswini Sanjay Todkar, Shivam Bhikaji Thorat, Mohammad Jarjish Suleman Siddibapa, Ashvini Gaikwad, Rushikesh Nikam. A Comparative Analysis of Machine Learning Techniques for Fruit Defect Detection Systems. Journal of Image Processing & Pattern Recognition Progress. 2024; 11(03):37-47.
How to cite this URL:
Suraj Mohit Yadav, Tejaswini Sanjay Todkar, Shivam Bhikaji Thorat, Mohammad Jarjish Suleman Siddibapa, Ashvini Gaikwad, Rushikesh Nikam. A Comparative Analysis of Machine Learning Techniques for Fruit Defect Detection Systems. Journal of Image Processing & Pattern Recognition Progress. 2024; 11(03):37-47. Available from: https://journals.stmjournals.com/joipprp/article=2024/view=177859


References

  1. Wang L, Li A, Tian X. Detection of fruit skin defects using machine vision system. In: Proceedings of the 2013 Int Conf Bus Intell Financ Eng. 2013. p. 44–8. DOI: 10.1109/BIFE.2013.11.
  2. Azizah LM, Umayah SF, Riyadi S, Damarjati C, Utama NA. Deep learning implementation using convolutional neural network in mangosteen surface defect detection. In: Proceedings of the 2017 IEEE Int Conf Control Syst Comput Eng. 2017. p. 242–6. DOI: 10.1109/ICCSCE.2017.8284412.
  3. Dong K, Zhou C, Ruan Y, Li Y. MobileNetV2 model for image classification. In: Proceedings of the 2020 Int Conf Inf Technol Comput Appl. 2020. p. 476–80. DOI: 10.1109/ITCA52113.2020.
  4. Kukreja V, Dhiman P. A deep neural network based disease detection scheme for citrus fruits. In: Proceedings of the 2020 Int Conf SMART Electron Commun. 2020. p. 97–101.
  5. De Luna RG, Dadios EP, Bandala AA, Vicerra RRP. Tomato fruit image dataset for deep transfer learning-based defect detection. In: Proceedings of the 2019 IEEE Int Conf Cybern Intell Syst Robot Autom Mechatron. 2019. p. 356–61. DOI: 10.1109/CIS-RAM47153.2019.9095778.
  6. Satpute MR, Jagdale SM. Automatic fruit quality inspection system. In: Proceedings of the 2016 Int Conf Invent Comput Technol. 2016. p. 1–4. DOI: 10.1109/INVENTIVE.2016.7823207.
  7. Wang H, Mou Q, Yue Y, Zhao H. Research on detection technology of various fruit disease spots based on mask R-CNN. In: Proceedings of the 2020 IEEE Int Conf Mechatron Autom. 2020. p. 1083–7. DOI: 10.1109/ICMA49215.2020.9233575.
  8. Chaudhary L, Yogesh Y. A comparative study of fruit defect segmentation techniques. In: Proceedings of the 2019 Int Conf Issues Chall Intell Comput Technol. 2019. p. 1–4. DOI: 10.1109/ICICT46931.2019.8977692.
  9. Kalia P, Garg A, Kumar A. Fruit quality evaluation using machine learning: A review. In: Proceedings of the 2019 Int Conf Intell Comput Instrum Control Technol. 2019. p. 952–6.
  10. Singhal P, Dubey AK, Goyal A. A comparative approach for image segmentation to identify the defected portion of apple. In: Proceedings of the 2017 Int Conf Reliab INFOCOM Technol Optim. 2017. p. 604–8.
  11. Ren A, Zahid A, Zoha A, Shah SA, Imran MA, Alomainy A, et al. Machine learning driven approach towards the quality assessment of fresh fruits using non-invasive sensing. IEEE Sensors J. 2020;20:2075–83. DOI: 10.1109/JSEN.2019.2949528.
Regular Issue Subscription Original Research
Volume 11
Issue 03
Received 27/06/2024
Accepted 03/10/2024
Published 11/10/2024
624

Login


My IP

PlumX Metrics