Journal of Image Processing & Pattern Recognition Progress Original Research

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

  1. Suraj Mohit Yadav Computer Engineering, A.P. Shah Institute of Technology, Thane
  2. Tejaswini Sanjay Todkar Computer Engineering, A.P. Shah Institute of Technology, Thane
  3. Shivam Bhikaji Thorat Computer Engineering, A.P. Shah Institute of Technology, Thane
  4. Mohammad Jarjish Suleman Siddibapa Computer Engineering, A.P. Shah Institute of Technology, Thane
  5. Ashvini Gaikwad Department of Computer Engineering, A.P. Shah Institute of Technology, Thane
  6. Rushikesh Nikam Department of Computer Engineering, A.P. Shah Institute of Technology, Thane

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

References (11)

  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.

Read more of it

Subscribe to one journal or build your own list of several. One invoice, one payment, access for a full year.

Subscribe to journals →

Publish your article

Peer-reviewed journals across every subject, with open access options. Send your manuscript to the right editor today.

Publish with us → Calculate your APC
Support