Work

Computationally Efficient Transfer Learning Pipeline for Oil Palm Fresh Fruit Bunch Defect Detection

Year: 2025

Type: article

Abstract: The present study addresses the inefficiencies of the manual classification of oil palm fresh fruit bunches (FFBs) by introducing a computationally efficient alternative to traditional deep learning approaches that require extensive retraining and large datasets. Using feature-based transfer learning, where pre-trained Convolutional Neural Network architectures, namely EfficientNet_B0, EfficientNet_B4, ResNet152, and VGG16, serve as fixed feature extractors coupled with the Logistic Regression classifier, this research evaluated the performance on a dataset of 466 images categorized as defective or non-defective. The results demonstrate a robust classification performance across all architectures, with the EfficientNet_B4–LR pipeline achieving an exceptional accuracy value of 96.81%, which was further enhanced through hyperparameter optimization. This confirms that feature-based transfer learning offers a reliable, resource-efficient, and practical solution for automated FFB defect detection that can significantly benefit the palm oil industry by providing a scalable alternative to subjective manual-grading methods.

Source: Technologies

DOI: 10.3390/technologies13060234

Authors: Yang Luo, Anwar P. P. Abdul Majeed, Zaid Omar, Saad Aslam, Yi Chen

Institutions: Xi’an Jiaotong-Liverpool University, Sunway University, University of Technology Malaysia

Language: English

Topic: Smart Agriculture and AI

Subfield: Plant Science

Field: Agricultural and Biological Sciences

Domain: Life Sciences

SDGs: Zero hunger, Industry, innovation and infrastructure

Open Access status: gold

Estimated APC paid: $1,930