Review of deep learning-based methods for non-destructive evaluation of agricultural products

Abstract

Deep Learning (DL) has emerged as a pivotal modelling tool in various domains because of its proficiency in learning distributed representations. Numerous DL algorithms have recently been proposed and applied to non-destructive testing (NDT) methods in agriculture. This study aimed to review the state-of-the-art applications of DL algorithms in NDT by analysing the application of DL to specific NDT applications and highlighting their contributions and challenges. It first presents a comprehensive overview of various NDT techniques that have been combined with DL in agricultural product evaluation, and then briefly describes their applications in diverse NDT tasks, such as image classification, object detection, image retrieval, and semantic segmentation. Second, this study addresses the ongoing challenges associated with data collection and fusion, model complexity, computational requirements, and robustness. Finally, future research directions are examined, underscoring the potential of novel neural network architectures and cross-disciplinary collaborations. This review aims to provide a clear understanding of the current state of DL-based NDT in agricultural product examinations and its prospects for the future.

© 2017 Elsevier Inc. All rights reserved.