Loddo Andrea, Di Ruberto Cecilia
Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124 Cagliari, Italy.
J Imaging. 2021 Aug 31;7(9):171. doi: 10.3390/jimaging7090171.
Computer vision techniques have become important in agriculture and plant sciences due to their wide variety of applications. In particular, the analysis of seeds can provide meaningful information on their evolution, the history of agriculture, the domestication of plants, and knowledge of diets in ancient times. This work aims to propose an exhaustive comparison of several different types of features in the context of multiclass seed classification, leveraging two public plant seeds data sets to classify their families or species. In detail, we studied possible optimisations of five traditional machine learning classifiers trained with seven different categories of handcrafted features. We also fine-tuned several well-known convolutional neural networks (CNNs) and the recently proposed SeedNet to determine whether and to what extent using their deep features may be advantageous over handcrafted features. The experimental results demonstrated that CNN features are appropriate to the task and representative of the multiclass scenario. In particular, SeedNet achieved a mean F-measure of 96%, at least. Nevertheless, several cases showed satisfactory performance from the handcrafted features to be considered a valid alternative. In detail, we found that the Ensemble strategy combined with all the handcrafted features can achieve 90.93% of mean F-measure, at least, with a considerably lower amount of times. We consider the obtained results an excellent preliminary step towards realising an automatic seeds recognition and classification framework.
由于计算机视觉技术具有广泛的应用，因此在农业和植物科学领域变得至关重要。特别是，种子分析可以提供有关其进化、农业历史、植物驯化以及古代饮食知识的有意义信息。这项工作旨在对多类种子分类背景下的几种不同类型特征进行详尽比较，利用两个公共植物种子数据集对其科或种进行分类。具体而言，我们研究了使用七种不同类别的手工制作特征训练的五个传统机器学习分类器的可能优化。我们还对几个著名的卷积神经网络（CNN）和最近提出的SeedNet进行了微调，以确定使用它们的深度特征是否以及在多大程度上可能比手工制作的特征更具优势。实验结果表明，CNN特征适用于该任务并且代表了多类场景。特别是，SeedNet至少实现了96%的平均F值。然而，在一些情况下，手工制作的特征表现出令人满意的性能，可被视为一种有效的替代方案。具体而言，我们发现结合所有手工制作特征的集成策略至少可以达到90.93%的平均F值，且所需时间要少得多。我们认为所获得的结果是朝着实现自动种子识别和分类框架迈出的出色初步步骤。
