Zhu Yanmin, Hang Yeung Chok, Lam Edmund Y
Appl Opt. 2021 Feb 1;60(4):A38-A47. doi: 10.1364/AO.403366.
We devise an inline digital holographic imaging system equipped with a lightweight deep learning network, termed CompNet, and develop the transfer learning for classification and analysis. It has a compression block consisting of a concatenated rectified linear unit (CReLU) activation to reduce the channels, and a class-balanced cross-entropy loss for training. The method is particularly suitable for small and imbalanced datasets, and we apply it to the detection and classification of microplastics. Our results show good improvements both in feature extraction, and generalization and classification accuracy, effectively overcoming the problem of overfitting. This method could be attractive for future in situ microplastic particle detection and classification applications.
我们设计了一种配备轻量级深度学习网络（称为CompNet）的在线数字全息成像系统，并开发了用于分类和分析的迁移学习。它有一个由级联整流线性单元（CReLU）激活组成的压缩块以减少通道数量，以及用于训练的类别平衡交叉熵损失。该方法特别适用于小型和不平衡数据集，我们将其应用于微塑料的检测和分类。我们的结果在特征提取、泛化和分类准确性方面都有显著提高，有效克服了过拟合问题。这种方法对于未来的原位微塑料颗粒检测和分类应用可能具有吸引力。
