Improving plankton image classification using context metadata
Improving plankton image classification using context metadata
复制标题
DOI：
10.1002/lom3.10324
复制
发表时间：
2019-08-01
影响因子：
2.7
通讯作者：
Ohman, Mark D.
中科院分区：
文献类型：
--
作者：
Ellen, Jeffrey S.;Graff, Casey A.;Ohman, Mark D.
硬件和软件的进步使得原位浮游生物成像方法迅速普及，需要更有效的机器学习方法来进行图像分类。深度学习方法，如卷积神经网络（CNN），比传统的基于特征的监督机器学习算法有明显的改进，但需要仔细优化超参数和足够的训练集。在这里，我们记录了将CNN应用于浮游动物和海洋雪图像的一些最佳实践，并指出我们的结果与其他领域的当代深度学习结果的不同之处。我们通过合并不同类型的元数据来提高CNN分类器的性能，并说明如何在简单的连接之外吸收元数据。我们利用地理时间（例如，采样深度、位置、一天中的时间）和水文（例如，温度、盐度、叶绿素a）元数据，并显示任一类型本身或两者组合，可以大大降低错误率。结合上下文元数据也提高了我们评估的基于特征的分类器的性能：随机森林，极端随机树，梯度提升分类器，支持向量机和多层感知器。在我们的评估中，我们使用了来自一个新的原位Zooglider的350，000张原位图像的原始数据集（大约50%的海洋雪和50%的非雪分类为26个类别）。我们记录了渐进增加的性能与更多的计算密集型技术，如大幅加深的网络和人工增强的数据集。我们最好的模型在27类数据集上达到了92.3%的准确率。我们提供指导，进一步完善，可能会提供额外的收益，在分类器的准确性。
Advances in both hardware and software are enabling rapid proliferation of in situ plankton imaging methods, requiring more effective machine learning approaches to image classification. Deep Learning methods, such as convolutional neural networks (CNNs), show marked improvement over traditional feature-based supervised machine learning algorithms, but require careful optimization of hyperparameters and adequate training sets. Here, we document some best practices in applying CNNs to zooplankton and marine snow images and note where our results differ from contemporary Deep Learning findings in other domains. We boost the performance of CNN classifiers by incorporating metadata of different types and illustrate how to assimilate metadata beyond simple concatenation. We utilize both geotemporal (e.g., sample depth, location, time of day) and hydrographic (e.g., temperature, salinity, chlorophyll a) metadata and show that either type by itself, or both combined, can substantially reduce error rates. Incorporation of context metadata also boosts performance of the feature-based classifiers we evaluated: Random Forest, Extremely Randomized Trees, Gradient Boosted Classifier, Support Vector Machines, and Multilayer Perceptron. For our assessments, we use an original data set of 350,000 in situ images (roughly 50% marine snow and 50% non-snow sorted into 26 categories) from a novel in situ Zooglider. We document asymptotically increasing performance with more computationally intensive techniques, such as substantially deeper networks and artificially augmented data sets. Our best model achieves 92.3% accuracy with our 27-class data set. We provide guidance for further refinements that are likely to provide additional gains in classifier accuracy.