Towards highly accurate coral texture images classification using deep convolutional neural networks and data augmentation

作者：

Highlights：

• Study the performance of promising CNNs in the classification of coral texture images.

• Analyze different types of transfer learning.

• Analyze data augmentation on the performance of the coral classification model.

• Experimental results outperform state-of-the-art methods needing human intervention.

• Generalize the best approach to other coral texture datasets.

摘要

•Study the performance of promising CNNs in the classification of coral texture images.•Analyze different types of transfer learning.•Analyze data augmentation on the performance of the coral classification model.•Experimental results outperform state-of-the-art methods needing human intervention.•Generalize the best approach to other coral texture datasets.

论文关键词：Coral images classification,Deep learning,Convolutional neural networks,Inception,ResNet,DenseNet

论文评审过程：Received 2 March 2018, Revised 4 August 2018, Accepted 6 October 2018, Available online 6 October 2018, Version of Record 15 October 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.10.010