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

• Published in: Expert systems with applications Vol. 118; pp. 315 - 328
• Main Authors: Gómez-Ríos, Anabel, Tabik, Siham, Luengo, Julián, Shihavuddin, ASM, Krawczyk, Bartosz, Herrera, Francisco
• Format: Journal Article
• Language: English
• Published: New York Elsevier Ltd 15.03.2019; Elsevier BV
• Subjects: Algorithms; Artificial neural networks; Classification; Convolutional neural networks; Coral images classification; Corals; Data augmentation; Datasets; Deep learning; DenseNet; Image classification; Inception; Machine learning; Neural networks; Object recognition; ResNet; Species classification; Subject specialists; Texture recognition; Deep learning; DenseNet; Inception; Convolutional neural networks; Coral images classification; ResNet
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2018.10.010

•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. [Display omitted] The recognition of coral species based on underwater texture images poses a significant difficulty for machine learning algorithms, due to the three following challenges embedded in the nature of this data: (1) datasets do not include information about the global structure of the coral; (2) several species of coral have very similar characteristics; and (3) defining the spatial borders between classes is difficult as many corals tend to appear together in groups. For this reasons, the classification of coral species has always required an aid from a domain expert. The objective of this paper is to develop an accurate classification model for coral texture images. Current datasets contain a large number of imbalanced classes, while the images are subject to inter-class variation. We have focused on the current small datasets and analyzed (1) several Convolutional Neural Network (CNN) architectures, (2) data augmentation techniques and (3) transfer learning approaches. We have achieved the state-of-the art accuracies using different variations of ResNet on the two small coral texture datasets, EILAT and RSMAS.