Towards Highly Accurate Coral Texture Images Classification Using Deep Convolutional Neural Networks and Data Augmentation

TL;DR

This paper develops a highly accurate coral texture image classification model using deep CNNs, data augmentation, and transfer learning, achieving state-of-the-art results on existing datasets despite inherent data challenges.

Contribution

It evaluates various CNN architectures, data augmentation, and transfer learning to improve coral species classification accuracy, setting new benchmarks.

Findings

ResNet variations achieved state-of-the-art accuracy.

Data augmentation improved model robustness.

Transfer learning enhanced classification performance.

Abstract

The recognition of coral species based on underwater texture images pose 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 reason, 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 analyzed 1) several Convolutional Neural Network (CNN) architectures, 2) data augmentation techniques and 3) transfer learning. We have achieved the state-of-the art accuracies using different variations of ResNet on the two current coral texture datasets, EILAT and RSMAS.