Automated CNN Based Coral Reef Classification Using Image Augmentation and Deep Learning
A critical issue faced by the marine scientist is to classify underwater images describing coral benthic cover. Typically, scientists take underwater imagery using high-resolution cameras and further analysis on these corals and marine species is done on land (preferably a laboratory) and by visual inspection. However, the analysis is time consuming, since the first step, which is the classification of corals, is an intensive activity by taxonomic experts. This traditional manual classification method is difficult to automate or quicken which is problematic given the high volume of images. In this work, the fundamental analysis is discussed by using available techniques such as deep learning (DL) and Convolutional Neural Network (CNN). It is required to find an easier, efficient and faster way to automate the classification of corals. This task is complicated, since most of the common coral
species look similar to one another. For reasons of structural diversity, it is easier to differentiate other forms of marine life such as fish and stingrays. This paper is based on the difficult but important Scleractinian (Stony) corals only. A technique recommended is investigated further at structural level such as branching corals. Verification result proves that the training and testing data are almost similar, thus the proposed technique is capable to learn and predict correctly.
Keywords: Coral classification, CNN, Automation, Deep learning, RGB approach.
S. Sharan, Harsh, S. Kininmonth, U. Mehta, "Automated CNN Based Coral Reef Classification Using
Image Augmentation and Deep Learning", Engineering Intelligent Systems, vol. 29 no. 4, pp. 253-261,