Abstract

We use a feedforward backpropagation neural network to classify close-up images of coral reef components into three benthic categories: living coral, dead coral and sand. We have achieved a success rate of 86.5% (false positive = 6.7%) for test images that were not in the training set which is high considering that corals occur in an immense variety of appearance. Color and texture features derived from video stills of coral reef transects from the Great Barrier Reef were used as inputs to the network. We also developed a rule-based decision tree classifier according to how marine scientists classify corals from texture and color, and obtained a lower recognition rate of 79.7% for the same set of images.

©2005 Optical Society of America

Development and evaluation of a genetic algorithm-based ocean color inversion model for simultaneously retrieving optical properties and bottom types in coral reef regions

Chih-Hua Chang, Cheng-Chien Liu, Hsiao-Wei Chung, Long-Jeng Lee, and Wen-Chang Yang
Appl. Opt. 53(4) 605-617 (2014)

Fluorescent image classification by major color histograms and a neural network

M. Soriano, L. Garcia, and C. Saloma
Opt. Express 8(5) 271-277 (2001)

Model for deriving benthic irradiance in the Great Barrier Reef from MODIS satellite imagery

Marites M. Magno-Canto, Lachlan I. W. McKinna, Barbara J. Robson, and Katharina E. Fabricius
Opt. Express 27(20) A1350-A1371 (2019)

Multiple light scattering and absorption in reef-building corals

Emiliano Terán, Eugenio R. Méndez, Susana Enríquez, and Roberto Iglesias-Prieto
Appl. Opt. 49(27) 5032-5042 (2010)

Classification of marine microalgae using low-resolution Mueller matrix images and convolutional neural network

Zhidi Liu, Ran Liao, Hui Ma, Jiajin Li, Priscilla T. Y. Leung, Meng Yan, and Jiarui Gu
Appl. Opt. 59(31) 9698-9709 (2020)