COMPARACIÓN DE NUEVE ALGORITMOS DE MÁQUINAS DE APRENDIZAJE CON APLICACIONES EN LA DETECCIÓN DE ARRECIFE DE CORAL

This work focuses on the comparison of nine machine learning algorithms for developing a coral reef detector. This detector has two parts: feature extraction that uses Gabor Wavelet filters, and feature classification that uses machine learning based on Neural Networks. We compare the accuracy and running time of nine machine learning algorithms, whose result was the selection of the Decision Trees algorithm. We implement the bank of Gabor Wavelets filters using C++ and the OpenCV library. We use a database of 621 images of coral reef in Belize (110 images for training and 511 images for testing). Our coral detector performs 70ms of running time with 70% of accuracy.