Classifier selection and cover area estimation of hard bottom in underwater belt transect thumbnails

Authors

Micholo Lanz Billones Medrana ⋅ PH National Institute of Physics, University of the Philippines Diliman
Maricor Narvaez Soriano ⋅ PH National Institute of Physics, University of the Philippines Diliman

Abstract

lassifier implementations of k-nearest neighbor (KNN), support vector machines (SVM), logistic regression (LR), and a feedforward neural network (NN) are assessed in terms of their performance in the classification between hard and soft bottom cover from thumbnails of underwater image mosaics. Input features were chosen from a set of 7 texture descriptors and appropriate parameters were tuned to maximize performance. The maximum accuracy values are 89% for both SVM and LR classifiers in Calatagan AM, and 88.4 ± 4.5% for NN in Calatagan PM. The performance of the KNN classifier is low for both datasets at 88.3 ± 2.5% and 86.3 ± 1.7% for Calatagan AM and PM respectively, and with low recall values. Errors across all classifiers are within range of each other. An application to the estimation of hard bottom cover and mapping is discussed.

Downloads

Issue

2017: Proceedings of the 35th Samahang Pisika ng Pilipinas Physics Conference

Article ID

SPP-2017-1G-05

Section

Image and Signal Processing

Published

2017-06-07

How to Cite

[1]

MLB Medrana and MN Soriano, Classifier selection and cover area estimation of hard bottom in underwater belt transect thumbnails, Proceedings of the Samahang Pisika ng Pilipinas 35, SPP-2017-1G-05 (2017). URL: https://proceedings.spp-online.org/article/view/SPP-2017-1G-05.