Texture Analysis of Seabed Images to Quantify the Presence of Posidonia Oceanica Using Logistic Model Trees

Author Miquel Massot Campos
Supervisor/s Gabriel Oliver Codina
In Universitat de les Illes Balears, 2013.

An automatic classifier algorithm has been designed to assess the population of Posidonia Oceanica over a set of underwater images taken at Palma Bay. Laws’ energy filters and statistical descriptors of the Gray Level Co-occurrence Matrix have been used to correctly classify the input image patches in two classes: Posidonia Oceanica or not Posidonia Oceanica. The input images have been first preprocessed and splitted in three different patch sizes in order to find the patch size to classify this seagrass. From all the attributes obtained in these patches, a best subset algorithm has been run to choose the optimal set of attributes. Then a decision tree classifier has been trained. The classifier was made by training a Logistic Model Tree from 125 pre-classified images. This classifier was finally tested on 100 new images. The classifier outputs gray level images where black color indicates Posidonia Oceanica presence and white no presence. Intermediate values are obtained by overlapping the processed patches, resulting in a smoother final result. This images can be merged in an offline process to obtain population density maps.

Uso de cookies

Este sitio web utiliza cookies para que usted tenga la mejor experiencia de usuario. Si continúa navegando está dando su consentimiento para la aceptación de las mencionadas cookies y la aceptación de nuestra política de cookies, pinche el enlace para mayor información.

Aviso de cookies