05958703

a

05958703 Fuertes, Juan Jos\'e Travieso, Carlos M. Alonso, J.B. Automatic identification approach for sea surface bubbles detection. Corchado, Emilio (ed.) et al., Hybrid artificial intelligent systems. 6th international conference, HAIS 2011, Wroclaw, Poland, May 23--25, 2011. Proceedings, Part I. Berlin: Springer (ISBN 978-3-642-21218-5/pbk). Lecture Notes in Computer Science 6678. Lecture Notes in Artificial Intelligence, 75-82 (2011). 2011 Berlin: Springer EN Sea Surface Image Bubble Detection Image Processing Pattern Recognition

doi:10.1007/978-3-642-21219-2_11

Summary: In this work a novel system for bubbles detection on sea surface images is presented. This application is basic to verify radiometer satellite systems which are used to the study of the floor humidity and the sea salinity. 160 images of 8 kinds of salinity have been processed, 20 per class. Two main steps have been implemented: image pre-processing and enhancing in order to improve the bubbles features, and segmentation and bubbles detection. A combination system has been performed with Support Vector Machines (SVM) in order to detect the sea salinity, showing a recognition rate of 95.43\%.