|Target classification from HR sonar images|Lopera, O.; Dupont, Y. (2013). Target classification from HR sonar images, in: IEEE OCEANS 2013 Norway. Proceedings of a meeting held 10-14 June 2013, Bergen, Norway. Oceans (New York), CFP13OCF: pp. 6 pp. hdl.handle.net/10.1109/OCEANS-Bergen.2013.6608183
In: IEEE (2013). OCEANS 2013 Norway. Proceedings of a meeting held 10-14 June 2013, Bergen, Norway. Oceans (New York), CFP13OCF. IEEE: New York. ISBN 978-1-479-90002-2. 1646 (2 Vols) pp., more
In: Oceans (New York). IEEE: New York. ISSN 0197-7385, more
This paper presents two integrated techniques for target classification from high-resolution (HR) sonar images. Both recognition procedures start with a despeckling algorithm based on the anisotropic diffusion filter. As a second step, a fuzzymorpho-based segmentation procedure is applied to the filtered images, which partitions the image into highlights and shadow areas. A number of geometrical features are extracted from these areas, and are then used to classify targets using two techniques: (i) a Markov Chain Monte Carlo (MCMC) approach and (ii) a Decision Tree Classifier (DTC) . A comparison of both recognition techniques is drawn, and classification performance is estimated by ROC curves. Very promising results are obtained.