Classification using a Radial Basis Function Neural Network on Side-Scan Sonar Data

Author

Skinner, Dana ; Foo, Simon Y.

Author_Institution

Florida State Univ., Tallahassee

fYear

2007

fDate

4-7 June 2007

Firstpage

1803

Lastpage

1806

Abstract

Detecting and classifying mines among natural formations and man-made debris along the sea floor can be a tedious task. To reduce operator dependency, an automated computer aided detection and classification system is needed. Our proposed automated system uses a two-step process. First the images are normalized and then a supervised learning method, radial basis function neural network (RBFNN), is applied to a side-scan sonar (SSS) data set. This method is able to extrapolate beyond the training data and successfully classify mine-like objects (MLOs).

Keywords

image classification; learning (artificial intelligence); mining; object detection; radial basis function networks; sonar imaging; automated computer aided detection; classification system; mine-like objects; radial basis function neural network; sea floor; side-scan sonar data; supervised learning; Costs; Flowcharts; Marine animals; Oceans; Radial basis function networks; Sea floor; Sonar applications; Supervised learning; Telecommunication traffic; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics, 2007. ISIE 2007. IEEE International Symposium on

Conference_Location

Vigo

Print_ISBN

978-1-4244-0754-5

Electronic_ISBN

978-1-4244-0755-2

Type

conf

DOI

10.1109/ISIE.2007.4374879

Filename

4374879