Target detection in side-scan sonar images: expert fusion reduces false alarms

We integrate several key components of a pattern recognition system for a mine-like targets detection problem. These include several image enhancements, postprocessing and multi-expert fusion. The image enhancement includes wavelet de-noising and classical computer vision methods such as nonlinear and adaptive equalization and other filters. Our approach attempts to make the different experts as independent as possible so as to maximally exploit their fusion. Results are given on a shallow water mine-like targets detection problem using sonar data.