Mine Classification of Sonar Image Using K-NN Method

Automatic Detection And Classification (ADAC) is a system to detect and classify the underwater objects for mine hunting applications. The segmentation, feature extraction, and classification are the main steps involved in the system. Two design issues in the system, the selection of the optimal classifier and the selection of the optimal feature subset. The comparison of classification systems is based on a pre-selected feature set. A different subset might yield a different ranking. The K-NN(nearest neighbour) method that assesses the classifier performance without constraints to any specific feature subset. In the classifier system a feature selection algorithm estimates the optimal feature subset. A new extension of the Sequential Forward Selection (SFS) and the Sequential Forward Floating Selection (SFFS) methods, overcomes their main limitations, the nesting problem. Option D is used to store the best alternative at each iteration. The performance of the so-called DSFS and D-SFFS is tested on simulated and real data. The methods are also used for designing an ADAC system for mine hunting based on synthetic aperture sonar images.The new k-nn method provide better performance than that the previous LDA method.