An improved sea mine computer-aided-detection/computer-aided- classification (CAD/CAC) processing string has
been developed. The overall CAD/CAC processing string consists of pre-processing, subimage adaptive clutter
filtering (SACF), normalization, detection, feature extraction, repeated application of optimal subset feature selection,
feature orthogonalization and log-likelihood-ratio-test (LLRT) classification processing, and fusion processing blocks.
The classified objects of 3 distinct processing strings are fused using the classification confidence values as features and
either "M-out-of-N" or LLRT-based fusion rules. The utility of the overall processing strings and their fusion was
demonstrated with new very shallow water high-resolution sonar imagery data. The processing string detection and
classification parameters were tuned and the string classification performance was optimized, by appropriately selecting
a subset of the original feature set. Two significant fusion algorithm improvements were made. First, a new nonlinear
(Volterra) feature LLRT fusion algorithm was developed. Second, a repeated application of the subset Volterra feature
selection/feature orthogonalization/LLRT fusion block was utilized. It was shown that this cascaded Volterra feature
LLRT fusion of the CAD/CAC processing strings outperforms the "M-out- of-N," the baseline LLRT and single-stage
Volterra feature LLRT fusion algorithms, and also yields an improvement over the best single CAD/CAC processing
string, providing a significant reduction in the false alarm rate. Additionally, the robustness of cascade Volterra feature
fusion was demonstrated, by showing that the algorithm yields similar performance with the training and test sets.