RKHS Bayes discriminant: a subspace constrained nonlinear feature projection for signal detection
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
In this paper a non-linear matched filter is introduced for target detection in hyperspectral imagery which is implemented by using the ideas in kernel-based learning theory. The proposed non-linear matched filter exploits the notion that performing matched filtering in a non-linear feature space of high dimensionality increases the probability of detection. Defining matched filter in a kernel feature space is equivalent to a non-linear matched filter in the original input space which allows the higher order correlation between the spectral bands to be exploited. It is also shown that the non-linear matched filter can easily be implemented using the ideas of kernel functions. The kernel version of the non-linear matched filter is implemented and simulation results are shown to outperform the linear version.