The multi-sensor fusion: image registration using artificial immune algorithm

The immune system is a cognitive system of complexity comparable to the brain and its computational algorithms suggest new solutions to engineering problems. Using immunological principles, an artificial immune algorithm is presented for the multi-sensor fusion image registration problem. The method uses receptor editing to escape from the local optima. The method applied to the registration problem shows good convergence results to the global minimum. Experimental results show the method to be efficient even in the presence of large amounts of noise.