Modelling of Long Wavelength Detection of Objects Using Elman Network Modified Covariance Combination

The problem of spatially detection and imaging of closely separated buried objects is investigated. A high resolution modified covariance method is employed. A recurrent neural network is used as a preprocessing technique to decrease the effect of concealing media on the results. The in-line holography is applied to increase the signal to noise ratio. Different concealing media and different values of signal to noise ratio are used to investigate the performance of such combination experimental results show that pre-processing the noisy data with recurrent neural network improves the performance.