Anomaly detection algorithms applied to hyperspectral imagery are able to identify objects from a natural environment without any prior knowledge about them based on the statistical analysis. RX detection algorithm is one of the most important detection algorithms in anomaly detection. It can detect targets with low probability of occurrence. In this paper, we introduce pre-processing techniques for the hyperspectral image cube, Filtering and Whitening, to enhance the performance of the RX algorithm. These preprocessing techniques are done to ensure the requirements of the RX algorithm. Statistical analysis of the image cube is made before and after these pre-processing. The performance is
investigated in terms of the detection probability, and the false alarm ratio (ROC curves).