Hyper Spectral Imaging (HSI) is a powerful approach used in far flung sensing packages that captures spatially contiguous set of spectrum statistics from a scene. HSI information incorporates beneficial facts about the goals within the scene; however, due to noise and various distortions, it can be tough to discover those objectives. Spatial filtering is a method used to reduce undesirable noise in images if you want to make goal identity easier and extra accurate. On this paper, we endorse a brand new technique evolved for applying spatial filters on HSI pics that utilizes a spatially adaptive sigma clear out to successfully lessen noise and improve target identity accuracy. The advanced method correctly carries spatial variability within the filter length and clear out parameters to obtains progressed goal discrimination overall performance. The proposed technique is evaluated the use of both simulated and actual HSI records sets and effects display progressed target accuracy when as compared to traditional spatial filters.