Rician noise reduction by combining mathematical morphological operators through genetic programming

摘要: We propose a genetic programming (GP)-based approach for noise reduction from magnetic resonance imaging (MRI). An optimal composite morphological supervised filter (F ocmsf ) is developed through certain number of generations by combining gray-scale mathematical (MM) operators under fitness criterion. The proposed method does not need any prior information about the variance. improved performance investigated using simulated and real MRI datasets. Comparative analysis demonstrates superiority GP-based scheme over existing approaches.