Abstract: In view of the problems of low recognition accuracy, multiple extraction parameters and low real-time processing efficiency of existing coal gangue recognition and separation methods based on image processing, an automatic separation method of coal gangue based on wavelet transform was proposed. The method uses wavelet analysis to do noise reduction processing of coal and coal gangue image, and adopts constructing wavelet moment to extract and analyze features of coal and gangue, calculates the feature value, and find out the obvious differences of characteristic parameters between coal and gangue, the characteristic parameters can take as the basis of coal and gangue recognition. The experimental results show that the method improves the efficiency and of on-line identification and separation of coal and gangue with high accuracy.