Improved Mathematical Morphology Difference Filter for Signal Noise Reduction and Feature Extraction

Aiming at the problem of frequency confusing in signal noise reduction and feature extraction, an improved mathematical morphology Difference Filter (IDIF) for signal noise reduction and feature extraction is proposed in this paper. According to the characteristics of the internal structure of the difference filter, it shows that the traditional morphological difference filter (DIF) can not identify the positive and negative impact characteristics at the same time, which leads to the difficulty of recognizing the frequency confusion. By improving the structure of the filter, the improved filter is used to identify the positive and negative impact characteristics ability. In order to verify the effectiveness of the method, the simulation experiment is carried out and make comparison with the DIF method. The experimental result shows that the improved morphological difference filter can distinguish the positive and negative characteristics, and avoid the frequency confusion.