Improvement and Simulation Analysis of Wavelet Threshold Algorithm

Jun Guo, Yao Wang, Wenjun Yi

By studying the traditional threshold function , it is found that the hard threshold function is discontinuous , the pseudo - Gibbs phenomenon occurs , and the soft threshold function is too much eliminating the detail coefficient , which causes the loss of high - frequency signal . The simulation experiment of Wavelet threshold noise reduction for different sonar signals is carried out. The experimental results show that the improved threshold function is better than the conventional algorithm , and the noise - reducing signal has higher SNR and smaller RMSE.