Abstract: This article mainly studies the wavelet threshold image denoising method in image denoising.The advantages and disadvantages of hard threshold denoising and soft threshold denoising in practical applications are studied.Combined with the advantages of these two methods,an improved threshold image denoising method is proposed based on hard threshold denoising and soft threshold denoising.For the Lena images of 256×256,the obtained peak signal-to-noise ratio(PSNR)of the improved threshold method was 1.63% and 1.59% higher than that of the soft threshold method and the hard threshold method,respectively.The results show that the improved threshold image denoising method can achieve a better denoising effect compared with the hard threshold denoising and the soft threshold denoising method when the appropriate control system values are selected.