Image Denoising Using Wavelet Transform

Abstract

Image Denoising method is developed according to the characteristics of energy distribution of noise and wavelet transform. In the first step, through wavelet transform with higher scale, noisy image is decomposed, further in the second step, the square margin of White Gaussian Noise (WGN) or Additive White Gaussian Noise (AWGN) and threshold in high frequency coefficient of wavelet transform with dissimilar scale are shown separately. The coefficients are compared with different values of threshold. At the end, after taking inverse wavelet transform for all coefficient, reconstructed image has been achieved. Experimental results show that the noise is removed from image efficiently and the maximum image information is kept saved.